fix(bmad-module): harden source/remove/update paths and channel input

Address automated review findings on PR #2482:
- source.mjs: validate URL-derived subdir with safePathInsideRoot so a
  ../ subdir can't copy out of the shared clone cache; run cleanup() if
  the terminal copyDir throws so the temp working dir never leaks.
- install.mjs: reject unknown --channel values (e.g. a 'stabl' typo)
  instead of silently treating them as the 'next' default.
- remove.mjs / update.mjs: containment-check manifest/CLI-derived paths
  before destructive fs.rm / atomic swap, reusing safePathInsideRoot.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -13,13 +13,14 @@
       "name": "bmad-pro-skills",
       "source": "./",
       "description": "Next level skills for power users — advanced prompting techniques, agent management, and more.",
-      "version": "6.6.0",
+      "version": "6.8.0",
       "author": {
         "name": "Brian (BMad) Madison"
       },
       "skills": [
         "./src/core-skills/bmad-help",
         "./src/core-skills/bmad-brainstorming",
+        "./src/core-skills/bmad-customize",
         "./src/core-skills/bmad-spec",
         "./src/core-skills/bmad-party-mode",
         "./src/core-skills/bmad-shard-doc",
@@ -35,12 +36,13 @@
       "name": "bmad-method-lifecycle",
       "source": "./",
       "description": "Full-lifecycle AI development framework — agents and workflows for product analysis, planning, architecture, and implementation.",
-      "version": "6.6.0",
+      "version": "6.8.0",
       "author": {
         "name": "Brian (BMad) Madison"
       },
       "skills": [
         "./src/bmm-skills/1-analysis/bmad-product-brief",
+        "./src/bmm-skills/1-analysis/bmad-prfaq",
         "./src/bmm-skills/1-analysis/bmad-agent-analyst",
         "./src/bmm-skills/1-analysis/bmad-agent-tech-writer",
         "./src/bmm-skills/1-analysis/bmad-document-project",
@@ -49,18 +51,22 @@
         "./src/bmm-skills/1-analysis/research/bmad-technical-research",
         "./src/bmm-skills/2-plan-workflows/bmad-agent-pm",
         "./src/bmm-skills/2-plan-workflows/bmad-agent-ux-designer",
+        "./src/bmm-skills/2-plan-workflows/bmad-prd",
         "./src/bmm-skills/2-plan-workflows/bmad-create-prd",
         "./src/bmm-skills/2-plan-workflows/bmad-edit-prd",
         "./src/bmm-skills/2-plan-workflows/bmad-validate-prd",
-        "./src/bmm-skills/2-plan-workflows/bmad-create-ux-design",
+        "./src/bmm-skills/2-plan-workflows/bmad-ux",
         "./src/bmm-skills/3-solutioning/bmad-agent-architect",
+        "./src/bmm-skills/3-solutioning/bmad-architecture",
         "./src/bmm-skills/3-solutioning/bmad-create-architecture",
         "./src/bmm-skills/3-solutioning/bmad-check-implementation-readiness",
         "./src/bmm-skills/3-solutioning/bmad-create-epics-and-stories",
         "./src/bmm-skills/3-solutioning/bmad-generate-project-context",
         "./src/bmm-skills/4-implementation/bmad-agent-dev",
+        "./src/bmm-skills/4-implementation/bmad-investigate",
         "./src/bmm-skills/4-implementation/bmad-dev-story",
         "./src/bmm-skills/4-implementation/bmad-quick-dev",
+        "./src/bmm-skills/4-implementation/bmad-checkpoint-preview",
         "./src/bmm-skills/4-implementation/bmad-sprint-planning",
         "./src/bmm-skills/4-implementation/bmad-sprint-status",
         "./src/bmm-skills/4-implementation/bmad-code-review",

.gitignore

@@ -26,6 +26,9 @@ design-artifacts/
 __pycache__/
 .pytest_cache/
 
+# BMad run artifacts (memlogs are per-run working memory, never committed)
+.memlog.md
+
 # System files
 .DS_Store
 Thumbs.db
@@ -45,6 +48,9 @@ CLAUDE.local.md
 .junie/
 .agents/
 
+# Test fixtures need a committed .mcp.json (the rule above ignores real projects')
+!src/core-skills/bmad-module/tests/fixtures/**/.mcp.json
+
 z*/
 !docs/zh-cn/
 

docs/explanation/party-mode.md

@@ -1,59 +1,140 @@
 ---
 title: "Party Mode"
-description: Multi-agent collaboration - get all your AI agents in one conversation
+description: Get your AI agents in one conversation — run them, build your own cast, and choose how independently they think
 sidebar:
   order: 11
 ---
 
-Get all your AI agents in one conversation.
+Party mode puts your AI agents in one room and lets them talk, to each other and to you. This page explains what a party is, the four ways it can run, and how to build your own cast of personas instead of using the installed agents.
 
 ## What is Party Mode?
 
-Run `bmad-party-mode` and you've got your whole AI team in one room - PM, Architect, Dev, UX Designer, whoever you need. Party Mode orchestrates the discussion, picking relevant installed agents per message. Agents respond in character, agree, disagree, and build on each other's ideas.
+Run `bmad-party-mode` and the BMad agents you already have installed gather in one conversation: the PM, Architect, Dev, UX Designer, and whoever else your selected modules bring. That installed lineup is your default party, ready with no setup. They answer in character, agree, disagree, and build on each other. You steer the room. Ask a follow-up, push back, pull one voice forward, or change the subject. The conversation runs until you end it.
 
-The conversation continues as long as you want. Ask follow-ups, push back on answers, redirect the discussion - it's a real back-and-forth with your agents until you're done.
+It works because the personas hold different priorities. The Architect guards the design, the PM guards scope, the Dev guards what's actually buildable. Put them in the same room and the tradeoff surfaces now, in the conversation, instead of three weeks into the sprint.
 
 **Good for:**
 
-- Big decisions with tradeoffs
+- Decisions with real tradeoffs
-- Brainstorming sessions
+- Brainstorming and "what are we missing?"
-- Post-mortems when things go wrong
+- Post-mortems and retrospectives
-- Sprint retrospectives and planning
+- Pressure-testing a plan before you commit
 
-## Examples
+Party mode is also a fast and genuinely fun way to brainstorm, since the personas have opinions and they clash. And you can start a party from inside any other workflow: mid-brainstorm, mid-PRD, while coding, working a sales angle, or shaping a creative piece. Any time you want more perspectives on what's in front of you, pull in a room without dropping what you were doing.
 
-### Calling Out Bad Architecture
+:::note[Example]
+**You:** Monolith or microservices for the MVP?
 
-**You:** "Okay team, our last sprint was a disaster. The authentication service went down three times. Who screwed this up?"
+**Architect:** Start monolith. Microservices add operating cost you don't need at a thousand users.
 
-**Architect:** "The design was sound - distributed authentication with proper fallbacks. If implementation deviated from the spec..."
+**PM:** Agreed. Time to market matters more than scaling we can't prove yet.
 
-**Dev:** "I followed the architecture doc exactly. The spec didn't account for concurrent session invalidation race conditions."
+**Dev:** Monolith, but with clean module boundaries so we can split a service out later without a rewrite.
-
+:::
-**PM:** "Both of you missed the bigger issue - we didn't validate session management requirements in the PRD. This is on me for not catching it."
+
-
+## Starting a party
-**TEA:** "And I should've caught this in integration tests. The test scenarios didn't cover concurrent invalidation."
+
-
+Invoke the skill and say what you want; it works out whether you mean to run a party or build one.
-### Creative Brainstorming
+
-
+| Goal | Type this |
-**You:** "How do we make onboarding feel magical instead of boring?"
+| --- | --- |
-
+| Start a party in the default mode | `/bmad-party-mode` |
-**UX Designer:** "Start with progressive disclosure - reveal features as users need them, not all at once in a tutorial."
+| Start in a specific mode | `/bmad-party-mode --mode auto` (also `session`, `subagent`, `agent-team`) |
-
+| Open a saved party | `/bmad-party-mode --party code-review-crew` |
-**Storyteller:** "What if onboarding was a story? Each step reveals a character's journey - the user IS the hero."
+| Conjure a cast on the spot | "party mode with the bridge crew of the Enterprise" |
-
+| Create or add a party | "party mode, create a new party" |
-**Game Designer:** "Building on that - what if the first 'quest' is actually solving a real user problem? They learn by doing something valuable."
+| Edit an existing party | "party mode, edit the writers' room" |
-
+| Customize the skill | `/bmad-customize bmad-party-mode` |
-### Technical Decision
+
-
+## How a party runs
-**You:** "Monolith or microservices for MVP?"
+
-
+A party can run in four modes. One mode is active per session, and it decides who does the thinking: a single model voicing everyone, or separate agents reasoning on their own.
-**Architect:** "Start monolith. Microservices add complexity you don't need at 1000 users."
+
-
+| Mode | What it does | Reach for it when |
-**PM:** "Agree. Time to market matters more than theoretical scalability."
+| --- | --- | --- |
-
+| `session` | Default. One model voices every persona inline. Fast and fully conversational. | Most conversations — banter, brainstorming, quick back-and-forth. |
-**Dev:** "Monolith with clear module boundaries. We can extract services later if needed."
+| `auto` | Voices inline for light rounds, spawns independent agents only when independence changes the answer. | You want speed most of the time but real independence on the hard rounds. |
-
+| `subagent` | Spawns a separate agent for each persona every substantive round, so no single mind colors them all. | Honest reviews and focus groups, where the voices must not bleed together. |
-:::tip[Better Decisions]
+| `agent-team` | Stands the personas up as a persistent team that address each other directly. Claude Code only. | A live, hands-off round-table where the agents talk among themselves. |
-Better decisions through diverse perspectives. Welcome to party mode.
+
+The choice matters because one model voicing five personas can quietly converge: they share a mind. Spawning real agents keeps their reasoning separate, which is the entire point of a review panel or a focus group. `session` is the cheapest and most fluid. The spawning modes cost more but protect independence, and `auto` aims for both by spawning only when a round needs it.
+
+`session` is the default, and every other mode falls back to it when a harness can't do the rest: `agent-team` drops to `subagent`, then to `session`. The configured default lives in your customization, and a runtime override wins for that session.
+
+:::tip[Override for one session]
+Start a party with `--mode subagent` (or `auto`, `agent-team`, `session`) to override the configured default just for that run.
+:::
+
+## Custom parties
+
+Out of the box, a party uses your installed BMad agents. The larger use is building your own cast from any set of personas you can describe, then saving it to reuse. You author a party through the same skill. It detects whether you want to run one or build one, and writes the result to your overrides through [bmad-customize](../how-to/customize-bmad.md).
+
+Party mode is customizable like every BMad skill. Run `/bmad-customize bmad-party-mode` to set its defaults directly: pin any group you've built as the default party so it loads without a flag, choose which mode it starts in, and set any house rules the room should hold for the whole session.
+
+Two ideas do most of the work.
+
+**Personas** are what make a member unmistakable: how they talk, what they value, how they argue, their pet peeves and blind spots. "Skeptical CFO" is a placeholder. "Won't approve anything without a payback under eighteen months, and says so in the first thirty seconds" is a persona. That detail is what gives a voice you'd recognize with the name labels hidden.
+
+**Scenes** set the stage. A scene is one freeform line: the setting, what's happening, who's hostile to whom, who pushes hardest. The same members play it differently each time, so you define a person once and drop them into a bridge crew on duty, the same crew off-duty in the lounge, or a hostile buyer panel. Members combine into named groups, and you can pin one group as the default room.
+
+### Shapes a party can take
+
+| Shape | What it is |
+| --- | --- |
+| Themed cast | Famous investors, a TV ensemble — distinct voices gathered around a topic. |
+| One-off personas | A persona or two added to the pool, no group needed. |
+| Focus group from data | Hand it customer or survey data; it clusters people by what drives their behavior and builds representative personas. Pair it with `subagent` mode so the customers stay independent. |
+| Review panel | Purpose-built critical lenses that argue about what matters. The shipped Code Review Crew is one. |
+| Open-cast room | No fixed roster. The scene names a universe and the room is cast on the fly as the topic shifts. |
+
+A focus group is the case that pays off most. Feed in real profiles and you get a standing panel of representative customers to test an idea against before you build it, each reacting from their own goals and budget instead of agreeing with the last voice.
+
+## Parties you could build
+
+A party is only personas and a scene, so the range is wide, and none of it needs a new skill or module:
+
+- A founder squad to stress-test a startup idea.
+- A compliance team to find the holes before an audit does.
+- The authors of the Agile Manifesto, debating a software concept.
+- A room of comedians as a writing-partner group.
+- Great minds of the past, to work through a question in philosophy or untangle a hard problem.
+- A business management team to plan the quarter.
+
+These are starting points. Any set of voices you can describe becomes a party: write the personas, give the room a scene, and you have it.
+
+## The Code Review Crew
+
+Your default party is the agents your installed modules provide. The Code Review Crew is a custom party BMad ships alongside that default — a working template to study before you build your own, not a replacement for it. It's a review panel: five lenses that attack a change from different angles and argue about what actually matters, instead of rubber-stamping it.
+
+| Member | Lens |
+| --- | --- |
+| Vex | Security — threat-models everything and names the concrete exploit path. |
+| Grumbal | The adversary — assumes the code is broken and sets out to prove it. |
+| Boundary | Edge cases — every branch, null, race, oversized input, odd timezone. |
+| Yui | The craftsman — simplicity, naming, no needless cleverness or duplication. |
+| Dana | The pragmatist — counters the perfectionists and ranks what's real versus a nit. |
+
+The crew ships defined but inactive. The members sit in the pool and cost nothing until you summon the group, and they never crowd your default room. Run it with `subagent` mode so each lens reviews on its own before the five clash over the findings.
+
+## Steering the conversation
+
+You drive the room the whole way:
+
+- Bring someone in: "Bring in the UX designer."
+- Go deep on one voice: "Winston, take that apart." A direct ask is the cue for one persona to stretch out.
+- Switch rooms mid-session: "Switch to the writers' room" swaps the active group and carries the thread over.
+- Summon anyone by name, even a custom member who isn't in the current room.
+
+Whichever mode is running, the orchestrator presents the result as one conversation rather than a stack of separate answers, and it keeps the personas in character — it won't break the fourth wall to narrate the mechanism.
+
+:::tip[Mix more than one room]
+You aren't limited to a single group. Pull members from several parties into the same conversation, or name a cast on the spot, and let them mix. Picture the Golden Girls thrown into an architecture review with Martin Fowler and Linus Torvalds, sparring over a change request: you can imagine how that goes.
+:::
+
+## A keepsake of the session
+
+When you wrap up, the orchestrator offers a keepsake: a single self-contained HTML document of the session to keep or share. It lays the conversation out by persona rather than dumping a raw transcript. Decline it and the party simply ends.
+
+:::tip[Better decisions]
+The value of a party is the disagreement. Diverse perspectives in one room catch what a single line of thinking misses.
 :::

src/bmm-skills/2-plan-workflows/bmad-prd/SKILL.md

@@ -88,5 +88,5 @@ Tell the user the sequence in one sentence, then walk it. Polish goes last so it
 4. **Triage open items.** All Open Questions, `[ASSUMPTION]` tags, `[NOTE FOR PM]` callouts. Phase-blockers (would make the PRD unsafe for UX/architecture/epics) surfaced one at a time and resolved; non-blockers deferred with owner + revisit condition logged to `.decision-log.md`. If phase-blocker count is high, flag it.
 5. **Polish.** Apply `{workflow.doc_standards}` to `prd.md` and `addendum.md` in declared order (structural passes before prose — prose should not polish soon-to-be-cut text). Parallelize across documents, sequential within.
 6. **External handoffs.** Execute `{workflow.external_handoffs}`; surface returned URLs/IDs. Skip and flag unavailable tools.
-7. **Close.** Set `prd.md` frontmatter `status: final` and `updated` to `{date}` so future invocations distinguish this PRD from in-progress drafts. Record finalization to `.decision-log.md`. Share artifact paths. Common next: `bmad-ux`, `bmad-create-architecture`, `bmad-create-epics-and-stories`; invoke `bmad-help` for authoritative routing.
+7. **Close.** Set `prd.md` frontmatter `status: final` and `updated` to `{date}` so future invocations distinguish this PRD from in-progress drafts. Record finalization to `.decision-log.md`. Share artifact paths. Common next: `bmad-ux`, `bmad-architecture`, `bmad-create-epics-and-stories`; invoke `bmad-help` for authoritative routing.
 8. Run `{workflow.on_complete}` if non-empty.

src/bmm-skills/2-plan-workflows/bmad-ux/SKILL.md

@@ -33,7 +33,7 @@ UX may lead, follow, or stand alone. Inherit `sources:` by reference; the spines
 1. Resolve customization: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly and use defaults.
 2. Run `{workflow.activation_steps_prepend}`. Treat `{workflow.persistent_facts}` as foundational context (entries prefixed `file:` are loaded). `{workflow.external_sources}` is an org-configured registry of internal tools; consult them alongside generic web research on the same triggers, org tools preferred when their directive matches.
 3. Load `{project-root}/_bmad/bmm/config.yaml` (+ `config.user.yaml` if present). Resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{planning_artifacts}`, `{project_name}`, `{date}`. Missing keys → neutral defaults; never block.
-4. If headless, follow `references/headless.md` for the whole run. Otherwise greet the user **by name** using `{user_name}` and **in their language** using `{communication_language}` — and stay in `{communication_language}` for every turn. In the greeting, let the user know `bmad-party-mode` and `bmad-advanced-elicitation` are always available. Then scan for misroute on the first message: PRD → `bmad-prd`; architecture → `bmad-create-architecture`; game UX → BMad GDS; agent/skill → `bmad-workflow-builder`; brief → `bmad-product-brief`.
+4. If headless, follow `references/headless.md` for the whole run. Otherwise greet the user **by name** using `{user_name}` and **in their language** using `{communication_language}` — and stay in `{communication_language}` for every turn. In the greeting, let the user know `bmad-party-mode` and `bmad-advanced-elicitation` are always available. Then scan for misroute on the first message: PRD → `bmad-prd`; architecture → `bmad-architecture`; game UX → BMad GDS; agent/skill → `bmad-workflow-builder`; brief → `bmad-product-brief`.
 5. Detect intent: **Create**, **Update**, **Validate**. For Create, before binding a fresh workspace, scan `{workflow.ux_output_path}` for prior in-progress runs (folders matching `{workflow.run_folder_pattern}` whose `DESIGN.md` frontmatter `status` is not `final`) and offer to resume rather than starting over.
 
 Run `{workflow.activation_steps_append}`.
@@ -87,4 +87,4 @@ Outcomes, in order:
 - **Key-screen mocks rendered.** Key-screens tool → `.working/` for surfaces where layout drives behavior or anchors visual language.
 - **Mock coverage confirmed.** Walk every IA surface; classify *mocked* vs *spine-only*. Ask: *"These will be built from spine tables alone — any need a visual reference?"* Render more if named; log spine-only choices.
 - **Layout extracted, artifacts promoted.** Distill subagent re-reads each `.working/` and `imports/` artifact; lifts visual decisions into DESIGN.md and behavioral decisions into EXPERIENCE.md. Promote `.working/` keepers to `mockups/` (HTML) or `wireframes/` (Excalidraw); imports stay. Inline relative links at relevant spine sections; state spines-win-on-conflict once.
-- **Polished, handed off, closed.** Apply `{workflow.doc_standards}` in order. Execute `{workflow.external_handoffs}`; surface URLs. Set both files' `status: final`, `updated: {date}`. Log finalization. Share paths. Common next: `bmad-create-architecture`, `bmad-create-epics-and-stories`, `bmad-dev-story`. Run `{workflow.on_complete}`.
+- **Polished, handed off, closed.** Apply `{workflow.doc_standards}` in order. Execute `{workflow.external_handoffs}`; surface URLs. Set both files' `status: final`, `updated: {date}`. Log finalization. Share paths. Common next: `bmad-architecture`, `bmad-create-epics-and-stories`, `bmad-dev-story`. Run `{workflow.on_complete}`.

src/bmm-skills/3-solutioning/bmad-agent-architect/customize.toml

@@ -56,8 +56,8 @@ principles = [
 
 [[agent.menu]]
 code = "CA"
-description = "Guided workflow to document technical decisions to keep implementation on track"
+description = "Produce the architecture spine: the invariants that keep independently-built units consistent"
-skill = "bmad-create-architecture"
+skill = "bmad-architecture"
 
 [[agent.menu]]
 code = "IR"

src/bmm-skills/3-solutioning/bmad-architecture/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: bmad-architecture
+description: 'Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".'
+---
+# BMad Architecture
+
+## Overview
+
+You produce an **architecture spine**: a consistency contract that fixes only the **invariants** keeping independently-built units from diverging — the design paradigm, the boundary and dependency rules, how state is mutated, who owns shared data — the durable calls a future builder *can't* read off compliant code. Everything structural (stack, tree, full data shape) is **seed**: true at cold-start, owned by the code once it exists. Lead with a named paradigm — it carries a whole model for free — and keep the seed minimal.
+
+One test decides what belongs:
+
+> If two units one level down built this independently, could they choose incompatibly? Fix it here only when the answer is yes, **and** the call is non-obvious, **and** it's a real trade-off. Otherwise name it under Deferred and move on.
+
+Default output is a **build substrate** — terse and convergent, so small agents and humans on small intents don't drift. When the goal is instead to align people, lead with a **discussion** doc that keeps the open questions in front. Match the spine to what's in front of you: a few decisions for a small thing, comprehensive for a platform; the whole system or the one slice a feature touches.
+
+Record decisions, not rationale (rationale lives in the memlog). Carry shape in diagrams, not prose. Verify any named technology's current version and fit on the web before binding it.
+
+## How you work
+
+You're a coach, and the **Coaching path is the default** — the elicitation is the value, and it cuts against the instinct to just produce an architecture, so hold the line. Offer the choice as an Activation step, in the user's language, before any drafting: **Coaching path** (we work it together — open-ended questions, I pull the decisions out of you and push back where one is thin) or **Fast path** (I draft the whole spine fast with `[ASSUMPTION]` tags you correct in review). Unless the user clearly wants speed, **coach; don't silently draft.** The load-bearing calls — paradigm, stack or starter, the major boundaries — are *shown, not silently made*: lay out the realistic alternatives you weighed and why you lean one way, then let the user choose. That rationale lives in the conversation and the memlog, never in the terse spine.
+
+Elicit, don't quiz: open-ended "how are you thinking about X?" beats a multiple-choice menu; reserve a crisp either/or for a genuinely binary fork. On the Fast path, inferring and tagging *is* the job.
+
+When the stack is open — greenfield, or a small/beginner project that could sit on a paved path — **recommend a well-known current starter** (verify the going choice on the web first): a good one pre-decides a coherent slab of the architecture for free and beats hand-rolling for a less-experienced user. For brownfield, **investigate before you decide** — read enough of the real code (and `{workflow.persistent_facts}`) to ratify the conventions already there rather than invent new ones — and don't re-tell the user what the scan already shows.
+
+## Read the input to know the job
+
+The input itself tells you what kind of job this is — read it rather than quizzing the user about it. A spec package (`SPEC.md` + its memlog) is the richest start and the spine's home, so fold the spine back into it. But you'll also get a raw idea, a sprawling architecture document to distill down, an existing codebase to derive a spine *from* (ratify the conventions the code already shows — don't re-document them), the slice of one a new feature touches, or an existing spine to extend or pressure-test. Prefer a `.memlog.md` over re-reading the source it came from. Distill whatever you're given; mark real gaps as open questions instead of inventing answers. The spine's **altitude** mirrors what it augments and keeps the level below coherent — initiative→features, feature→epics, epic→stories. Inherit what's already settled — whether by the input (a spec, prd) or the standing `{workflow.persistent_facts}` — silently; don't re-decide or re-ask it. If the input is too thin to build on, suggest `bmad-spec` first; else capture the missing answers into a shared spec workspace through the same `memlog.py`, so `bmad-spec` can later derive `SPEC.md` without drift.
+
+**Inheriting a parent spine** (e.g. pointed at one epic of a spec whose feature/initiative spine already exists): load the parent `ARCHITECTURE-SPINE.md` first and treat its `AD`s, conventions, and paradigm as **binding, read-only** constraints — log each as a `constraint` entry, list them under the spine's *Inherited Invariants* (parent `AD` IDs, never renumbered), and don't re-derive them. Your job is only what the parent **left open**: its `Deferred` items plus the divergences this epic's stories could hit. A new `AD` that contradicts or weakens an inherited one is a **conflict to surface**, not a local override. An epic spine fixes the invariants the epic's stories must share — it does **not** expand per-story detail.
+
+## How a run works
+
+The **memlog** (`.memlog.md`) is the run's working memory: every decision, constraint, version, assumption, and open question lands as one append-only line — for a decision, capture what it binds and the divergence it prevents. It is the shared canonical memlog (the same `{project-root}/_bmad/scripts/memlog.py` bmad-spec writes through), so it carries no lifecycle status — terminal moments are logged as `event` entries, not a frontmatter flag. The spine is **distilled from the memlog at the end**, not written as you go. Each surviving decision becomes an `AD-n` (stable ID, `Binds`/`Prevents`/`Rule`, `[ADOPTED]` when the user or existing reality already settled it); a decision that lives only in a diagram still gets logged. Resume a prior run by reloading its memlog.
+
+Writes go through the shared script (don't read the file back except on resume):
+
+- `python3 {project-root}/_bmad/scripts/memlog.py init --workspace {doc_workspace} --field scope="…" --field purpose="…" --field altitude="…"`
+- `python3 {project-root}/_bmad/scripts/memlog.py append --workspace {doc_workspace} --type <decision|constraint|version|assumption|question|direction|event> --text "…"`
+
+## Resolution rules
+
+- Bare paths and `{skill-root}` (e.g. `references/headless.md`) resolve from this skill's installed directory.
+- `{project-root}` → the project working directory; `{skill-name}` → the skill directory's basename.
+- `{workflow.<name>}` → a merged `customize.toml` field; `{doc_workspace}` → the bound run folder.
+- Forward slashes only. Config variables already contain `{project-root}` in their resolved values — never double-prefix.
+
+## On Activation
+
+**Forwarded activation:** if a caller (e.g. the `bmad-create-architecture` shim) invoked you with a stated intent and pre-resolved customization fields, honor them verbatim — skip your own intent inference, use the supplied values for those named fields, and resolve only the remaining fields from your own `customize.toml`.
+
+1. Resolve customization: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow` (on failure read `{skill-root}/customize.toml`, use defaults). Run `{workflow.activation_steps_prepend}`, then `{workflow.activation_steps_append}`. Hold `{workflow.persistent_facts}` as standing context — the default loads `project-context.md`, load-bearing for brownfield — and consult `{workflow.external_sources}` on demand.
+2. Load `{project-root}/_bmad/bmm/config.yaml` (+ `config.user.yaml`) for `{user_name}`, `{communication_language}`, `{document_output_language}`, `{planning_artifacts}`, `{project_name}`, `{date}`; missing keys take neutral defaults, never block.
+3. Headless (no interactive user) → follow `references/headless.md` for the whole run. Otherwise greet `{user_name}` in `{communication_language}`. Detect the intent from the conversation and input — **create** (the default), **update** an existing spine, or **validate** one (see those sections). If the real ask is requirements / UX / a capability contract / epic breakdown / an agent, invoke the `bmad-prd`, `bmad-ux`, `bmad-spec`, `bmad-create-epics-and-stories`, or `bmad-workflow-builder` (if the BMad Builder module is installed) skill instead.
+4. If a run folder for this target already exists under `{workflow.spine_output_path}`, offer to resume from its memlog rather than restart.
+5. Interactive create: offer the working mode in `{communication_language}` — **Coaching path** (default) or **Fast path** (see *How you work*) — before any drafting; default to Coaching unless the user asks for speed.
+6. **Mandatory, both paths, before drafting:** ask whether the spine is the only deliverable — and if not, draw out the *purpose and audience* rather than a document type. "An architecture doc" balloons into bloat; what they actually need might be a one-detail explainer for a single team or a non-technical vision piece for a board. Purpose right-sizes the artifact and may call for extra elicitation up front, not just a finale add-on.
+
+For a new spine, bind `{doc_workspace}` to `{workflow.spine_output_path}/{workflow.run_folder_pattern}/`, seed `ARCHITECTURE-SPINE.md` from `{workflow.spine_template}`, run `memlog.py init`, and tell the user the path. **At epic altitude, scope the folder to the epic** (set `run_folder_pattern` per `customize.toml`) so per-epic runs don't collide.
+
+## Reviewer Gate
+
+The spine's pre-handoff review — full mechanics in `references/reviewer-gate.md`. Load it when finalizing or validating: a deterministic `lint_spine.py` pass, then a rubric walker (good-spine checklist) + every `{workflow.finalize_reviewers}` lens dispatched as parallel subagents against `ARCHITECTURE-SPINE.md`, scaled to stakes. At Finalize you apply the clear fixes; under the Validate intent you deliver a bespoke HTML report and then get user input.
+
+## Finalize
+
+Walk the sequence; reviewer fixes land before polish.
+
+1. **Distill.** Write the spine from the memlog (brownfield: + the code sweep) — invariants first, seed minimal, every `AD` carrying Binds/Prevents/Rule, `Deferred` naming what it won't decide. No placeholders; never invent to fill a gap. The template's `<!-- -->` notes are guidance — act on them, then strip them; the finished spine carries no template comment, and only the diagrams that convey the structure (as many as the altitude needs, valid mermaid). Sweep the breadth the altitude owns — every structural dimension is decided, deferred, or an open question; a whole dimension left silent (e.g. the operational/environmental envelope: deployment & environments, infra/provider strategy, operations) is the failure, not a clean spine. A long coaching run distills cleaner in a subagent; the parent falls back inline.
+2. **Reconcile inputs.** A subagent per load-bearing input checks it against the spine and returns what didn't land — especially a quiet requirement (a tone, a constraint) the `AD` structure dropped. Before the gate.
+3. **Reviewer pass.** Run the Reviewer Gate (`references/reviewer-gate.md`). Resolve before polish.
+4. **Triage.** Open questions and `[ASSUMPTION]` tags: blockers (unsafe for what's next) resolved one at a time; the rest deferred with a revisit condition in the memlog.
+5. **Renderings & polish.** The spine is the build deliverable; with it and the memlog now in place, produce any *additional* human-facing artifact the user needs, scoped to the purpose and audience drawn out up front. The up-front question already flagged whether one's needed; if it wasn't, still offer one here, seeding concrete options: an interactive HTML+SVG deck to walk a team through the architecture and drive discussion, a fuller HTML/md solution design, a C4 set, or a view of how the work splits across teams/epics. Build only what they pick, right-sized to that purpose; apply `{workflow.doc_standards}` polish to that prose only, never to the spine.
+6. **External handoffs.** Run `{workflow.external_handoffs}`; surface returned URLs/IDs. Offer to invoke the `bmad-spec` skill to adopt the spine as a companion, keeping `AD` IDs stable so downstream can cite them.
+7. **Close.** Set the spine's own frontmatter `status: final`, `updated: {date}`; log a `memlog.py append --type event --text "spine finalized"` (the memlog has no status field). Share paths. Next, **lead with `bmad-spec`** — recommend adopting/refreshing the spine as a spec companion (always the top recommendation when a spec was an input, and a useful next step even when it wasn't), then `bmad-create-epics-and-stories` or — epic altitude — `bmad-create-story`; or invoke `bmad-help` to route.
+8. Run `{workflow.on_complete}`.
+
+## Update
+
+Amend an existing spine or provided artifact. Resume from its `.memlog.md` (the authority on what was decided), not the rendered spine. Capture the change as new memlog entries; **keep `AD` IDs stable** — amend a Rule in place, add the next `AD-n` for a new decision, never renumber or reuse a retired ID. Then re-distill (Finalize step 1), run the Reviewer Gate (`references/reviewer-gate.md`), and close as in Finalize. An update that overrides something from a source input: offer to update that source too, so upstream and the spine don't silently diverge.
+
+## Validate
+
+The standalone intent — critique an existing spine without changing it. Run the Reviewer Gate (`references/reviewer-gate.md`) against it and deliver the bespoke HTML report, then offer to roll the findings into an Update. (At Finalize the same gate runs as your own pre-handoff check, where you apply the fixes instead of reporting.)

src/bmm-skills/3-solutioning/bmad-architecture/assets/spine-template.md

@@ -0,0 +1,79 @@
+---
+name: '{name}'
+type: architecture-spine
+purpose: build-substrate    # build-substrate (default) · discussion · report · deck
+altitude: feature           # initiative (keeps features) · feature (keeps epics) · epic (keeps stories)
+paradigm: '{named design pattern, e.g. hexagonal, layered, pipes-and-filters, actor}'
+scope: '{what this spine governs}'
+status: draft               # draft · final
+created: '{date}'
+updated: '{date}'
+binds: []                   # capability / unit IDs governed (from the driving spec; at epic altitude, also the inherited parent AD ids)
+sources: []
+companions: []
+---
+
+# Architecture Spine — {name}
+
+<!-- TEMPLATE GUIDE — act on these comments, then delete them; never emit a comment in the finished spine. This is a shape, not a script: keep only the sections this spine needs and cut the rest (no empty headers). A small intent may be just paradigm + a few ADs + conventions; a platform earns more. An inherited epic spine is usually mostly Inherited Invariants + a thin Deferred. Decisions, not rationale (rationale lives in the memlog). Carry shape in diagrams; prose only where it must. -->
+
+## Design Paradigm
+
+<!-- Name the pattern (a known one loads a whole model for free) and map its layers to namespaces/directories. The smallest, most durable thing here. -->
+
+## Inherited Invariants
+
+<!-- Only when this spine inherits a higher-altitude parent. The parent's ADs/conventions/paradigm that bind here, by their ORIGINAL ids — read-only, never renumbered, not re-derived. A local decision that contradicts one is a conflict to surface, not an override. Cut this section otherwise. -->
+
+| Inherited | From parent | Binds here |
+| --- | --- | --- |
+| {AD-id / convention} | {parent spine} | {what it constrains in this scope} |
+
+## Invariants & Rules
+
+<!-- The durable heart: calls a future builder can't read off compliant code. One block per decision: stable ascending id (never reused/renumbered), Binds, Prevents (the divergence), Rule (enforceable). Tag [ADOPTED] when the user or existing reality settled it. Include a dependency-direction diagram (who may depend on whom) — it IS a rule; author it as valid mermaid, never an empty graph. -->
+
+### AD-1 — {decision}
+
+- **Binds:** {capability / unit ids / fr/nfr's, areas, or `all`}
+- **Prevents:** {the divergence this stops}
+- **Rule:** {the constraint downstream must follow}
+
+## Consistency Conventions
+
+<!-- Defaults that bind where independent builders would drift. Cut rows that don't apply; add rows the project needs. -->
+
+| Concern | Convention |
+| --- | --- |
+| Naming (entities, files, interfaces, events) | |
+| Data & formats (ids, dates, error shapes, envelopes) | |
+| State & cross-cutting (mutation, errors, logging, config, auth) | |
+
+## Stack
+
+<!-- SEED — verified current at authoring; the code owns this once it exists. Name + version only; the why lives in the memlog. One row per language, framework, key dependency, platform, or chain that's pinned. -->
+
+| Name | Version |
+| --- | --- |
+| {language / framework / key dep / platform / chain} | {pinned version} |
+
+## Structural Seed
+
+<!-- The shapes worth fixing at cold-start — not a fixed list. Include only what's non-obvious at this altitude, and use as many diagrams as convey it, each as VALID mermaid (never a placeholder or empty graph). Candidates: system/container/context view; DEPLOYMENT & ENVIRONMENTS and external provider/infra topology (cover the operational envelope here when this altitude owns it — don't let it fall through); core-entity ERD (names + relationships only; an attribute that's itself an invariant is an AD, not a diagram); a minimal source tree. The code owns the detail — this is scaffold, not a mirror to maintain. -->
+
+```text
+{root}/
+  {dir}/   # {what lives here}
+```
+
+## Capability → Architecture Map
+
+<!-- Present when a spec drove this run. Bridges the spec's capabilities to where they live + what governs them; the consistency auditor's checklist. Cut otherwise. -->
+
+| Capability / Area | Lives in | Governed by |
+| --- | --- | --- |
+| {CAP-id / area} | {component / module} | {AD-id, convention, paradigm} |
+
+## Deferred
+
+<!-- Decisions intentionally pushed down, each with the reason it can wait — including whole dimensions this altitude doesn't own yet. The half of the contract that keeps the spine lean. -->

src/bmm-skills/3-solutioning/bmad-architecture/customize.toml

@@ -0,0 +1,100 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Workflow customization surface for bmad-architecture.
+#
+# Override files (not edited here):
+#   {project-root}/_bmad/custom/bmad-architecture.toml         (team)
+#   {project-root}/_bmad/custom/bmad-architecture.user.toml    (personal)
+
+[workflow]
+
+# --- Configurable below. Overrides merge per BMad structural rules: ---
+#   scalars: override wins • arrays: append
+
+# Steps to run before the standard activation (config load, greet).
+# Use for pre-flight loads, approved-stack policy checks, etc.
+activation_steps_prepend = []
+
+# Steps to run after greet but before the workflow begins.
+# Use for context-heavy setup that should happen once the user has been acknowledged.
+activation_steps_append = []
+
+# Persistent facts the workflow keeps in mind for the whole run
+# (approved stacks, banned dependencies, platform constraints, compliance guardrails).
+# Each entry is either a literal sentence, a skill prefixed with `skill:`, or a `file:`-prefixed
+# path/glob whose contents are loaded as facts.
+#
+# Default loads project-context.md if bmad-generate-project-context produced one — giving the
+# architect persistent awareness of the project's tech, domain, and conventions (load-bearing
+# for brownfield). Common opt-ins (set in team/user override TOML):
+#   "Our org is AWS-only -- do not propose GCP or Azure."
+#   "file:{project-root}/docs/engineering-standards.md"
+persistent_facts = [
+  "file:{project-root}/**/project-context.md",
+]
+
+# Executed when the workflow completes (after the spine is final and the user has been told).
+# String scalar (single instruction) or array of instructions executed in order. Empty for none.
+on_complete = ""
+
+# The architecture spine template. Treated as expert prior knowledge, not a checklist — the LLM
+# adapts it to the project, altitude, and domain, and drops sections a project genuinely doesn't
+# need. Override the path in team/user TOML to enforce a different spine shape.
+spine_template = "assets/spine-template.md"
+
+# Run folder location. ARCHITECTURE-SPINE.md, its .memlog.md, and any fuller rendering the run
+# produces all land inside `{spine_output_path}/{run_folder_pattern}/`. Resume-check scans
+# `{spine_output_path}` for prior unfinished runs.
+#
+# The default pattern fits the common case (one spine per project, at the altitude above epics).
+# At EPIC altitude, override run_folder_pattern to carry the epic identity so per-epic runs don't
+# collide on the same day — e.g. set it (team/user TOML) to "architecture-epic-{epic_id}", binding
+# {epic_id} from the driving spec / the activating payload. Headless callers may instead pass an
+# explicit doc_workspace and bypass the pattern entirely.
+spine_output_path = "{planning_artifacts}/architecture"
+run_folder_pattern = "architecture-{project_name}-{date}"
+
+# Prose-editorial standards applied at finalize ONLY to a fuller prose document the run produces
+# (a discussion report, full architecture doc, or design addendum) — never to the spine or other
+# short, structured outputs, which are terse and carry decisions in AD-n blocks and diagrams by
+# design. Each entry is a `skill:`, `file:`, or plain-text directive applied before the user sees
+# the polished draft. Suggested order: structural passes first, prose mechanics last. Append-only.
+doc_standards = [
+  "skill:bmad-editorial-review-structure",
+  "skill:bmad-editorial-review-prose",
+]
+
+# External-source registry. Natural-language directives describing knowledge bases, MCP tools, or
+# internal systems the LLM may consult ON DEMAND during the run (not preemptively) — approved-stack
+# catalogs, internal platform docs, version registries. Each entry names the tool, the trigger
+# condition, and any fields it needs. If a named tool is unavailable at runtime, the LLM falls back
+# to standard behavior (e.g. web research) and notes the gap. Empty by default.
+#
+# Examples (set in team/user override TOML):
+#   "When choosing a datastore, consult corp:platform_catalog before recommending one."
+#   "For current library versions, query corp:artifact_registry before web search."
+external_sources = []
+
+# External-handoff routing applied at Finalize to push outputs beyond local files (Confluence,
+# Notion, ticket systems). Each entry names the MCP tool, the destination, and required fields.
+# Runs after polish; returned URLs/IDs are surfaced. Unavailable tools are skipped and flagged;
+# local files always exist. Empty by default.
+external_handoffs = []
+
+# --- Finalize reviewers ---
+# Extra review lenses spawned as parallel subagents at the validation gate (Finalize and the
+# Validate intent), on top of the skill's built-in good-spine checklist and the lint_spine.py
+# mechanical floor. The GATE is stakes-gated — a throwaway spine may run it quietly or skip it —
+# but whenever the gate runs, every entry here runs with it (the configured floor, never cherry-
+# picked); only ad-hoc lenses are optional, and headless never skips the gate.
+#
+# Entries follow the standard prefix convention:
+#   "skill:NAME"   invoke the named review skill as a subagent against ARCHITECTURE-SPINE.md
+#   "file:PATH"    load the file as a review prompt; spawn an adversarial subagent applying it
+#   plain text     use the text directly as the subagent's review prompt
+#
+# Resolved on-demand (not at activation). Override TOML may append.
+finalize_reviewers = [
+  "Verify every committed decision was web-researched or reality-checked rather than asserted from training data: current library/framework versions, that each named technology still exists and fits, and — greenfield — the live defaults of any starter it leans on. Flag anything that could be out of date and wasn't confirmed against the web, the existing project, or the current starter.",
+  "Attack the spine as an adversary: construct two units one level down that each obey every AD to the letter yet still build incompatibly — clashing shared-data shapes, two owners of one entity, conflicting state-mutation paths. Every pair you find is a hole to close with a new or tightened AD.",
+]

src/bmm-skills/3-solutioning/bmad-architecture/references/headless.md

@@ -0,0 +1,26 @@
+# Headless
+
+No interactive user: infer everything, ask nothing, but never invent — record inferences as `assumptions[]` and gaps that need a human as `open_questions[]`. Detect headless from a `headless: true` flag, a non-interactive / no-TTY invocation, an activation hook that declares it, or a first message that pre-supplies all inputs and asks for an artifact path back; when ambiguous, default to interactive.
+
+Drive the run from the payload in the first message — `intent`, `altitude`, `purpose`, the driving input (spec package / PRD / raw intent / brownfield path), a parent spine path at lower altitude, and `doc_workspace` if a specific folder is required. Infer anything absent from the inputs or workspace; don't invent stack, constraints, or scope to fill a gap. You still verify named tech on the web (you can't ask, but you can check) and still drive every write through the shared `{project-root}/_bmad/scripts/memlog.py`. Run the full Reviewer Gate (`references/reviewer-gate.md`) non-interactively: `scripts/lint_spine.py` plus **every `{workflow.finalize_reviewers}` lens as a parallel subagent** (and any ad-hoc lens the spine's criticality warrants). Headless skips only the human picking from the menu — never the reviewers themselves; apply the clear fixes and record anything unresolved in `open_questions[]`. For a true authority collision, list it in `conflicts_with_prior_decisions[]`. For the Validate intent, always write the report to `{doc_workspace}` and add `"offer_to_update": true`. If intent stays ambiguous after inference, halt blocked.
+
+End with JSON only, omitting keys for artifacts not produced — the shape below is the fully-produced (`complete`) case; a `blocked` run produces no spine, so it omits `spine`, `memlog`, and `companions` entirely (see the note under the block):
+
+```json
+{
+  "status": "complete | partial | blocked",
+  "intent": "create | update | validate",
+  "altitude": "initiative | feature | epic",
+  "purpose": "build-substrate | discussion",
+  "doc_workspace": "<resolved run folder>",
+  "spine": "{doc_workspace}/ARCHITECTURE-SPINE.md",
+  "memlog": "{doc_workspace}/.memlog.md",
+  "companions": [],
+  "assumptions": [],
+  "open_questions": [],
+  "conflicts_with_prior_decisions": [],
+  "reason": "<one line, only when blocked>"
+}
+```
+
+`complete` stands alone · `partial` (spine produced, but `open_questions[]` non-empty or critical inputs inferred) means review before downstream use · `blocked` means no spine produced — return only `status`, `intent`, `reason`, and `doc_workspace` (if bound), omitting `spine`, `memlog`, `companions`, and the artifact arrays that don't exist.

src/bmm-skills/3-solutioning/bmad-architecture/references/reviewer-gate.md

@@ -0,0 +1,13 @@
+# Reviewer Gate
+
+The spine's pre-handoff review. Runs at Finalize (after distill + reconcile) and *is* the Validate intent. The difference is the ending: at Finalize you apply the clear fixes yourself; under Validate you report and don't change the spine.
+
+Cheap deterministic pass first: `python3 {skill-root}/scripts/lint_spine.py --workspace {doc_workspace}` settles the mechanical misses (placeholders, duplicate `AD` IDs, missing Binds/Prevents/Rule, unpinned Stack versions), so reviewers spend judgment on the semantic half.
+
+Assemble the menu: a **rubric walker** that judges the spine against the good-spine checklist below, **+ every entry in `{workflow.finalize_reviewers}`**, + ad-hoc lenses you invent or offer as the spine's rigor, altitude, and criticality warrant — a security/compliance lens for regulated stakes, a seam reviewer cross-team, a data-integrity lens for a heavy data model. Scale *whether and how heavily the gate runs* to the stakes: a throwaway prototype may run it quietly or skip the gate entirely; a high-criticality or platform-altitude spine earns more lenses and the explicit all / subset / skip menu. But once the gate runs, the `{workflow.finalize_reviewers}` always run — they are the configured floor, never cherry-picked out; only the ad-hoc lenses are optional. (Headless never skips the gate.)
+
+Dispatch every entry as a **parallel subagent against `ARCHITECTURE-SPINE.md`** (prefix convention: `skill:` / `file:` / plain text). Each writes its full review to `{doc_workspace}/reviews/review-{slug}.md` — a subfolder, so the gate's scratch stays out of the deliverable folder — and returns ONLY a compact summary (verdict, top 2–5 findings, file path) — the parent never holds full review text. An inline self-check does not count: the independent context is the point, because a fresh reviewer finds the divergences the author talks past. If subagents are unavailable, run sequentially — write the file first, then flush it from context.
+
+**Good-spine checklist** (what the rubric walker judges): it fixes the real divergence points for the level below and misses none; every `AD`'s Rule is enforceable and actually prevents its stated divergence; nothing under Deferred could let two units diverge; named tech is verified-current; it ratifies rather than contradicts a brownfield codebase; if a spec drove it, it covers that spec's capabilities; if a parent spine is inherited, no new `AD` weakens or contradicts an inherited one; and every dimension the altitude owns is decided, deferred, or an open question — a whole dimension left silent is a finding, especially the operational/environmental envelope (deployment & environments, infra/provider strategy, operations) a domain-focused draft skips.
+
+Surface findings tiered, never dumped: a one-sentence gate verdict, then critical + high; medium/low roll into a tail ("plus N more in {file}"). Per finding: autofix, discuss, defer to Deferred / open items, or ignore. **At Finalize this is your own gate — apply the clear fixes rather than handing over a list; surface only what genuinely needs the user.** Under the **Validate intent**, fold every reviewer's output into one bespoke HTML + markdown report and open the HTML.

src/bmm-skills/3-solutioning/bmad-architecture/scripts/lint_spine.py

@@ -0,0 +1,257 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# ///
+"""lint-spine — the mechanical half of spine decision-integrity, done deterministically.
+
+LLMs miscount IDs and miss literal placeholders; a grep does not. This linter owns the
+checks a script does better than a prompt, and leaves the semantic half (is each Rule
+actually enforceable? does the boundary make sense?) to the rubric walker.
+
+It reads ARCHITECTURE-SPINE.md from a workspace and reports, as compact JSON on stdout:
+
+  - placeholder    literal TBD / TODO / "similar to AD-n" / unfilled {template-token}
+  - ad_id          duplicate or non-monotonic AD-n identifiers
+  - ad_fields      an AD-n block missing Binds / Prevents / Rule
+  - version_pin    a ## Stack table row with no version
+
+Fenced code blocks are blanked (replaced with equal-count blank lines) before scanning, so
+mermaid and source trees don't trip false positives AND reported line numbers still line up
+with the real file. Reported lines are absolute file lines (frontmatter offset added). Exit
+code is always 0 — findings travel in the JSON; the caller (Reviewer Gate / rubric walker)
+decides what to do with them.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import re
+import sys
+from pathlib import Path
+
+SPINE = "ARCHITECTURE-SPINE.md"
+
+AD_HEADING = re.compile(r"^#{2,4}\s*AD-(\d+)\b(.*)$", re.MULTILINE)
+HEADING = re.compile(r"^#{1,6}\s", re.MULTILINE)
+FENCE = re.compile(r"```.*?```", re.DOTALL)
+PLACEHOLDER_WORD = re.compile(r"\b(TBD|TODO|FIXME|XXX)\b")
+SIMILAR_TO = re.compile(r"similar to AD-\d+", re.IGNORECASE)
+TEMPLATE_TOKEN = re.compile(r"\{[a-z_][a-z0-9_ /.-]*\}")
+
+
+def split_frontmatter(text: str) -> tuple[str, str, int]:
+    """Return (frontmatter, body, body_line_offset).
+
+    Frontmatter is the content between the first two lines that are *exactly* `---`
+    (line-exact, like memlog.split — a `---` inside a value or a body thematic break never
+    truncates it). body_line_offset is the number of file lines before the body begins, so a
+    body-relative line number plus the offset gives the absolute file line. Absent frontmatter
+    → ('', text, 0)."""
+    lines = text.split("\n")
+    if lines and lines[0] == "---":
+        for i in range(1, len(lines)):
+            if lines[i] == "---":
+                fm = "\n".join(lines[1:i])
+                body = "\n".join(lines[i + 1:])
+                return fm, body, i + 1
+    return "", text, 0
+
+
+def blank_fences(text: str) -> str:
+    """Replace each fenced block with the same number of newlines, so scanning skips fenced
+    content while every line number outside the fence stays put."""
+    return FENCE.sub(lambda m: "\n" * m.group(0).count("\n"), text)
+
+
+def line_of(text: str, idx: int) -> int:
+    return text.count("\n", 0, idx) + 1
+
+
+def find_placeholders(body: str, offset: int) -> list[dict]:
+    findings: list[dict] = []
+    scan = blank_fences(body)
+    # (regex, label, severity) — TBD/TODO and dangling cross-refs are unambiguous; a bare
+    # {template-token} can be legitimate brace prose, so it is flagged low ("possible") to keep
+    # the mechanical pass near-zero false-positive rather than train reviewers to ignore it.
+    for rx, label, severity in (
+        (PLACEHOLDER_WORD, "placeholder marker", "high"),
+        (SIMILAR_TO, "unresolved cross-reference", "high"),
+        (TEMPLATE_TOKEN, "possible unfilled template token (verify)", "low"),
+    ):
+        for m in rx.finditer(scan):
+            findings.append({
+                "category": "placeholder",
+                "severity": severity,
+                "detail": f"{label}: {m.group(0)!r}",
+                "location": f"{SPINE} (line {offset + line_of(scan, m.start())})",
+            })
+    return findings
+
+
+def find_frontmatter_placeholders(frontmatter: str) -> list[dict]:
+    """Catch unfilled tokens left in frontmatter (e.g. paradigm/scope/date) — part of the
+    spine contract, but outside the body that find_placeholders scans."""
+    findings: list[dict] = []
+    for rx, label, severity in (
+        (PLACEHOLDER_WORD, "placeholder marker", "high"),
+        (TEMPLATE_TOKEN, "possible unfilled template token (verify)", "low"),
+    ):
+        for m in rx.finditer(frontmatter):
+            findings.append({
+                "category": "placeholder",
+                "severity": severity,
+                "detail": f"frontmatter {label}: {m.group(0)!r}",
+                "location": f"{SPINE} frontmatter (line {1 + line_of(frontmatter, m.start())})",
+            })
+    return findings
+
+
+def find_ad_issues(body: str, offset: int) -> list[dict]:
+    findings: list[dict] = []
+    scan = blank_fences(body)  # AD headings shown inside a code fence are not live ADs
+    matches = list(AD_HEADING.finditer(scan))
+    seen: dict[int, int] = {}
+    prev: int | None = None
+    for m in matches:
+        num = int(m.group(1))
+        file_line = offset + line_of(scan, m.start())
+        loc = f"{SPINE} AD-{num} (line {file_line})"
+        if num in seen:
+            findings.append({
+                "category": "ad_id",
+                "severity": "high",
+                "detail": f"AD-{num} id reused (also at line {seen[num]})",
+                "location": loc,
+            })
+        else:
+            seen[num] = file_line
+        if prev is not None and num <= prev:
+            findings.append({
+                "category": "ad_id",
+                "severity": "high",
+                "detail": f"AD-{num} is non-monotonic (follows AD-{prev}); ids must ascend and never renumber",
+                "location": loc,
+            })
+        prev = num if prev is None else max(prev, num)
+
+        # block text = from this heading to the next heading of any level
+        start = m.end()
+        nxt = HEADING.search(scan, start)
+        block = scan[start:nxt.start()] if nxt else scan[start:]
+        low = block.lower()
+        missing = [f for f in ("binds", "prevents", "rule") if f not in low]
+        if missing:
+            findings.append({
+                "category": "ad_fields",
+                "severity": "high",
+                "detail": f"AD-{num} missing required field(s): {', '.join(missing)}",
+                "location": loc,
+            })
+    return findings
+
+
+def find_unpinned_stack(body: str, offset: int) -> list[dict]:
+    """Flag a `## Stack` table row that names something but leaves its version blank or a
+    placeholder. Pinning lives in the body table now, not frontmatter. A row whose name is
+    still a `{token}` skeleton is left to the placeholder pass, not double-reported here.
+
+    Fences are blanked first (like find_placeholders / find_ad_issues), so a pipe-row or
+    heading inside a code block is never read as live Stack content. The heading match is
+    `## Stack` with a word boundary, so a renamed heading (`## Stack & Versions`) still
+    counts. Name and Version columns are located from the header row, so a reordered table
+    pairs name to version correctly; both default to the canonical positions (0, 1)."""
+    findings: list[dict] = []
+    in_stack = False
+    header_seen = False
+    name_idx, ver_idx = 0, 1
+    scan = blank_fences(body)
+    for i, raw in enumerate(scan.splitlines()):
+        if HEADING.match(raw):
+            in_stack = re.match(r"^##\s+Stack\b", raw) is not None
+            header_seen = False
+            name_idx, ver_idx = 0, 1
+            continue
+        if not in_stack or not raw.lstrip().startswith("|"):
+            continue
+        if set(raw.strip()) <= set("|-: "):
+            continue  # separator row
+        cells = _table_cells(raw)
+        if not header_seen:
+            header_seen = True
+            for j, c in enumerate(cells):
+                if c.lower() == "name":
+                    name_idx = j
+                elif c.lower() == "version":
+                    ver_idx = j
+            continue
+        name = cells[name_idx] if len(cells) > name_idx else ""
+        version = cells[ver_idx] if len(cells) > ver_idx else ""
+        if not name or TEMPLATE_TOKEN.search(name):
+            continue
+        if not version or TEMPLATE_TOKEN.search(version):
+            findings.append({
+                "category": "version_pin",
+                "severity": "medium",
+                "detail": f"Stack entry {name!r} has no version",
+                "location": f"{SPINE} (line {offset + i + 1})",
+            })
+    return findings
+
+
+def _table_cells(row: str) -> list[str]:
+    """Split a markdown table row into trimmed cells, dropping the leading/trailing pipe."""
+    s = row.strip()
+    if s.startswith("|"):
+        s = s[1:]
+    if s.endswith("|"):
+        s = s[:-1]
+    return [c.strip() for c in s.split("|")]
+
+
+def lint(text: str) -> dict:
+    frontmatter, body, offset = split_frontmatter(text)
+    findings: list[dict] = []
+    findings += find_frontmatter_placeholders(frontmatter)
+    findings += find_placeholders(body, offset)
+    findings += find_ad_issues(body, offset)
+    findings += find_unpinned_stack(body, offset)
+    counts: dict[str, int] = {}
+    for f in findings:
+        counts[f["severity"]] = counts.get(f["severity"], 0) + 1
+    return {
+        "ok": len(findings) == 0,
+        "spine": SPINE,
+        "total_findings": len(findings),
+        "by_severity": counts,
+        "findings": findings,
+    }
+
+
+def main(argv: list[str] | None = None) -> int:
+    ap = argparse.ArgumentParser(description="Lint an architecture spine for mechanical integrity.")
+    ap.add_argument("--workspace", required=True, help="run folder containing ARCHITECTURE-SPINE.md")
+    ap.add_argument("-o", "--output", help="write JSON here instead of stdout")
+    args = ap.parse_args(argv)
+
+    spine_path = Path(args.workspace) / SPINE
+    if not spine_path.exists():
+        result = {"ok": False, "error": f"{spine_path} not found", "findings": [], "total_findings": 0}
+    else:
+        try:
+            text = spine_path.read_text(encoding="utf-8")
+        except (OSError, UnicodeDecodeError) as e:
+            # honor the "exit code is always 0" contract: a read/decode failure travels in JSON
+            result = {"ok": False, "error": f"could not read {spine_path}: {e}", "findings": [], "total_findings": 0}
+        else:
+            result = lint(text)
+
+    out = json.dumps(result, indent=2)
+    if args.output:
+        Path(args.output).write_text(out + "\n", encoding="utf-8")
+    else:
+        print(out)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

src/bmm-skills/3-solutioning/bmad-architecture/scripts/tests/test_lint_spine.py

@@ -0,0 +1,270 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = ["pytest>=8.0"]
+# ///
+"""Tests for lint_spine.py. Run: uv run --with pytest pytest scripts/tests/test_lint_spine.py
+
+The spine under test: a clean spine lints empty; the linter catches exactly the
+mechanical defects a prompt is unreliable at — literal placeholders, AD-n id breakage,
+AD-n blocks missing required fields, and unpinned Stack versions.
+"""
+import importlib.util
+import json
+import re
+import sys
+from pathlib import Path
+
+import pytest
+
+_SPEC = importlib.util.spec_from_file_location(
+    "lint_spine", Path(__file__).resolve().parent.parent / "lint_spine.py"
+)
+lint_spine = importlib.util.module_from_spec(_SPEC)
+sys.modules["lint_spine"] = lint_spine
+_SPEC.loader.exec_module(lint_spine)
+
+
+CLEAN = """---
+name: 'Demo'
+---
+
+## Invariants & Rules
+
+### AD-1 — single write path
+
+- **Binds:** all
+- **Prevents:** divergent mutation
+- **Rule:** state changes only through the command bus
+
+### AD-2 — layered deps `[ADOPTED]`
+
+- **Binds:** all
+- **Prevents:** import cycles
+- **Rule:** ui -> app -> domain, never backward
+
+```mermaid
+flowchart LR
+  A --> B{decision}
+```
+
+## Stack
+
+| Name | Version |
+| --- | --- |
+| fastapi | 0.115 |
+| pydantic | 2.9 |
+"""
+
+
+def cats(result):
+    return sorted(f["category"] for f in result["findings"])
+
+
+def test_clean_spine_passes():
+    result = lint_spine.lint(CLEAN)
+    assert result["ok"] is True
+    assert result["total_findings"] == 0
+
+
+def test_mermaid_braces_not_flagged():
+    # the {decision} node lives in a fenced block and must not read as a template token
+    result = lint_spine.lint(CLEAN)
+    assert "placeholder" not in cats(result)
+
+
+def test_placeholder_markers_caught():
+    text = CLEAN.replace("the command bus", "TBD")
+    result = lint_spine.lint(text)
+    assert "placeholder" in cats(result)
+
+
+def test_similar_to_caught():
+    text = CLEAN.replace("import cycles", "similar to AD-1")
+    result = lint_spine.lint(text)
+    assert any("cross-reference" in f["detail"] for f in result["findings"])
+
+
+def test_unfilled_template_token_caught():
+    text = CLEAN.replace("single write path", "{decision}")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "placeholder" for f in result["findings"])
+
+
+def test_duplicate_ad_id_caught():
+    text = CLEAN.replace("### AD-2 — layered deps `[ADOPTED]`", "### AD-1 — layered deps")
+    result = lint_spine.lint(text)
+    assert "ad_id" in cats(result)
+
+
+def test_non_monotonic_ad_id_caught():
+    text = CLEAN.replace("### AD-2 — layered deps `[ADOPTED]`", "### AD-5 — layered deps").replace(
+        "### AD-1 — single write path", "### AD-9 — single write path"
+    )
+    result = lint_spine.lint(text)
+    assert any("non-monotonic" in f["detail"] for f in result["findings"])
+
+
+def test_missing_field_caught():
+    text = CLEAN.replace("- **Rule:** state changes only through the command bus\n", "")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "ad_fields" and "rule" in f["detail"] for f in result["findings"])
+
+
+def test_unpinned_dep_caught():
+    text = CLEAN.replace("| fastapi | 0.115 |", "| fastapi |  |")
+    result = lint_spine.lint(text)
+    assert "version_pin" in cats(result)
+
+
+def test_placeholder_version_caught():
+    text = CLEAN.replace("| fastapi | 0.115 |", "| fastapi | {pin} |")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "version_pin" and "fastapi" in f["detail"] for f in result["findings"])
+
+
+def test_no_stack_section_ok():
+    text = CLEAN.split("## Stack")[0]
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_stack_skeleton_row_not_version_pinned():
+    # a leftover {token} name is the placeholder pass's job, not a double-reported version_pin
+    text = CLEAN.replace("| fastapi | 0.115 |", "| {language / framework} | {pinned version} |")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_stack_html_comment_not_parsed_as_row():
+    text = CLEAN.replace("## Stack\n", "## Stack\n\n<!-- SEED — verified current 2026-06 -->\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_template_token_is_low_severity():
+    # a bare {token} can be legitimate brace prose; it is flagged, but low (not high) so the
+    # mechanical pass stays near-zero false-positive
+    text = CLEAN.replace("single write path", "{decision}")
+    result = lint_spine.lint(text)
+    toks = [f for f in result["findings"] if f["category"] == "placeholder" and "template token" in f["detail"]]
+    assert toks and all(f["severity"] == "low" for f in toks)
+
+
+def test_no_frontmatter_body_still_scanned():
+    text = "## Invariants\n\n### AD-1 — x\n\n- **Binds:** all\n- **Prevents:** drift\n- **Rule:** TBD\n"
+    result = lint_spine.lint(text)
+    assert "placeholder" in cats(result)  # TBD caught even with no frontmatter
+
+
+def test_frontmatter_value_with_dashes_not_truncated():
+    # a value containing '---' must not be read as the closing fence (line-exact close)
+    text = ("---\nname: 'x'\nscope: 'phase 1 --- phase 2'\n---\n\n"
+            "## Stack\n\n| Name | Version |\n| --- | --- |\n| fastapi |  |\n")
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "version_pin" for f in result["findings"])  # read past the inline ---
+
+
+def test_ad_heading_in_fence_not_counted():
+    text = (
+        "---\nname: 'x'\n---\n\n"
+        "### AD-1 — real\n\n- **Binds:** all\n- **Prevents:** drift\n- **Rule:** do x\n\n"
+        "## Docs\n\n```text\n### AD-2 — illustrative only, no fields\n```\n"
+    )
+    result = lint_spine.lint(text)
+    assert result["ok"] is True  # the fenced AD-2 is not a live AD → no ad_fields/ad_id finding
+
+
+def test_stack_table_flags_only_the_unpinned_row():
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Name | Version |\n| --- | --- |\n"
+            "| fastapi | 0.115 |\n| redis |  |\n")
+    result = lint_spine.lint(text)
+    pins = [f for f in result["findings"] if f["category"] == "version_pin"]
+    assert len(pins) == 1 and "redis" in pins[0]["detail"]
+
+
+def test_stack_table_all_pinned_ok():
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Name | Version |\n| --- | --- |\n"
+            "| fastapi | 0.115 |\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_fenced_stack_rows_not_parsed():
+    # an illustrative fenced table under ## Stack must not be read as live rows (fences are
+    # blanked first, like every other pass) — a blank-version row inside a fence is not a finding
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Name | Version |\n| --- | --- |\n"
+            "| fastapi | 0.115 |\n\n```text\n| example |  |\n```\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_fenced_stack_heading_not_live():
+    # a `## Stack` heading shown inside a code fence is not the live Stack section
+    text = ("---\nname: 'x'\n---\n\n## Docs\n\n```md\n## Stack\n\n| foo |  |\n```\n")
+    result = lint_spine.lint(text)
+    assert "version_pin" not in cats(result)
+
+
+def test_renamed_stack_heading_still_scanned():
+    # the heading match is word-boundary, so a varied `## Stack` heading still counts
+    text = ("---\nname: 'x'\n---\n\n## Stack & Versions\n\n| Name | Version |\n| --- | --- |\n"
+            "| redis |  |\n")
+    result = lint_spine.lint(text)
+    pins = [f for f in result["findings"] if f["category"] == "version_pin"]
+    assert len(pins) == 1 and "redis" in pins[0]["detail"]
+
+
+def test_reordered_columns_pair_name_to_version():
+    # Version-then-Name header: the unpinned row must still be flagged by its real name
+    text = ("---\nname: 'x'\n---\n\n## Stack\n\n| Version | Name |\n| --- | --- |\n"
+            "| 0.115 | fastapi |\n|  | redis |\n")
+    result = lint_spine.lint(text)
+    pins = [f for f in result["findings"] if f["category"] == "version_pin"]
+    assert len(pins) == 1 and "redis" in pins[0]["detail"]
+
+
+def test_placeholder_line_number_is_absolute():
+    # a TBD after a multi-line fence reports its real file line (fence blanked, not collapsed)
+    text = (
+        "---\nname: 'x'\n---\n\n"
+        "## A\n\n"
+        "```text\nf1\nf2\nf3\n```\n\n"
+        "TBD here\n"
+    )
+    result = lint_spine.lint(text)
+    ph = next(f for f in result["findings"] if "TBD" in f["detail"])
+    n = int(re.search(r"line (\d+)", ph["location"]).group(1))
+    assert n == 13
+
+
+def test_missing_spine_file_reports_error(tmp_path, capsys):
+    rc = lint_spine.main(["--workspace", str(tmp_path)])
+    out = json.loads(capsys.readouterr().out)
+    assert rc == 0 and out["ok"] is False and "not found" in out["error"]
+
+
+def test_frontmatter_unfilled_token_caught():
+    # an unfilled {scope}/{paradigm}/{date} in frontmatter is part of the contract and must lint
+    text = "---\nname: 'x'\nscope: '{what this spine governs}'\n---\n\n## Invariants\n"
+    result = lint_spine.lint(text)
+    fm = [f for f in result["findings"] if f["category"] == "placeholder" and "frontmatter" in f["detail"]]
+    assert fm and any("template token" in f["detail"] for f in fm)
+
+
+def test_frontmatter_tbd_caught():
+    text = "---\nname: 'x'\nstatus: TBD\n---\n\n## Invariants\n"
+    result = lint_spine.lint(text)
+    assert any(f["category"] == "placeholder" and "frontmatter" in f["detail"] and "TBD" in f["detail"]
+               for f in result["findings"])
+
+
+def test_unreadable_spine_returns_error_not_crash(tmp_path, capsys):
+    # a spine that exists but can't be UTF-8 decoded must yield error JSON + exit 0, not a traceback
+    (tmp_path / lint_spine.SPINE).write_bytes(b"\xff\xfe bad bytes not utf-8")
+    rc = lint_spine.main(["--workspace", str(tmp_path)])
+    out = json.loads(capsys.readouterr().out)
+    assert rc == 0 and out["ok"] is False and "could not read" in out["error"]
+
+
+if __name__ == "__main__":
+    sys.exit(pytest.main([__file__, "-q"]))

src/bmm-skills/3-solutioning/bmad-create-architecture/SKILL.md

@@ -1,74 +1,30 @@
 ---
 name: bmad-create-architecture
-description: 'Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design"'
+description: 'DEPRECATED — consolidated into bmad-architecture create intent - this skill will be removed in v7 in favor of `bmad-architecture`.'
 ---
 
-# Architecture Workflow
+# DEPRECATED — forwards to bmad-architecture (create intent)
 
-**Goal:** Create comprehensive architecture decisions through collaborative step-by-step discovery that ensures AI agents implement consistently.
+This skill was consolidated into `bmad-architecture`. It is retained as a thin compatibility shim so existing invocations by name and `_bmad/custom/bmad-create-architecture.toml` override files keep working. New work should invoke `bmad-architecture` directly — it detects create / update / validate intent from the conversation.
-
-**Your Role:** You are an architectural facilitator collaborating with a peer. This is a partnership, not a client-vendor relationship. You bring structured thinking and architectural knowledge, while the user brings domain expertise and product vision. Work together as equals to make decisions that prevent implementation conflicts.
-
-## Conventions
-
-- Bare paths (e.g. `steps/step-01-init.md`) resolve from the skill root.
-- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
-- `{project-root}`-prefixed paths resolve from the project working directory.
-- `{skill-name}` resolves to the skill directory's basename.
-
-## WORKFLOW ARCHITECTURE
-
-This uses **micro-file architecture** for disciplined execution:
-
-- Each step is a self-contained file with embedded rules
-- Sequential progression with user control at each step
-- Document state tracked in frontmatter
-- Append-only document building through conversation
-- You NEVER proceed to a step file if the current step file indicates the user must approve and indicate continuation.
 
 ## On Activation
 
-### Step 1: Resolve the Workflow Block
+1. Resolve customization: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`. This picks up any `{project-root}/_bmad/custom/bmad-create-architecture.toml` and `bmad-create-architecture.user.toml` overrides for the legacy fields (`activation_steps_prepend`, `activation_steps_append`, `persistent_facts`, `on_complete`).
 
-Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`
+2. Load `{project-root}/_bmad/bmm/config.yaml` (and `config.user.yaml` if present) to resolve `{user_name}` and `{communication_language}`.
 
-**If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
+3. Emit a deprecation notice to the user in `{communication_language}`:
 
-1. `{skill-root}/customize.toml` — defaults
+   > Notice: `bmad-create-architecture` is deprecated and will be removed in a future release. It now forwards to `bmad-architecture` with create intent. To silence this notice and access the full new customization surface (`spine_template`, `spine_output_path`, `run_folder_pattern`, `doc_standards`, `external_sources`, `external_handoffs`, `finalize_reviewers`), migrate `_bmad/custom/bmad-create-architecture.toml` to `_bmad/custom/bmad-architecture.toml` and invoke `bmad-architecture` directly next time. Customization fields that were in this version still remain in the new version and will be respected if present in `_bmad/custom/bmad-architecture.toml`, but the new version also supports additional fields that you can take advantage of by migrating.
-2. `{project-root}/_bmad/custom/{skill-name}.toml` — team overrides
-3. `{project-root}/_bmad/custom/{skill-name}.user.toml` — personal overrides
 
-Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
+4. Invoke `bmad-architecture` with the following context. Pass these as the activating context so `bmad-architecture` honors them instead of resolving its own customization from scratch:
 
-### Step 2: Execute Prepend Steps
+   - **Intent:** `create` — skip `bmad-architecture`'s usual intent detection step.
+   - **Pre-resolved legacy customization** — use these in place of resolving from `bmad-architecture`'s own `customize.toml` for the four legacy fields. For everything else (`spine_template`, `spine_output_path`, `run_folder_pattern`, `doc_standards`, `external_sources`, `external_handoffs`, `finalize_reviewers`), use `bmad-architecture`'s own defaults and overrides as normal:
+     - `activation_steps_prepend` = the resolved value from step 1
+     - `activation_steps_append` = the resolved value from step 1
+     - `persistent_facts` = the resolved value from step 1
+     - `on_complete` = the resolved value from step 1
+   - **Original user input:** forward whatever the user said when invoking this skill verbatim.
 
-Execute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.
+   `bmad-architecture` takes the workflow from here. Do not execute any further steps in this shim.
-
-### Step 3: Load Persistent Facts
-
-Treat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.
-
-### Step 4: Load Config
-
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
-- Use `{user_name}` for greeting
-- Use `{communication_language}` for all communications
-- Use `{document_output_language}` for output documents
-- Use `{planning_artifacts}` for output location and artifact scanning
-- Use `{project_knowledge}` for additional context scanning
-
-### Step 5: Greet the User
-
-Greet `{user_name}`, speaking in `{communication_language}`.
-
-### Step 6: Execute Append Steps
-
-Execute each entry in `{workflow.activation_steps_append}` in order.
-
-Activation is complete. If `activation_steps_prepend` or `activation_steps_append` were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.
-
-## Execution
-
-Read fully and follow: `./steps/step-01-init.md` to begin the workflow.
-
-**Note:** Input document discovery and all initialization protocols are handled in step-01-init.md.

src/bmm-skills/3-solutioning/bmad-create-architecture/architecture-decision-template.md

@@ -1,12 +0,0 @@
----
-stepsCompleted: []
-inputDocuments: []
-workflowType: 'architecture'
-project_name: '{{project_name}}'
-user_name: '{{user_name}}'
-date: '{{date}}'
----
-
-# Architecture Decision Document
-
-_This document builds collaboratively through step-by-step discovery. Sections are appended as we work through each architectural decision together._

src/bmm-skills/3-solutioning/bmad-create-architecture/data/domain-complexity.csv

@@ -1,13 +0,0 @@
-domain,signals,complexity_level,suggested_workflow,web_searches
-e_commerce,"shopping,cart,checkout,payment,products,store",medium,standard,"ecommerce architecture patterns, payment processing, inventory management"
-fintech,"banking,payment,trading,finance,money,investment",high,enhanced,"financial security, PCI compliance, trading algorithms, fraud detection"
-healthcare,"medical,diagnostic,clinical,patient,hospital,health",high,enhanced,"HIPAA compliance, medical data security, FDA regulations, health tech"
-social,"social network,community,users,friends,posts,sharing",high,advanced,"social graph algorithms, feed ranking, notification systems, privacy"
-education,"learning,course,student,teacher,training,academic",medium,standard,"LMS architecture, progress tracking, assessment systems, video streaming"
-productivity,"productivity,workflow,tasks,management,business,tools",medium,standard,"collaboration patterns, real-time editing, notification systems, integration"
-media,"content,media,video,audio,streaming,broadcast",high,advanced,"CDN architecture, video encoding, streaming protocols, content delivery"
-iot,"IoT,sensors,devices,embedded,smart,connected",high,advanced,"device communication, real-time data processing, edge computing, security"
-government,"government,civic,public,admin,policy,regulation",high,enhanced,"accessibility standards, security clearance, data privacy, audit trails"
-process_control,"industrial automation,process control,PLC,SCADA,DCS,HMI,operational technology,control system,cyberphysical,MES,instrumentation,I&C,P&ID",high,advanced,"industrial process control architecture, SCADA system design, OT cybersecurity architecture, real-time control systems"
-building_automation,"building automation,BAS,BMS,HVAC,smart building,fire alarm,fire protection,fire suppression,life safety,elevator,DDC,access control,sequence of operations,commissioning",high,advanced,"building automation architecture, BACnet integration patterns, smart building design, building management system security"
-gaming,"game,gaming,multiplayer,real-time,interactive,entertainment",high,advanced,"real-time multiplayer, game engine architecture, matchmaking, leaderboards"

src/bmm-skills/3-solutioning/bmad-create-architecture/data/project-types.csv

@@ -1,7 +0,0 @@
-project_type,detection_signals,description,typical_starters
-web_app,"website,web application,browser,frontend,UI,interface",Web-based applications running in browsers,Next.js, Vite, Remix
-mobile_app,"mobile,iOS,Android,app,smartphone,tablet",Native mobile applications,React Native, Expo, Flutter
-api_backend,"API,REST,GraphQL,backend,service,microservice",Backend services and APIs,NestJS, Express, Fastify
-full_stack,"full-stack,complete,web+mobile,frontend+backend",Applications with both frontend and backend,T3 App, RedwoodJS, Blitz
-cli_tool,"CLI,command line,terminal,console,tool",Command-line interface tools,oclif, Commander, Caporal
-desktop_app,"desktop,Electron,Tauri,native app,macOS,Windows",Desktop applications,Electron, Tauri, Flutter Desktop

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-01-init.md

@@ -1,153 +0,0 @@
-# Step 1: Architecture Workflow Initialization
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on initialization and setup only - don't look ahead to future steps
-- 🚪 DETECT existing workflow state and handle continuation properly
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 💾 Initialize document and update frontmatter
-- 📖 Set up frontmatter `stepsCompleted: [1]` before loading next step
-- 🚫 FORBIDDEN to load next step until setup is complete
-
-## CONTEXT BOUNDARIES:
-
-- Variables from workflow.md are available in memory
-- Previous context = what's in output document + frontmatter
-- Don't assume knowledge from other steps
-- Input document discovery happens in this step
-
-## YOUR TASK:
-
-Initialize the Architecture workflow by detecting continuation state, discovering input documents, and setting up the document for collaborative architectural decision making.
-
-## INITIALIZATION SEQUENCE:
-
-### 1. Check for Existing Workflow
-
-First, check if the output document already exists:
-
-- Look for existing {planning_artifacts}/`*architecture*.md`
-- If exists, read the complete file(s) including frontmatter
-- If not exists, this is a fresh workflow
-
-### 2. Handle Continuation (If Document Exists)
-
-If the document exists and has frontmatter with `stepsCompleted`:
-
-- **STOP here** and load `./step-01b-continue.md` immediately
-- Do not proceed with any initialization tasks
-- Let step-01b handle the continuation logic
-
-### 3. Fresh Workflow Setup (If No Document)
-
-If no document exists or no `stepsCompleted` in frontmatter:
-
-#### A. Input Document Discovery
-
-Discover and load context documents using smart discovery. Documents can be in the following locations:
-- {planning_artifacts}/**
-- {output_folder}/**
-- {project_knowledge}/**
-- {project-root}/docs/**
-
-Also - when searching - documents can be a single markdown file, or a folder with an index and multiple files. For Example, if searching for `*foo*.md` and not found, also search for a folder called *foo*/index.md (which indicates sharded content)
-
-Try to discover the following:
-- Product Brief (`*brief*.md`)
-- Product Requirements Document (`*prd*.md`)
-- UX Design (`*ux-design*.md`) and other
-- Research Documents (`*research*.md`)
-- Project Documentation (generally multiple documents might be found for this in the `{project_knowledge}` or `{project-root}/docs` folder.)
-- Project Context (`**/project-context.md`)
-
-<critical>Confirm what you have found with the user, along with asking if the user wants to provide anything else. Only after this confirmation will you proceed to follow the loading rules</critical>
-
-**Loading Rules:**
-
-- Load ALL discovered files completely that the user confirmed or provided (no offset/limit)
-- If there is a project context, whatever is relevant should try to be biased in the remainder of this whole workflow process
-- For sharded folders, load ALL files to get complete picture, using the index first to potentially know the potential of each document
-- index.md is a guide to what's relevant whenever available
-- Track all successfully loaded files in frontmatter `inputDocuments` array
-
-#### B. Validate Required Inputs
-
-Before proceeding, verify we have the essential inputs:
-
-**PRD Validation:**
-
-- If no PRD found: "Architecture requires a PRD to work from. Please run the PRD workflow first or provide the PRD file path."
-- Do NOT proceed without PRD
-
-**Other Input that might exist:**
-
-- UX Spec: "Provides UI/UX architectural requirements"
-
-#### C. Create Initial Document
-
-Copy the template from `../architecture-decision-template.md` to `{planning_artifacts}/architecture.md`
-
-#### D. Complete Initialization and Report
-
-Complete setup and report to user:
-
-**Document Setup:**
-
-- Created: `{planning_artifacts}/architecture.md` from template
-- Initialized frontmatter with workflow state
-
-**Input Documents Discovered:**
-Report what was found:
-"Welcome {{user_name}}! I've set up your Architecture workspace for {{project_name}}.
-
-**Documents Found:**
-
-- PRD: {number of PRD files loaded or "None found - REQUIRED"}
-- UX Design: {number of UX files loaded or "None found"}
-- Research: {number of research files loaded or "None found"}
-- Project docs: {number of project files loaded or "None found"}
-- Project context: {project_context_rules count of rules for AI agents found}
-
-**Files loaded:** {list of specific file names or "No additional documents found"}
-
-Ready to begin architectural decision making. Do you have any other documents you'd like me to include?
-
-[C] Continue to project context analysis
-
-## SUCCESS METRICS:
-
-✅ Existing workflow detected and handed off to step-01b correctly
-✅ Fresh workflow initialized with template and frontmatter
-✅ Input documents discovered and loaded using sharded-first logic
-✅ All discovered files tracked in frontmatter `inputDocuments`
-✅ PRD requirement validated and communicated
-✅ User confirmed document setup and can proceed
-
-## FAILURE MODES:
-
-❌ Proceeding with fresh initialization when existing workflow exists
-❌ Not updating frontmatter with discovered input documents
-❌ Creating document without proper template
-❌ Not checking sharded folders first before whole files
-❌ Not reporting what documents were found to user
-❌ Proceeding without validating PRD requirement
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects [C] to continue, only after ensuring all the template output has been created, then load `./step-02-context.md` to analyze the project context and begin architectural decision making.
-
-Remember: Do NOT proceed to step-02 until user explicitly selects [C] from the menu and setup is confirmed!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-01b-continue.md

@@ -1,173 +0,0 @@
-# Step 1b: Workflow Continuation Handler
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on understanding current state and getting user confirmation
-- 🚪 HANDLE workflow resumption smoothly and transparently
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 📖 Read existing document completely to understand current state
-- 💾 Update frontmatter to reflect continuation
-- 🚫 FORBIDDEN to proceed to next step without user confirmation
-
-## CONTEXT BOUNDARIES:
-
-- Existing document and frontmatter are available
-- Input documents already loaded should be in frontmatter `inputDocuments`
-- Steps already completed are in `stepsCompleted` array
-- Focus on understanding where we left off
-
-## YOUR TASK:
-
-Handle workflow continuation by analyzing existing work and guiding the user to resume at the appropriate step.
-
-## CONTINUATION SEQUENCE:
-
-### 1. Analyze Current Document State
-
-Read the existing architecture document completely and analyze:
-
-**Frontmatter Analysis:**
-
-- `stepsCompleted`: What steps have been done
-- `inputDocuments`: What documents were loaded
-- `lastStep`: Last step that was executed
-- `project_name`, `user_name`, `date`: Basic context
-
-**Content Analysis:**
-
-- What sections exist in the document
-- What architectural decisions have been made
-- What appears incomplete or in progress
-- Any TODOs or placeholders remaining
-
-### 2. Present Continuation Summary
-
-Show the user their current progress:
-
-"Welcome back {{user_name}}! I found your Architecture work for {{project_name}}.
-
-**Current Progress:**
-
-- Steps completed: {{stepsCompleted list}}
-- Last step worked on: Step {{lastStep}}
-- Input documents loaded: {{number of inputDocuments}} files
-
-**Document Sections Found:**
-{list all H2/H3 sections found in the document}
-
-{if_incomplete_sections}
-**Incomplete Areas:**
-
-- {areas that appear incomplete or have placeholders}
-  {/if_incomplete_sections}
-
-**What would you like to do?**
-[R] Resume from where we left off
-[C] Continue to next logical step
-[O] Overview of all remaining steps
-[X] Start over (will overwrite existing work)
-"
-
-### 3. Handle User Choice
-
-#### If 'R' (Resume from where we left off):
-
-- Identify the next step based on `stepsCompleted`
-- Load the appropriate step file to continue
-- Example: If `stepsCompleted: [1, 2, 3]`, load `./step-04-decisions.md`
-
-#### If 'C' (Continue to next logical step):
-
-- Analyze the document content to determine logical next step
-- May need to review content quality and completeness
-- If content seems complete for current step, advance to next
-- If content seems incomplete, suggest staying on current step
-
-#### If 'O' (Overview of all remaining steps):
-
-- Provide brief description of all remaining steps
-- Let user choose which step to work on
-- Don't assume sequential progression is always best
-
-#### If 'X' (Start over):
-
-- Confirm: "This will delete all existing architectural decisions. Are you sure? (y/n)"
-- If confirmed: Delete existing document and read fully and follow: `./step-01-init.md`
-- If not confirmed: Return to continuation menu
-
-### 4. Navigate to Selected Step
-
-After user makes choice:
-
-**Load the selected step file:**
-
-- Update frontmatter `lastStep` to reflect current navigation
-- Execute the selected step file
-- Let that step handle the detailed continuation logic
-
-**State Preservation:**
-
-- Maintain all existing content in the document
-- Keep `stepsCompleted` accurate
-- Track the resumption in workflow status
-
-### 5. Special Continuation Cases
-
-#### If `stepsCompleted` is empty but document has content:
-
-- This suggests an interrupted workflow
-- Ask user: "I see the document has content but no steps are marked as complete. Should I analyze what's here and set the appropriate step status?"
-
-#### If document appears corrupted or incomplete:
-
-- Ask user: "The document seems incomplete. Would you like me to try to recover what's here, or would you prefer to start fresh?"
-
-#### If document is complete but workflow not marked as done:
-
-- Ask user: "The architecture looks complete! Should I mark this workflow as finished, or is there more you'd like to work on?"
-
-## SUCCESS METRICS:
-
-✅ Existing document state properly analyzed and understood
-✅ User presented with clear continuation options
-✅ User choice handled appropriately and transparently
-✅ Workflow state preserved and updated correctly
-✅ Navigation to appropriate step handled smoothly
-
-## FAILURE MODES:
-
-❌ Not reading the complete existing document before making suggestions
-❌ Losing track of what steps were actually completed
-❌ Automatically proceeding without user confirmation of next steps
-❌ Not checking for incomplete or placeholder content
-❌ Losing existing document content during resumption
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects their continuation option, load the appropriate step file based on their choice. The step file will handle the detailed work from that point forward.
-
-Valid step files to load:
-- `./step-02-context.md`
-- `./step-03-starter.md`
-- `./step-04-decisions.md`
-- `./step-05-patterns.md`
-- `./step-06-structure.md`
-- `./step-07-validation.md`
-- `./step-08-complete.md`
-
-Remember: The goal is smooth, transparent resumption that respects the work already done while giving the user control over how to proceed.

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-02-context.md

@@ -1,224 +0,0 @@
-# Step 2: Project Context Analysis
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on understanding project scope and requirements for architecture
-- 🎯 ANALYZE loaded documents, don't assume or generate requirements
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- ⚠️ Present A/P/C menu after generating project context analysis
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1, 2]` before loading next step
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## COLLABORATION MENUS (A/P/C):
-
-This step will generate content and present choices:
-
-- **A (Advanced Elicitation)**: Use discovery protocols to develop deeper insights about project context and architectural implications
-- **P (Party Mode)**: Bring multiple perspectives to analyze project requirements from different architectural angles
-- **C (Continue)**: Save the content to the document and proceed to next step
-
-## PROTOCOL INTEGRATION:
-
-- When 'A' selected: Invoke the `bmad-advanced-elicitation` skill
-- When 'P' selected: Invoke the `bmad-party-mode` skill
-- PROTOCOLS always return to display this step's A/P/C menu after the A or P have completed
-- User accepts/rejects protocol changes before proceeding
-
-## CONTEXT BOUNDARIES:
-
-- Current document and frontmatter from step 1 are available
-- Input documents already loaded are in memory (PRD, epics, UX spec, etc.)
-- Focus on architectural implications of requirements
-- No technology decisions yet - pure analysis phase
-
-## YOUR TASK:
-
-Fully read and Analyze the loaded project documents to understand architectural scope, requirements, and constraints before beginning decision making.
-
-## CONTEXT ANALYSIS SEQUENCE:
-
-### 1. Review Project Requirements
-
-**From PRD Analysis:**
-
-- Extract and analyze Functional Requirements (FRs)
-- Identify Non-Functional Requirements (NFRs) like performance, security, compliance
-- Note any technical constraints or dependencies mentioned
-- Count and categorize requirements to understand project scale
-
-**From Epics/Stories (if available):**
-
-- Map epic structure and user stories to architectural components
-- Extract acceptance criteria for technical implications
-- Identify cross-cutting concerns that span multiple epics
-- Estimate story complexity for architectural planning
-
-**From UX Design (if available):**
-
-- Extract architectural implications from UX requirements:
-  - Component complexity (simple forms vs rich interactions)
-  - Animation/transition requirements
-  - Real-time update needs (live data, collaborative features)
-  - Platform-specific UI requirements
-  - Accessibility standards (WCAG compliance level)
-  - Responsive design breakpoints
-  - Offline capability requirements
-  - Performance expectations (load times, interaction responsiveness)
-
-### 2. Project Scale Assessment
-
-Calculate and present project complexity:
-
-**Complexity Indicators:**
-
-- Real-time features requirements
-- Multi-tenancy needs
-- Regulatory compliance requirements
-- Integration complexity
-- User interaction complexity
-- Data complexity and volume
-
-### 3. Reflect Understanding
-
-Present your analysis back to user for validation:
-
-"I'm reviewing your project documentation for {{project_name}}.
-
-{if_epics_loaded}I see {{epic_count}} epics with {{story_count}} total stories.{/if_epics_loaded}
-{if_no_epics}I found {{fr_count}} functional requirements organized into {{fr_category_list}}.{/if_no_epics}
-{if_ux_loaded}I also found your UX specification which defines the user experience requirements.{/if_ux_loaded}
-
-**Key architectural aspects I notice:**
-
-- [Summarize core functionality from FRs]
-- [Note critical NFRs that will shape architecture]
-- {if_ux_loaded}[Note UX complexity and technical requirements]{/if_ux_loaded}
-- [Identify unique technical challenges or constraints]
-- [Highlight any regulatory or compliance requirements]
-
-**Scale indicators:**
-
-- Project complexity appears to be: [low/medium/high/enterprise]
-- Primary technical domain: [web/mobile/api/backend/full-stack/etc]
-- Cross-cutting concerns identified: [list major ones]
-
-This analysis will help me guide you through the architectural decisions needed to ensure AI agents implement this consistently.
-
-Does this match your understanding of the project scope and requirements?"
-
-### 4. Generate Project Context Content
-
-Prepare the content to append to the document:
-
-#### Content Structure:
-
-```markdown
-## Project Context Analysis
-
-### Requirements Overview
-
-**Functional Requirements:**
-{{analysis of FRs and what they mean architecturally}}
-
-**Non-Functional Requirements:**
-{{NFRs that will drive architectural decisions}}
-
-**Scale & Complexity:**
-{{project_scale_assessment}}
-
-- Primary domain: {{technical_domain}}
-- Complexity level: {{complexity_level}}
-- Estimated architectural components: {{component_count}}
-
-### Technical Constraints & Dependencies
-
-{{known_constraints_dependencies}}
-
-### Cross-Cutting Concerns Identified
-
-{{concerns_that_will_affect_multiple_components}}
-```
-
-### 5. Present Content and Menu
-
-Show the generated content and present choices:
-
-"I've drafted the Project Context Analysis based on your requirements. This sets the foundation for our architectural decisions.
-
-**Here's what I'll add to the document:**
-
-[Show the complete markdown content from step 4]
-
-**What would you like to do?**
-[A] Advanced Elicitation - Let's dive deeper into architectural implications
-[P] Party Mode - Bring different perspectives to analyze requirements
-[C] Continue - Save this analysis and begin architectural decisions"
-
-### 6. Handle Menu Selection
-
-#### If 'A' (Advanced Elicitation):
-
-- Invoke the `bmad-advanced-elicitation` skill with the current context analysis
-- Process the enhanced architectural insights that come back
-- Ask user: "Accept these enhancements to the project context analysis? (y/n)"
-- If yes: Update content with improvements, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'P' (Party Mode):
-
-- Invoke the `bmad-party-mode` skill with the current project context
-- Process the collaborative improvements to architectural understanding
-- Ask user: "Accept these changes to the project context analysis? (y/n)"
-- If yes: Update content with improvements, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'C' (Continue):
-
-- Append the final content to `{planning_artifacts}/architecture.md`
-- Update frontmatter: `stepsCompleted: [1, 2]`
-- Load `./step-03-starter.md`
-
-## APPEND TO DOCUMENT:
-
-When user selects 'C', append the content directly to the document using the structure from step 4.
-
-## SUCCESS METRICS:
-
-✅ All input documents thoroughly analyzed for architectural implications
-✅ Project scope and complexity clearly assessed and validated
-✅ Technical constraints and dependencies identified
-✅ Cross-cutting concerns mapped for architectural planning
-✅ User confirmation of project understanding
-✅ A/P/C menu presented and handled correctly
-✅ Content properly appended to document when C selected
-
-## FAILURE MODES:
-
-❌ Skimming documents without deep architectural analysis
-❌ Missing or misinterpreting critical NFRs
-❌ Not validating project understanding with user
-❌ Underestimating complexity indicators
-❌ Generating content without real analysis of loaded documents
-❌ Not presenting A/P/C menu after content generation
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects 'C' and content is saved to document, load `./step-03-starter.md` to evaluate starter template options.
-
-Remember: Do NOT proceed to step-03 until user explicitly selects 'C' from the A/P/C menu and content is saved!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-03-starter.md

@@ -1,329 +0,0 @@
-# Step 3: Starter Template Evaluation
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on evaluating starter template options with current versions
-- 🌐 ALWAYS search the web to verify current versions - NEVER trust hardcoded versions
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete architecture
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 🌐 Search the web to verify current versions and options
-- ⚠️ Present A/P/C menu after generating starter template analysis
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1, 2, 3]` before loading next step
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## COLLABORATION MENUS (A/P/C):
-
-This step will generate content and present choices:
-
-- **A (Advanced Elicitation)**: Use discovery protocols to explore unconventional starter options or custom approaches
-- **P (Party Mode)**: Bring multiple perspectives to evaluate starter trade-offs for different use cases
-- **C (Continue)**: Save the content to the document and proceed to next step
-
-## PROTOCOL INTEGRATION:
-
-- When 'A' selected: Invoke the `bmad-advanced-elicitation` skill
-- When 'P' selected: Invoke the `bmad-party-mode` skill
-- PROTOCOLS always return to display this step's A/P/C menu after the A or P have completed
-- User accepts/rejects protocol changes before proceeding
-
-## CONTEXT BOUNDARIES:
-
-- Project context from step 2 is available and complete
-- Project context file from step-01 may contain technical preferences
-- No architectural decisions made yet - evaluating foundations
-- Focus on technical preferences discovery and starter evaluation
-- Consider project requirements and existing preferences when evaluating options
-
-## YOUR TASK:
-
-Discover technical preferences and evaluate starter template options, leveraging existing technical preferences and establishing solid architectural foundations.
-
-## STARTER EVALUATION SEQUENCE:
-
-### 0. Check Technical Preferences & Context
-
-**Check Project Context for Existing Technical Preferences:**
-"Before we dive into starter templates, let me check if you have any technical preferences already documented.
-
-{{if_project_context_exists}}
-I found some technical rules in your project context file:
-{{extracted_technical_preferences_from_project_context}}
-
-**Project Context Technical Rules Found:**
-
-- Languages/Frameworks: {{languages_frameworks_from_context}}
-- Tools & Libraries: {{tools_from_context}}
-- Development Patterns: {{patterns_from_context}}
-- Platform Preferences: {{platforms_from_context}}
-
-{{else}}
-No existing technical preferences found in project context file. We'll establish your technical preferences now.
-{{/if_project_context}}"
-
-**Discover User Technical Preferences:**
-"Based on your project context, let's discuss your technical preferences:
-
-{{primary_technology_category}} Preferences:
-
-- **Languages**: Do you have preferences between TypeScript/JavaScript, Python, Go, Rust, etc.?
-- **Frameworks**: Any existing familiarity or preferences (React, Vue, Angular, Next.js, etc.)?
-- **Databases**: Any preferences or existing infrastructure (PostgreSQL, MongoDB, MySQL, etc.)?
-
-**Development Experience:**
-
-- What's your team's experience level with different technologies?
-- Are there any technologies you want to learn vs. what you're comfortable with?
-
-**Platform/Deployment Preferences:**
-
-- Cloud provider preferences (AWS, Vercel, Railway, etc.)?
-- Container preferences (Docker, Serverless, Traditional)?
-
-**Integrations:**
-
-- Any existing systems or APIs you need to integrate with?
-- Third-party services you plan to use (payment, authentication, analytics, etc.)?
-
-These preferences will help me recommend the most suitable starter templates and guide our architectural decisions."
-
-### 1. Identify Primary Technology Domain
-
-Based on project context analysis and technical preferences, identify the primary technology stack:
-
-- **Web application** → Look for Next.js, Vite, Remix, SvelteKit starters
-- **Mobile app** → Look for React Native, Expo, Flutter starters
-- **API/Backend** → Look for NestJS, Express, Fastify, Supabase starters
-- **CLI tool** → Look for CLI framework starters (oclif, commander, etc.)
-- **Full-stack** → Look for T3, RedwoodJS, Blitz, Next.js starters
-- **Desktop** → Look for Electron, Tauri starters
-
-### 2. UX Requirements Consideration
-
-If UX specification was loaded, consider UX requirements when selecting starter:
-
-- **Rich animations** → Framer Motion compatible starter
-- **Complex forms** → React Hook Form included starter
-- **Real-time features** → Socket.io or WebSocket ready starter
-- **Design system** → Storybook-enabled starter
-- **Offline capability** → Service worker or PWA configured starter
-
-### 3. Research Current Starter Options
-
-Search the web to find current, maintained starter templates:
-
-```
-Search the web: "{{primary_technology}} starter template CLI create command latest"
-Search the web: "{{primary_technology}} boilerplate generator latest options"
-Search the web: "{{primary_technology}} production-ready starter best practices"
-```
-
-### 4. Investigate Top Starter Options
-
-For each promising starter found, investigate details:
-
-```
-Search the web: "{{starter_name}} default setup technologies included latest"
-Search the web: "{{starter_name}} project structure file organization"
-Search the web: "{{starter_name}} production deployment capabilities"
-Search the web: "{{starter_name}} recent updates maintenance status"
-```
-
-### 5. Analyze What Each Starter Provides
-
-For each viable starter option, document:
-
-**Technology Decisions Made:**
-
-- Language/TypeScript configuration
-- Styling solution (CSS, Tailwind, Styled Components, etc.)
-- Testing framework setup
-- Linting/Formatting configuration
-- Build tooling and optimization
-- Project structure and organization
-
-**Architectural Patterns Established:**
-
-- Code organization patterns
-- Component structure conventions
-- API layering approach
-- State management setup
-- Routing patterns
-- Environment configuration
-
-**Development Experience Features:**
-
-- Hot reloading and development server
-- TypeScript configuration
-- Debugging setup
-- Testing infrastructure
-- Documentation generation
-
-### 6. Present Starter Options
-
-Based on user skill level and project needs:
-
-**For Expert Users:**
-"Found {{starter_name}} which provides:
-{{quick_decision_list_of_key_decisions}}
-
-This would establish our base architecture with these technical decisions already made. Use it?"
-
-**For Intermediate Users:**
-"I found {{starter_name}}, which is a well-maintained starter for {{project_type}} projects.
-
-It makes these architectural decisions for us:
-{{decision_list_with_explanations}}
-
-This gives us a solid foundation following current best practices. Should we use it?"
-
-**For Beginner Users:**
-"I found {{starter_name}}, which is like a pre-built foundation for your project.
-
-Think of it like buying a prefab house frame instead of cutting each board yourself.
-
-It makes these decisions for us:
-{{friendly_explanation_of_decisions}}
-
-This is a great starting point that follows best practices and saves us from making dozens of small technical choices. Should we use it?"
-
-### 7. Get Current CLI Commands
-
-If user shows interest in a starter, get the exact current commands:
-
-```
-Search the web: "{{starter_name}} CLI command options flags latest"
-Search the web: "{{starter_name}} create new project command examples"
-```
-
-### 8. Generate Starter Template Content
-
-Prepare the content to append to the document:
-
-#### Content Structure:
-
-````markdown
-## Starter Template Evaluation
-
-### Primary Technology Domain
-
-{{identified_domain}} based on project requirements analysis
-
-### Starter Options Considered
-
-{{analysis_of_evaluated_starters}}
-
-### Selected Starter: {{starter_name}}
-
-**Rationale for Selection:**
-{{why_this_starter_was_chosen}}
-
-**Initialization Command:**
-
-```bash
-{{full_starter_command_with_options}}
-```
-
-**Architectural Decisions Provided by Starter:**
-
-**Language & Runtime:**
-{{language_typescript_setup}}
-
-**Styling Solution:**
-{{styling_solution_configuration}}
-
-**Build Tooling:**
-{{build_tools_and_optimization}}
-
-**Testing Framework:**
-{{testing_setup_and_configuration}}
-
-**Code Organization:**
-{{project_structure_and_patterns}}
-
-**Development Experience:**
-{{development_tools_and_workflow}}
-
-**Note:** Project initialization using this command should be the first implementation story.
-
-````
-
-### 9. Present Content and Menu
-
-Show the generated content and present choices:
-
-"I've analyzed starter template options for {{project_type}} projects.
-
-**Here's what I'll add to the document:**
-
-[Show the complete markdown content from step 8]
-
-**What would you like to do?**
-[A] Advanced Elicitation - Explore custom approaches or unconventional starters
-[P] Party Mode - Evaluate trade-offs from different perspectives
-[C] Continue - Save this decision and move to architectural decisions"
-
-### 10. Handle Menu Selection
-
-#### If 'A' (Advanced Elicitation):
-
-- Invoke the `bmad-advanced-elicitation` skill with current starter analysis
-- Process enhanced insights about starter options or custom approaches
-- Ask user: "Accept these changes to the starter template evaluation? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'P' (Party Mode):
-
-- Invoke the `bmad-party-mode` skill with starter evaluation context
-- Process collaborative insights about starter trade-offs
-- Ask user: "Accept these changes to the starter template evaluation? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'C' (Continue):
-
-- Append the final content to `{planning_artifacts}/architecture.md`
-- Update frontmatter: `stepsCompleted: [1, 2, 3]`
-- Load `./step-04-decisions.md`
-
-## APPEND TO DOCUMENT:
-
-When user selects 'C', append the content directly to the document using the structure from step 8.
-
-## SUCCESS METRICS:
-
-✅ Primary technology domain correctly identified from project context
-✅ Current, maintained starter templates researched and evaluated
-✅ All versions verified using web search, not hardcoded
-✅ Architectural implications of starter choice clearly documented
-✅ User provided with clear rationale for starter selection
-✅ A/P/C menu presented and handled correctly
-✅ Content properly appended to document when C selected
-
-## FAILURE MODES:
-
-❌ Not verifying current versions with web search
-❌ Ignoring UX requirements when evaluating starters
-❌ Not documenting what architectural decisions the starter makes
-❌ Failing to consider maintenance status of starter templates
-❌ Not providing clear rationale for starter selection
-❌ Not presenting A/P/C menu after content generation
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects 'C' and content is saved to document, load `./step-04-decisions.md` to begin making specific architectural decisions.
-
-Remember: Do NOT proceed to step-04 until user explicitly selects 'C' from the A/P/C menu and content is saved!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-04-decisions.md

@@ -1,318 +0,0 @@
-# Step 4: Core Architectural Decisions
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on making critical architectural decisions collaboratively
-- 🌐 ALWAYS search the web to verify current technology versions
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 🌐 Search the web to verify technology versions and options
-- ⚠️ Present A/P/C menu after each major decision category
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4]` before loading next step
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## COLLABORATION MENUS (A/P/C):
-
-This step will generate content and present choices for each decision category:
-
-- **A (Advanced Elicitation)**: Use discovery protocols to explore innovative approaches to specific decisions
-- **P (Party Mode)**: Bring multiple perspectives to evaluate decision trade-offs
-- **C (Continue)**: Save the current decisions and proceed to next decision category
-
-## PROTOCOL INTEGRATION:
-
-- When 'A' selected: Invoke the `bmad-advanced-elicitation` skill
-- When 'P' selected: Invoke the `bmad-party-mode` skill
-- PROTOCOLS always return to display this step's A/P/C menu after the A or P have completed
-- User accepts/rejects protocol changes before proceeding
-
-## CONTEXT BOUNDARIES:
-
-- Project context from step 2 is available
-- Starter template choice from step 3 is available
-- Project context file may contain technical preferences and rules
-- Technical preferences discovered in step 3 are available
-- Focus on decisions not already made by starter template or existing preferences
-- Collaborative decision making, not recommendations
-
-## YOUR TASK:
-
-Facilitate collaborative architectural decision making, leveraging existing technical preferences and starter template decisions, focusing on remaining choices critical to the project's success.
-
-## DECISION MAKING SEQUENCE:
-
-### 1. Load Decision Framework & Check Existing Preferences
-
-**Review Technical Preferences from Step 3:**
-"Based on our technical preferences discussion in step 3, let's build on those foundations:
-
-**Your Technical Preferences:**
-{{user_technical_preferences_from_step_3}}
-
-**Starter Template Decisions:**
-{{starter_template_decisions}}
-
-**Project Context Technical Rules:**
-{{project_context_technical_rules}}"
-
-**Identify Remaining Decisions:**
-Based on technical preferences, starter template choice, and project context, identify remaining critical decisions:
-
-**Already Decided (Don't re-decide these):**
-
-- {{starter_template_decisions}}
-- {{user_technology_preferences}}
-- {{project_context_technical_rules}}
-
-**Critical Decisions:** Must be decided before implementation can proceed
-**Important Decisions:** Shape the architecture significantly
-**Nice-to-Have:** Can be deferred if needed
-
-### 2. Decision Categories by Priority
-
-#### Category 1: Data Architecture
-
-- Database choice (if not determined by starter)
-- Data modeling approach
-- Data validation strategy
-- Migration approach
-- Caching strategy
-
-#### Category 2: Authentication & Security
-
-- Authentication method
-- Authorization patterns
-- Security middleware
-- Data encryption approach
-- API security strategy
-
-#### Category 3: API & Communication
-
-- API design patterns (REST, GraphQL, etc.)
-- API documentation approach
-- Error handling standards
-- Rate limiting strategy
-- Communication between services
-
-#### Category 4: Frontend Architecture (if applicable)
-
-- State management approach
-- Component architecture
-- Routing strategy
-- Performance optimization
-- Bundle optimization
-
-#### Category 5: Infrastructure & Deployment
-
-- Hosting strategy
-- CI/CD pipeline approach
-- Environment configuration
-- Monitoring and logging
-- Scaling strategy
-
-### 3. Facilitate Each Decision Category
-
-For each category, facilitate collaborative decision making:
-
-**Present the Decision:**
-Based on user skill level and project context:
-
-**Expert Mode:**
-"{{Decision_Category}}: {{Specific_Decision}}
-
-Options: {{concise_option_list_with_tradeoffs}}
-
-What's your preference for this decision?"
-
-**Intermediate Mode:**
-"Next decision: {{Human_Friendly_Category}}
-
-We need to choose {{Specific_Decision}}.
-
-Common options:
-{{option_list_with_brief_explanations}}
-
-For your project, I'd lean toward {{recommendation}} because {{reason}}. What are your thoughts?"
-
-**Beginner Mode:**
-"Let's talk about {{Human_Friendly_Category}}.
-
-{{Educational_Context_About_Why_This_Matters}}
-
-Think of it like {{real_world_analogy}}.
-
-Your main options:
-{{friendly_options_with_pros_cons}}
-
-My suggestion: {{recommendation}}
-This is good for you because {{beginner_friendly_reason}}.
-
-What feels right to you?"
-
-**Verify Technology Versions:**
-If decision involves specific technology:
-
-```
-Search the web: "{{technology}} latest stable version"
-Search the web: "{{technology}} current LTS version"
-Search the web: "{{technology}} production readiness"
-```
-
-**Get User Input:**
-"What's your preference? (or 'explain more' for details)"
-
-**Handle User Response:**
-
-- If user wants more info: Provide deeper explanation
-- If user has preference: Discuss implications and record decision
-- If user wants alternatives: Explore other options
-
-**Record the Decision:**
-
-- Category: {{category}}
-- Decision: {{user_choice}}
-- Version: {{verified_version_if_applicable}}
-- Rationale: {{user_reasoning_or_default}}
-- Affects: {{components_or_epics}}
-- Provided by Starter: {{yes_if_from_starter}}
-
-### 4. Check for Cascading Implications
-
-After each major decision, identify related decisions:
-
-"This choice means we'll also need to decide:
-
-- {{related_decision_1}}
-- {{related_decision_2}}"
-
-### 5. Generate Decisions Content
-
-After facilitating all decision categories, prepare the content to append:
-
-#### Content Structure:
-
-```markdown
-## Core Architectural Decisions
-
-### Decision Priority Analysis
-
-**Critical Decisions (Block Implementation):**
-{{critical_decisions_made}}
-
-**Important Decisions (Shape Architecture):**
-{{important_decisions_made}}
-
-**Deferred Decisions (Post-MVP):**
-{{decisions_deferred_with_rationale}}
-
-### Data Architecture
-
-{{data_related_decisions_with_versions_and_rationale}}
-
-### Authentication & Security
-
-{{security_related_decisions_with_versions_and_rationale}}
-
-### API & Communication Patterns
-
-{{api_related_decisions_with_versions_and_rationale}}
-
-### Frontend Architecture
-
-{{frontend_related_decisions_with_versions_and_rationale}}
-
-### Infrastructure & Deployment
-
-{{infrastructure_related_decisions_with_versions_and_rationale}}
-
-### Decision Impact Analysis
-
-**Implementation Sequence:**
-{{ordered_list_of_decisions_for_implementation}}
-
-**Cross-Component Dependencies:**
-{{how_decisions_affect_each_other}}
-```
-
-### 6. Present Content and Menu
-
-Show the generated decisions content and present choices:
-
-"I've documented all the core architectural decisions we've made together.
-
-**Here's what I'll add to the document:**
-
-[Show the complete markdown content from step 5]
-
-**What would you like to do?**
-[A] Advanced Elicitation - Explore innovative approaches to any specific decisions
-[P] Party Mode - Review decisions from multiple perspectives
-[C] Continue - Save these decisions and move to implementation patterns"
-
-### 7. Handle Menu Selection
-
-#### If 'A' (Advanced Elicitation):
-
-- Invoke the `bmad-advanced-elicitation` skill with specific decision categories
-- Process enhanced insights about particular decisions
-- Ask user: "Accept these enhancements to the architectural decisions? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'P' (Party Mode):
-
-- Invoke the `bmad-party-mode` skill with architectural decisions context
-- Process collaborative insights about decision trade-offs
-- Ask user: "Accept these changes to the architectural decisions? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'C' (Continue):
-
-- Append the final content to `{planning_artifacts}/architecture.md`
-- Update frontmatter: `stepsCompleted: [1, 2, 3, 4]`
-- Load `./step-05-patterns.md`
-
-## APPEND TO DOCUMENT:
-
-When user selects 'C', append the content directly to the document using the structure from step 5.
-
-## SUCCESS METRICS:
-
-✅ All critical architectural decisions made collaboratively
-✅ Technology versions verified using web search
-✅ Decision rationale clearly documented
-✅ Cascading implications identified and addressed
-✅ User provided appropriate level of explanation for skill level
-✅ A/P/C menu presented and handled correctly for each category
-✅ Content properly appended to document when C selected
-
-## FAILURE MODES:
-
-❌ Making recommendations instead of facilitating decisions
-❌ Not verifying technology versions with web search
-❌ Missing cascading implications between decisions
-❌ Not adapting explanations to user skill level
-❌ Forgetting to document decisions made by starter template
-❌ Not presenting A/P/C menu after content generation
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects 'C' and content is saved to document, load `./step-05-patterns.md` to define implementation patterns that ensure consistency across AI agents.
-
-Remember: Do NOT proceed to step-05 until user explicitly selects 'C' from the A/P/C menu and content is saved!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-05-patterns.md

@@ -1,359 +0,0 @@
-# Step 5: Implementation Patterns & Consistency Rules
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on patterns that prevent AI agent implementation conflicts
-- 🎯 EMPHASIZE what agents could decide DIFFERENTLY if not specified
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 🎯 Focus on consistency, not implementation details
-- ⚠️ Present A/P/C menu after generating patterns content
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4, 5]` before loading next step
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## COLLABORATION MENUS (A/P/C):
-
-This step will generate content and present choices:
-
-- **A (Advanced Elicitation)**: Use discovery protocols to develop comprehensive consistency patterns
-- **P (Party Mode)**: Bring multiple perspectives to identify potential conflict points
-- **C (Continue)**: Save the patterns and proceed to project structure
-
-## PROTOCOL INTEGRATION:
-
-- When 'A' selected: Invoke the `bmad-advanced-elicitation` skill
-- When 'P' selected: Invoke the `bmad-party-mode` skill
-- PROTOCOLS always return to display this step's A/P/C menu after the A or P have completed
-- User accepts/rejects protocol changes before proceeding
-
-## CONTEXT BOUNDARIES:
-
-- Core architectural decisions from step 4 are complete
-- Technology stack is decided and versions are verified
-- Focus on HOW agents should implement, not WHAT they should implement
-- Consider what could vary between different AI agents
-
-## YOUR TASK:
-
-Define implementation patterns and consistency rules that ensure multiple AI agents write compatible, consistent code that works together seamlessly.
-
-## PATTERNS DEFINITION SEQUENCE:
-
-### 1. Identify Potential Conflict Points
-
-Based on the chosen technology stack and decisions, identify where AI agents could make different choices:
-
-**Naming Conflicts:**
-
-- Database table/column naming conventions
-- API endpoint naming patterns
-- File and directory naming
-- Component/function/variable naming
-- Route parameter formats
-
-**Structural Conflicts:**
-
-- Where tests are located
-- How components are organized
-- Where utilities and helpers go
-- Configuration file organization
-- Static asset organization
-
-**Format Conflicts:**
-
-- API response wrapper formats
-- Error response structures
-- Date/time formats in APIs and UI
-- JSON field naming conventions
-- API status code usage
-
-**Communication Conflicts:**
-
-- Event naming conventions
-- Event payload structures
-- State update patterns
-- Action naming conventions
-- Logging formats and levels
-
-**Process Conflicts:**
-
-- Loading state handling
-- Error recovery patterns
-- Retry implementation approaches
-- Authentication flow patterns
-- Validation timing and methods
-
-### 2. Facilitate Pattern Decisions
-
-For each conflict category, facilitate collaborative pattern definition:
-
-**Present the Conflict Point:**
-"Given that we're using {{tech_stack}}, different AI agents might handle {{conflict_area}} differently.
-
-For example, one agent might name database tables 'users' while another uses 'Users' - this would cause conflicts.
-
-We need to establish consistent patterns that all agents follow."
-
-**Show Options and Trade-offs:**
-"Common approaches for {{pattern_category}}:
-
-1. {{option_1}} - {{pros_and_cons}}
-2. {{option_2}} - {{pros_and_cons}}
-3. {{option_3}} - {{pros_and_cons}}
-
-Which approach makes the most sense for our project?"
-
-**Get User Decision:**
-"What's your preference for this pattern? (or discuss the trade-offs more)"
-
-### 3. Define Pattern Categories
-
-#### Naming Patterns
-
-**Database Naming:**
-
-- Table naming: users, Users, or user?
-- Column naming: user_id or userId?
-- Foreign key format: user_id or fk_user?
-- Index naming: idx_users_email or users_email_index?
-
-**API Naming:**
-
-- REST endpoint naming: /users or /user? Plural or singular?
-- Route parameter format: :id or {id}?
-- Query parameter naming: user_id or userId?
-- Header naming conventions: X-Custom-Header or Custom-Header?
-
-**Code Naming:**
-
-- Component naming: UserCard or user-card?
-- File naming: UserCard.tsx or user-card.tsx?
-- Function naming: getUserData or get_user_data?
-- Variable naming: userId or user_id?
-
-#### Structure Patterns
-
-**Project Organization:**
-
-- Where do tests live? **tests**/ or \*.test.ts co-located?
-- How are components organized? By feature or by type?
-- Where do shared utilities go?
-- How are services and repositories organized?
-
-**File Structure:**
-
-- Config file locations and naming
-- Static asset organization
-- Documentation placement
-- Environment file organization
-
-#### Format Patterns
-
-**API Formats:**
-
-- API response wrapper? {data: ..., error: ...} or direct response?
-- Error format? {message, code} or {error: {type, detail}}?
-- Date format in JSON? ISO strings or timestamps?
-- Success response structure?
-
-**Data Formats:**
-
-- JSON field naming: snake_case or camelCase?
-- Boolean representations: true/false or 1/0?
-- Null handling patterns
-- Array vs object for single items
-
-#### Communication Patterns
-
-**Event Systems:**
-
-- Event naming convention: user.created or UserCreated?
-- Event payload structure standards
-- Event versioning approach
-- Async event handling patterns
-
-**State Management:**
-
-- State update patterns: immutable updates or direct mutation?
-- Action naming conventions
-- Selector patterns
-- State organization principles
-
-#### Process Patterns
-
-**Error Handling:**
-
-- Global error handling approach
-- Error boundary patterns
-- User-facing error message format
-- Logging vs user error distinction
-
-**Loading States:**
-
-- Loading state naming conventions
-- Global vs local loading states
-- Loading state persistence
-- Loading UI patterns
-
-### 4. Generate Patterns Content
-
-Prepare the content to append to the document:
-
-#### Content Structure:
-
-```markdown
-## Implementation Patterns & Consistency Rules
-
-### Pattern Categories Defined
-
-**Critical Conflict Points Identified:**
-{{number_of_potential_conflicts}} areas where AI agents could make different choices
-
-### Naming Patterns
-
-**Database Naming Conventions:**
-{{database_naming_rules_with_examples}}
-
-**API Naming Conventions:**
-{{api_naming_rules_with_examples}}
-
-**Code Naming Conventions:**
-{{code_naming_rules_with_examples}}
-
-### Structure Patterns
-
-**Project Organization:**
-{{project_structure_rules_with_examples}}
-
-**File Structure Patterns:**
-{{file_organization_rules_with_examples}}
-
-### Format Patterns
-
-**API Response Formats:**
-{{api_response_structure_rules}}
-
-**Data Exchange Formats:**
-{{data_format_rules_with_examples}}
-
-### Communication Patterns
-
-**Event System Patterns:**
-{{event_naming_and_structure_rules}}
-
-**State Management Patterns:**
-{{state_update_and_organization_rules}}
-
-### Process Patterns
-
-**Error Handling Patterns:**
-{{consistent_error_handling_approaches}}
-
-**Loading State Patterns:**
-{{loading_state_management_rules}}
-
-### Enforcement Guidelines
-
-**All AI Agents MUST:**
-
-- {{mandatory_pattern_1}}
-- {{mandatory_pattern_2}}
-- {{mandatory_pattern_3}}
-
-**Pattern Enforcement:**
-
-- How to verify patterns are followed
-- Where to document pattern violations
-- Process for updating patterns
-
-### Pattern Examples
-
-**Good Examples:**
-{{concrete_examples_of_correct_pattern_usage}}
-
-**Anti-Patterns:**
-{{examples_of_what_to_avoid}}
-```
-
-### 5. Present Content and Menu
-
-Show the generated patterns content and present choices:
-
-"I've documented implementation patterns that will prevent conflicts between AI agents working on this project.
-
-**Here's what I'll add to the document:**
-
-[Show the complete markdown content from step 4]
-
-**What would you like to do?**
-[A] Advanced Elicitation - Explore additional consistency patterns
-[P] Party Mode - Review patterns from different implementation perspectives
-[C] Continue - Save these patterns and move to project structure"
-
-### 6. Handle Menu Selection
-
-#### If 'A' (Advanced Elicitation):
-
-- Invoke the `bmad-advanced-elicitation` skill with current patterns
-- Process enhanced consistency rules that come back
-- Ask user: "Accept these additional pattern refinements? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'P' (Party Mode):
-
-- Invoke the `bmad-party-mode` skill with implementation patterns context
-- Process collaborative insights about potential conflicts
-- Ask user: "Accept these changes to the implementation patterns? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'C' (Continue):
-
-- Append the final content to `{planning_artifacts}/architecture.md`
-- Update frontmatter: `stepsCompleted: [1, 2, 3, 4, 5]`
-- Load `./step-06-structure.md`
-
-## APPEND TO DOCUMENT:
-
-When user selects 'C', append the content directly to the document using the structure from step 4.
-
-## SUCCESS METRICS:
-
-✅ All potential AI agent conflict points identified and addressed
-✅ Comprehensive patterns defined for naming, structure, and communication
-✅ Concrete examples provided for each pattern
-✅ Enforcement guidelines clearly documented
-✅ User collaborated on pattern decisions rather than receiving recommendations
-✅ A/P/C menu presented and handled correctly
-✅ Content properly appended to document when C selected
-
-## FAILURE MODES:
-
-❌ Missing potential conflict points that could cause agent conflicts
-❌ Being too prescriptive about implementation details instead of focusing on consistency
-❌ Not providing concrete examples for each pattern
-❌ Failing to address cross-cutting concerns like error handling
-❌ Not considering the chosen technology stack when defining patterns
-❌ Not presenting A/P/C menu after content generation
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects 'C' and content is saved to document, load `./step-06-structure.md` to define the complete project structure.
-
-Remember: Do NOT proceed to step-06 until user explicitly selects 'C' from the A/P/C menu and content is saved!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-06-structure.md

@@ -1,379 +0,0 @@
-# Step 6: Project Structure & Boundaries
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on defining complete project structure and clear boundaries
-- 🗺️ MAP requirements/epics to architectural components
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 🗺️ Create complete project tree, not generic placeholders
-- ⚠️ Present A/P/C menu after generating project structure
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4, 5, 6]` before loading next step
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## COLLABORATION MENUS (A/P/C):
-
-This step will generate content and present choices:
-
-- **A (Advanced Elicitation)**: Use discovery protocols to explore innovative project organization approaches
-- **P (Party Mode)**: Bring multiple perspectives to evaluate project structure trade-offs
-- **C (Continue)**: Save the project structure and proceed to validation
-
-## PROTOCOL INTEGRATION:
-
-- When 'A' selected: Invoke the `bmad-advanced-elicitation` skill
-- When 'P' selected: Invoke the `bmad-party-mode` skill
-- PROTOCOLS always return to display this step's A/P/C menu after the A or P have completed
-- User accepts/rejects protocol changes before proceeding
-
-## CONTEXT BOUNDARIES:
-
-- All previous architectural decisions are complete
-- Implementation patterns and consistency rules are defined
-- Focus on physical project structure and component boundaries
-- Map requirements to specific files and directories
-
-## YOUR TASK:
-
-Define the complete project structure and architectural boundaries based on all decisions made, creating a concrete implementation guide for AI agents.
-
-## PROJECT STRUCTURE SEQUENCE:
-
-### 1. Analyze Requirements Mapping
-
-Map project requirements to architectural components:
-
-**From Epics (if available):**
-"Epic: {{epic_name}} → Lives in {{module/directory/service}}"
-
-- User stories within the epic
-- Cross-epic dependencies
-- Shared components needed
-
-**From FR Categories (if no epics):**
-"FR Category: {{fr_category_name}} → Lives in {{module/directory/service}}"
-
-- Related functional requirements
-- Shared functionality across categories
-- Integration points between categories
-
-### 2. Define Project Directory Structure
-
-Based on technology stack and patterns, create the complete project structure:
-
-**Root Configuration Files:**
-
-- Package management files (package.json, requirements.txt, etc.)
-- Build and development configuration
-- Environment configuration files
-- CI/CD pipeline files
-- Documentation files
-
-**Source Code Organization:**
-
-- Application entry points
-- Core application structure
-- Feature/module organization
-- Shared utilities and libraries
-- Configuration and environment files
-
-**Test Organization:**
-
-- Unit test locations and structure
-- Integration test organization
-- End-to-end test structure
-- Test utilities and fixtures
-
-**Build and Distribution:**
-
-- Build output directories
-- Distribution files
-- Static assets
-- Documentation build
-
-### 3. Define Integration Boundaries
-
-Map how components communicate and where boundaries exist:
-
-**API Boundaries:**
-
-- External API endpoints
-- Internal service boundaries
-- Authentication and authorization boundaries
-- Data access layer boundaries
-
-**Component Boundaries:**
-
-- Frontend component communication patterns
-- State management boundaries
-- Service communication patterns
-- Event-driven integration points
-
-**Data Boundaries:**
-
-- Database schema boundaries
-- Data access patterns
-- Caching boundaries
-- External data integration points
-
-### 4. Create Complete Project Tree
-
-Generate a comprehensive directory structure showing all files and directories:
-
-**Technology-Specific Structure Examples:**
-
-**Next.js Full-Stack:**
-
-```
-project-name/
-├── README.md
-├── package.json
-├── next.config.js
-├── tailwind.config.js
-├── tsconfig.json
-├── .env.local
-├── .env.example
-├── .gitignore
-├── .github/
-│   └── workflows/
-│       └── ci.yml
-├── src/
-│   ├── app/
-│   │   ├── globals.css
-│   │   ├── layout.tsx
-│   │   └── page.tsx
-│   ├── components/
-│   │   ├── ui/
-│   │   ├── forms/
-│   │   └── features/
-│   ├── lib/
-│   │   ├── db.ts
-│   │   ├── auth.ts
-│   │   └── utils.ts
-│   ├── types/
-│   └── middleware.ts
-├── prisma/
-│   ├── schema.prisma
-│   └── migrations/
-├── tests/
-│   ├── __mocks__/
-│   ├── components/
-│   └── e2e/
-└── public/
-    └── assets/
-```
-
-**API Backend (NestJS):**
-
-```
-project-name/
-├── package.json
-├── nest-cli.json
-├── tsconfig.json
-├── .env
-├── .env.example
-├── .gitignore
-├── README.md
-├── src/
-│   ├── main.ts
-│   ├── app.module.ts
-│   ├── config/
-│   ├── modules/
-│   │   ├── auth/
-│   │   ├── users/
-│   │   └── common/
-│   ├── services/
-│   ├── repositories/
-│   ├── decorators/
-│   ├── pipes/
-│   ├── guards/
-│   └── interceptors/
-├── test/
-│   ├── unit/
-│   ├── integration/
-│   └── e2e/
-├── prisma/
-│   ├── schema.prisma
-│   └── migrations/
-└── docker-compose.yml
-```
-
-### 5. Map Requirements to Structure
-
-Create explicit mapping from project requirements to specific files/directories:
-
-**Epic/Feature Mapping:**
-"Epic: User Management
-
-- Components: src/components/features/users/
-- Services: src/services/users/
-- API Routes: src/app/api/users/
-- Database: prisma/migrations/_*users*_
-- Tests: tests/features/users/"
-
-**Cross-Cutting Concerns:**
-"Authentication System
-
-- Components: src/components/auth/
-- Services: src/services/auth/
-- Middleware: src/middleware/auth.ts
-- Guards: src/guards/auth.guard.ts
-- Tests: tests/auth/"
-
-### 6. Generate Structure Content
-
-Prepare the content to append to the document:
-
-#### Content Structure:
-
-```markdown
-## Project Structure & Boundaries
-
-### Complete Project Directory Structure
-```
-
-{{complete_project_tree_with_all_files_and_directories}}
-
-```
-
-### Architectural Boundaries
-
-**API Boundaries:**
-{{api_boundary_definitions_and_endpoints}}
-
-**Component Boundaries:**
-{{component_communication_patterns_and_boundaries}}
-
-**Service Boundaries:**
-{{service_integration_patterns_and_boundaries}}
-
-**Data Boundaries:**
-{{data_access_patterns_and_boundaries}}
-
-### Requirements to Structure Mapping
-
-**Feature/Epic Mapping:**
-{{mapping_of_epics_or_features_to_specific_directories}}
-
-**Cross-Cutting Concerns:**
-{{mapping_of_shared_functionality_to_locations}}
-
-### Integration Points
-
-**Internal Communication:**
-{{how_components_within_the_project_communicate}}
-
-**External Integrations:**
-{{third_party_service_integration_points}}
-
-**Data Flow:**
-{{how_data_flows_through_the_architecture}}
-
-### File Organization Patterns
-
-**Configuration Files:**
-{{where_and_how_config_files_are_organized}}
-
-**Source Organization:**
-{{how_source_code_is_structured_and_organized}}
-
-**Test Organization:**
-{{how_tests_are_structured_and_organized}}
-
-**Asset Organization:**
-{{how_static_and_dynamic_assets_are_organized}}
-
-### Development Workflow Integration
-
-**Development Server Structure:**
-{{how_the_project_is organized_for_development}}
-
-**Build Process Structure:**
-{{how_the_build_process_uses_the_project_structure}}
-
-**Deployment Structure:**
-{{how_the_project_structure_supports_deployment}}
-```
-
-### 7. Present Content and Menu
-
-Show the generated project structure content and present choices:
-
-"I've created a complete project structure based on all our architectural decisions.
-
-**Here's what I'll add to the document:**
-
-[Show the complete markdown content from step 6]
-
-**What would you like to do?**
-[A] Advanced Elicitation - Explore innovative project organization approaches
-[P] Party Mode - Review structure from different development perspectives
-[C] Continue - Save this structure and move to architecture validation"
-
-### 8. Handle Menu Selection
-
-#### If 'A' (Advanced Elicitation):
-
-- Invoke the `bmad-advanced-elicitation` skill with current project structure
-- Process enhanced organizational insights that come back
-- Ask user: "Accept these changes to the project structure? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'P' (Party Mode):
-
-- Invoke the `bmad-party-mode` skill with project structure context
-- Process collaborative insights about organization trade-offs
-- Ask user: "Accept these changes to the project structure? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'C' (Continue):
-
-- Append the final content to `{planning_artifacts}/architecture.md`
-- Update frontmatter: `stepsCompleted: [1, 2, 3, 4, 5, 6]`
-- Load `./step-07-validation.md`
-
-## APPEND TO DOCUMENT:
-
-When user selects 'C', append the content directly to the document using the structure from step 6.
-
-## SUCCESS METRICS:
-
-✅ Complete project tree defined with all files and directories
-✅ All architectural boundaries clearly documented
-✅ Requirements/epics mapped to specific locations
-✅ Integration points and communication patterns defined
-✅ Project structure aligned with chosen technology stack
-✅ A/P/C menu presented and handled correctly
-✅ Content properly appended to document when C selected
-
-## FAILURE MODES:
-
-❌ Creating generic placeholder structure instead of specific, complete tree
-❌ Not mapping requirements to specific files and directories
-❌ Missing important integration boundaries
-❌ Not considering the chosen technology stack in structure design
-❌ Not defining how components communicate across boundaries
-❌ Not presenting A/P/C menu after content generation
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects 'C' and content is saved to document, load `./step-07-validation.md` to validate architectural coherence and completeness.
-
-Remember: Do NOT proceed to step-07 until user explicitly selects 'C' from the A/P/C menu and content is saved!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-07-validation.md

@@ -1,361 +0,0 @@
-# Step 7: Architecture Validation & Completion
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on validating architectural coherence and completeness
-- ✅ VALIDATE all requirements are covered by architectural decisions
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- ✅ Run comprehensive validation checks on the complete architecture
-- ⚠️ Present A/P/C menu after generating validation results
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1, 2, 3, 4, 5, 6, 7]` before loading next step
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## COLLABORATION MENUS (A/P/C):
-
-This step will generate content and present choices:
-
-- **A (Advanced Elicitation)**: Use discovery protocols to address complex architectural issues found during validation
-- **P (Party Mode)**: Bring multiple perspectives to resolve validation concerns
-- **C (Continue)**: Save the validation results and complete the architecture
-
-## PROTOCOL INTEGRATION:
-
-- When 'A' selected: Invoke the `bmad-advanced-elicitation` skill
-- When 'P' selected: Invoke the `bmad-party-mode` skill
-- PROTOCOLS always return to display this step's A/P/C menu after the A or P have completed
-- User accepts/rejects protocol changes before proceeding
-
-## CONTEXT BOUNDARIES:
-
-- Complete architecture document with all sections is available
-- All architectural decisions, patterns, and structure are defined
-- Focus on validation, gap analysis, and coherence checking
-- Prepare for handoff to implementation phase
-
-## YOUR TASK:
-
-Validate the complete architecture for coherence, completeness, and readiness to guide AI agents through consistent implementation.
-
-## VALIDATION SEQUENCE:
-
-### 1. Coherence Validation
-
-Check that all architectural decisions work together:
-
-**Decision Compatibility:**
-
-- Do all technology choices work together without conflicts?
-- Are all versions compatible with each other?
-- Do patterns align with technology choices?
-- Are there any contradictory decisions?
-
-**Pattern Consistency:**
-
-- Do implementation patterns support the architectural decisions?
-- Are naming conventions consistent across all areas?
-- Do structure patterns align with technology stack?
-- Are communication patterns coherent?
-
-**Structure Alignment:**
-
-- Does the project structure support all architectural decisions?
-- Are boundaries properly defined and respected?
-- Does the structure enable the chosen patterns?
-- Are integration points properly structured?
-
-### 2. Requirements Coverage Validation
-
-Verify all project requirements are architecturally supported:
-
-**From Epics (if available):**
-
-- Does every epic have architectural support?
-- Are all user stories implementable with these decisions?
-- Are cross-epic dependencies handled architecturally?
-- Are there any gaps in epic coverage?
-
-**From FR Categories (if no epics):**
-
-- Does every functional requirement have architectural support?
-- Are all FR categories fully covered by architectural decisions?
-- Are cross-cutting FRs properly addressed?
-- Are there any missing architectural capabilities?
-
-**Non-Functional Requirements:**
-
-- Are performance requirements addressed architecturally?
-- Are security requirements fully covered?
-- Are scalability considerations properly handled?
-- Are compliance requirements architecturally supported?
-
-### 3. Implementation Readiness Validation
-
-Assess if AI agents can implement consistently:
-
-**Decision Completeness:**
-
-- Are all critical decisions documented with versions?
-- Are implementation patterns comprehensive enough?
-- Are consistency rules clear and enforceable?
-- Are examples provided for all major patterns?
-
-**Structure Completeness:**
-
-- Is the project structure complete and specific?
-- Are all files and directories defined?
-- Are integration points clearly specified?
-- Are component boundaries well-defined?
-
-**Pattern Completeness:**
-
-- Are all potential conflict points addressed?
-- Are naming conventions comprehensive?
-- Are communication patterns fully specified?
-- Are process patterns (error handling, etc.) complete?
-
-### 4. Gap Analysis
-
-Identify and document any missing elements:
-
-**Critical Gaps:**
-
-- Missing architectural decisions that block implementation
-- Incomplete patterns that could cause conflicts
-- Missing structural elements needed for development
-- Undefined integration points
-
-**Important Gaps:**
-
-- Areas that need more detailed specification
-- Patterns that could be more comprehensive
-- Documentation that would help implementation
-- Examples that would clarify complex decisions
-
-**Nice-to-Have Gaps:**
-
-- Additional patterns that would be helpful
-- Supplementary documentation
-- Tooling recommendations
-- Development workflow optimizations
-
-### 5. Address Validation Issues
-
-For any issues found, facilitate resolution:
-
-**Critical Issues:**
-"I found some issues that need to be addressed before implementation:
-
-{{critical_issue_description}}
-
-These could cause implementation problems. How would you like to resolve this?"
-
-**Important Issues:**
-"I noticed a few areas that could be improved:
-
-{{important_issue_description}}
-
-These aren't blocking, but addressing them would make implementation smoother. Should we work on these?"
-
-**Minor Issues:**
-"Here are some minor suggestions for improvement:
-
-{{minor_issue_description}}
-
-These are optional refinements. Would you like to address any of these?"
-
-### 6. Generate Validation Content
-
-Prepare the content to append to the document:
-
-#### Content Structure:
-
-```markdown
-## Architecture Validation Results
-
-### Coherence Validation ✅
-
-**Decision Compatibility:**
-{{assessment_of_how_all_decisions_work_together}}
-
-**Pattern Consistency:**
-{{verification_that_patterns_support_decisions}}
-
-**Structure Alignment:**
-{{confirmation_that_structure_supports_architecture}}
-
-### Requirements Coverage Validation ✅
-
-**Epic/Feature Coverage:**
-{{verification_that_all_epics_or_features_are_supported}}
-
-**Functional Requirements Coverage:**
-{{confirmation_that_all_FRs_are_architecturally_supported}}
-
-**Non-Functional Requirements Coverage:**
-{{verification_that_NFRs_are_addressed}}
-
-### Implementation Readiness Validation ✅
-
-**Decision Completeness:**
-{{assessment_of_decision_documentation_completeness}}
-
-**Structure Completeness:**
-{{evaluation_of_project_structure_completeness}}
-
-**Pattern Completeness:**
-{{verification_of_implementation_patterns_completeness}}
-
-### Gap Analysis Results
-
-{{gap_analysis_findings_with_priority_levels}}
-
-### Validation Issues Addressed
-
-{{description_of_any_issues_found_and_resolutions}}
-
-### Architecture Completeness Checklist
-
-Mark each item `[x]` only if validation confirms it; leave `[ ]` if it is missing, partial, or unverified. Any unchecked item must be reflected in the Gap Analysis above and in the Overall Status below.
-
-**Requirements Analysis**
-
-- [ ] Project context thoroughly analyzed
-- [ ] Scale and complexity assessed
-- [ ] Technical constraints identified
-- [ ] Cross-cutting concerns mapped
-
-**Architectural Decisions**
-
-- [ ] Critical decisions documented with versions
-- [ ] Technology stack fully specified
-- [ ] Integration patterns defined
-- [ ] Performance considerations addressed
-
-**Implementation Patterns**
-
-- [ ] Naming conventions established
-- [ ] Structure patterns defined
-- [ ] Communication patterns specified
-- [ ] Process patterns documented
-
-**Project Structure**
-
-- [ ] Complete directory structure defined
-- [ ] Component boundaries established
-- [ ] Integration points mapped
-- [ ] Requirements to structure mapping complete
-
-### Architecture Readiness Assessment
-
-**Overall Status:** {{READY FOR IMPLEMENTATION | READY WITH MINOR GAPS | NOT READY}} (choose READY FOR IMPLEMENTATION only when all 16 checklist items are `[x]` and no Critical Gaps remain; choose NOT READY when any Critical Gap is open or any Requirements Analysis or Architectural Decisions item is unchecked; otherwise READY WITH MINOR GAPS)
-
-**Confidence Level:** {{high/medium/low}} based on validation results
-
-**Key Strengths:**
-{{list_of_architecture_strengths}}
-
-**Areas for Future Enhancement:**
-{{areas_that_could_be_improved_later}}
-
-### Implementation Handoff
-
-**AI Agent Guidelines:**
-
-- Follow all architectural decisions exactly as documented
-- Use implementation patterns consistently across all components
-- Respect project structure and boundaries
-- Refer to this document for all architectural questions
-
-**First Implementation Priority:**
-{{starter_template_command_or_first_architectural_step}}
-```
-
-### 7. Present Content and Menu
-
-Show the validation results and present choices:
-
-"I've completed a comprehensive validation of your architecture.
-
-**Validation Summary:**
-
-- ✅ Coherence: All decisions work together
-- ✅ Coverage: All requirements are supported
-- ✅ Readiness: AI agents can implement consistently
-
-**Here's what I'll add to complete the architecture document:**
-
-[Show the complete markdown content from step 6]
-
-**What would you like to do?**
-[A] Advanced Elicitation - Address any complex architectural concerns
-[P] Party Mode - Review validation from different implementation perspectives
-[C] Continue - Complete the architecture and finish workflow
-
-### 8. Handle Menu Selection
-
-#### If 'A' (Advanced Elicitation):
-
-- Invoke the `bmad-advanced-elicitation` skill with validation issues
-- Process enhanced solutions for complex concerns
-- Ask user: "Accept these architectural improvements? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'P' (Party Mode):
-
-- Invoke the `bmad-party-mode` skill with validation context
-- Process collaborative insights on implementation readiness
-- Ask user: "Accept these changes to the validation results? (y/n)"
-- If yes: Update content, then return to A/P/C menu
-- If no: Keep original content, then return to A/P/C menu
-
-#### If 'C' (Continue):
-
-- Append the final content to `{planning_artifacts}/architecture.md`
-- Update frontmatter: `stepsCompleted: [1, 2, 3, 4, 5, 6, 7]`
-- Load `./step-08-complete.md`
-
-## APPEND TO DOCUMENT:
-
-When user selects 'C', append the content directly to the document using the structure from step 6.
-
-## SUCCESS METRICS:
-
-✅ All architectural decisions validated for coherence
-✅ Complete requirements coverage verified
-✅ Implementation readiness confirmed
-✅ All gaps identified and addressed
-✅ Comprehensive validation checklist completed
-✅ A/P/C menu presented and handled correctly
-✅ Content properly appended to document when C selected
-
-## FAILURE MODES:
-
-❌ Skipping validation of decision compatibility
-❌ Not verifying all requirements are architecturally supported
-❌ Missing potential implementation conflicts
-❌ Not addressing gaps found during validation
-❌ Providing incomplete validation checklist
-❌ Not presenting A/P/C menu after content generation
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## NEXT STEP:
-
-After user selects 'C' and content is saved to document, load `./step-08-complete.md` to complete the workflow and provide implementation guidance.
-
-Remember: Do NOT proceed to step-08 until user explicitly selects 'C' from the A/P/C menu and content is saved!

src/bmm-skills/3-solutioning/bmad-create-architecture/steps/step-08-complete.md

@@ -1,82 +0,0 @@
-# Step 8: Architecture Completion & Handoff
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- ✅ ALWAYS treat this as collaborative completion between architectural peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- 💬 FOCUS on successful workflow completion and implementation handoff
-- 🎯 PROVIDE clear next steps for implementation phase
-- ⚠️ ABSOLUTELY NO TIME ESTIMATES - AI development speed has fundamentally changed
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 🎯 Present completion summary and implementation guidance
-- 📖 Update frontmatter with final workflow state
-- 🚫 THIS IS THE FINAL STEP IN THIS WORKFLOW
-
-## YOUR TASK:
-
-Complete the architecture workflow, provide a comprehensive completion summary, and guide the user to the next phase of their project development.
-
-## COMPLETION SEQUENCE:
-
-### 1. Congratulate the User on Completion
-
-Both you and the User completed something amazing here - give a summary of what you achieved together and really congratulate the user on a job well done.
-
-### 2. Update the created document's frontmatter
-
-```yaml
-stepsCompleted: [1, 2, 3, 4, 5, 6, 7, 8]
-workflowType: 'architecture'
-lastStep: 8
-status: 'complete'
-completedAt: '{{current_date}}'
-```
-
-### 3. Next Steps Guidance
-
-Architecture complete. Invoke the `bmad-help` skill.
-
-Upon Completion of task output: offer to answer any questions about the Architecture Document.
-
-
-## SUCCESS METRICS:
-
-✅ Complete architecture document delivered with all sections
-✅ All architectural decisions documented and validated
-✅ Implementation patterns and consistency rules finalized
-✅ Project structure complete with all files and directories
-✅ User provided with clear next steps and implementation guidance
-✅ Workflow status properly updated
-✅ User collaboration maintained throughout completion process
-
-## FAILURE MODES:
-
-❌ Not providing clear implementation guidance
-❌ Missing final validation of document completeness
-❌ Not updating workflow status appropriately
-❌ Failing to celebrate the successful completion
-❌ Not providing specific next steps for the user
-❌ Rushing completion without proper summary
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
-
-## WORKFLOW COMPLETE:
-
-This is the final step of the Architecture workflow. The user now has a complete, validated architecture document ready for AI agent implementation.
-
-The architecture will serve as the single source of truth for all technical decisions, ensuring consistent implementation across the entire project development lifecycle.
-
-## On Complete
-
-Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete`
-
-If the resolved `workflow.on_complete` is non-empty, follow it as the final terminal instruction before exiting.

src/bmm-skills/4-implementation/bmad-code-review/steps/step-02-review.md

@@ -18,7 +18,7 @@ failed_layers: '' # set at runtime: comma-separated list of layers that failed o
 
 2. Launch parallel subagents without conversation context. If subagents are not available, generate prompt files in `{implementation_artifacts}` — one per reviewer role below — and HALT. Ask the user to run each in a separate session (ideally a different LLM) and paste back the findings. When findings are pasted, resume from this point and proceed to step 3.
 
-   - **Blind Hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill.
+   - **Blind Hunter** — receives inline `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill.
 
    - **Edge Case Hunter** — receives `{diff_output}` and read access to the project. Invoke via the `bmad-review-edge-case-hunter` skill.
 

src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md

@@ -25,7 +25,7 @@ Do NOT `git add` anything — this is read-only inspection.
 
 Launch three subagents without conversation context. If no sub-agents are available, generate three review prompt files in `{implementation_artifacts}` — one per reviewer role below — and HALT. Ask the human to run each in a separate session (ideally a different LLM) and paste back the findings.
 
-- **Blind hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill.
+- **Blind hunter** — receives inline `{diff_output}` only. No spec, no context docs, no project access. Invoke via the `bmad-review-adversarial-general` skill.
 - **Edge case hunter** — receives `{diff_output}` and read access to the project. Invoke via the `bmad-review-edge-case-hunter` skill.
 - **Acceptance auditor** — receives `{diff_output}`, `{spec_file}`, and read access to the project. Must also read the docs listed in `{spec_file}` frontmatter `context`. Checks for violations of acceptance criteria, rules, and principles from the spec and context docs.
 

src/bmm-skills/4-implementation/bmad-retrospective/SKILL.md

@@ -350,6 +350,7 @@ Amelia (Developer): "I found our retrospectives from Epic {{prev_epic_num}}. Let
 
     **Action Item Follow-Through:**
     - For each action item from Epic {{prev_epic_num}} retro, check if it was completed
+    - Cross-check the action_items section in {sprint_status_file} (if present) for Epic {{prev_epic_num}} entries and their current status
     - Look for evidence in current epic's story records
     - Mark each action item: ✅ Completed, ⏳ In Progress, ❌ Not Addressed
 
@@ -1403,6 +1404,19 @@ Amelia (Developer): "See you all when prep work is done. Meeting adjourned!"
 <action>Find development_status key "epic-{{epic_number}}-retrospective"</action>
 <action>Verify current status (typically "optional" or "pending")</action>
 <action>Update development_status["epic-{{epic_number}}-retrospective"] = "done"</action>
+<action>Append each Epic {{epic_number}} action item to the action_items section, creating the section after development_status if missing. One entry per item:</action>
+
+```yaml
+action_items:
+  - epic: {{epic_number}}
+    action: "{{action_description}}"
+    owner: "{{owner}}"
+    status: open
+```
+
+<action>Quote action and owner values so punctuation (e.g., "#") cannot break YAML parsing</action>
+
+<action>Update Epic {{prev_epic_num}} action_items entries based on Step 4 follow-through: ✅ Completed → done, ⏳ In Progress → in-progress, ❌ Not Addressed → keep existing status (do not modify)</action>
 <action>Update last_updated field to current date</action>
 <action>Save file, preserving ALL comments and structure including STATUS DEFINITIONS</action>
 
@@ -1412,6 +1426,7 @@ Amelia (Developer): "See you all when prep work is done. Meeting adjourned!"
 
 Retrospective key: epic-{{epic_number}}-retrospective
 Status: {{previous_status}} → done
+Action items recorded: {{action_count}}
 </output>
 </check>
 

src/bmm-skills/4-implementation/bmad-sprint-planning/SKILL.md

@@ -151,6 +151,7 @@ development_status:
 
 - If existing `{status_file}` exists and has more advanced status, preserve it
 - Never downgrade status (e.g., don't change `done` to `ready-for-dev`)
+- If existing `{status_file}` has an `action_items` section, carry it over unchanged
 
 **Status Flow Reference:**
 
@@ -194,12 +195,18 @@ development_status:
 #   - optional: Can be completed but not required
 #   - done: Retrospective has been completed
 #
+# Action Item Status:
+#   - open: Committed during a retrospective, not yet addressed
+#   - in-progress: Actively being worked on
+#   - done: Completed
+#
 # WORKFLOW NOTES:
 # ===============
 # - Epic transitions to 'in-progress' automatically when first story is created
 # - Stories can be worked in parallel if team capacity allows
 # - Developer typically creates next story after previous one is 'done' to incorporate learnings
 # - Dev moves story to 'review', then runs code-review (fresh context, different LLM recommended)
+# - Retrospective appends its action items to action_items; sprint-status surfaces open ones
 
 generated: { date }
 last_updated: { date }
@@ -215,6 +222,7 @@ development_status:
 <action>Write the complete sprint status YAML to {status_file}</action>
 <action>CRITICAL: Metadata appears TWICE - once as comments (#) for documentation, once as YAML key:value fields for parsing</action>
 <action>Ensure all items are ordered: epic, its stories, its retrospective, next epic...</action>
+<action>If the existing file had an action_items section, write it back unchanged after development_status</action>
 </step>
 
 <step n="5" goal="Validate and report">
@@ -223,7 +231,8 @@ development_status:
 - [ ] Every epic in epic files appears in {status_file}
 - [ ] Every story in epic files appears in {status_file}
 - [ ] Every epic has a corresponding retrospective entry
-- [ ] No items in {status_file} that don't exist in epic files
+- [ ] No development_status items in {status_file} that don't exist in epic files
+- [ ] action_items section (if it existed) carried over unchanged
 - [ ] All status values are legal (match state machine definitions)
 - [ ] File is valid YAML syntax
 
@@ -291,6 +300,16 @@ optional ↔ done
 - **optional**: Ready to be conducted but not required
 - **done**: Finished
 
+**Action Item Status:**
+
+```
+open → in-progress → done
+```
+
+- **open**: Committed during a retrospective, not yet addressed
+- **in-progress**: Actively being worked on
+- **done**: Completed
+
 ### Guidelines
 
 1. **Epic Activation**: Mark epic as `in-progress` when starting work on its first story

src/bmm-skills/4-implementation/bmad-sprint-planning/checklist.md

@@ -7,7 +7,8 @@
 - [ ] Every epic found in epic\*.md files appears in sprint-status.yaml
 - [ ] Every story found in epic\*.md files appears in sprint-status.yaml
 - [ ] Every epic has a corresponding retrospective entry
-- [ ] No items in sprint-status.yaml that don't exist in epic files
+- [ ] No development_status items in sprint-status.yaml that don't exist in epic files
+- [ ] action_items section (if it existed) carried over unchanged
 
 ### Parsing Verification
 

src/bmm-skills/4-implementation/bmad-sprint-planning/sprint-status-template.yaml

@@ -26,11 +26,17 @@
 #   - optional: Can be completed but not required
 #   - done: Retrospective has been completed
 #
+# Action Item Status:
+#   - open: Committed during a retrospective, not yet addressed
+#   - in-progress: Actively being worked on
+#   - done: Completed
+#
 # WORKFLOW NOTES:
 # ===============
 # - Mark epic as 'in-progress' when starting work on its first story
 # - Developer typically creates next story ONLY after previous one is 'done' to incorporate learnings
 # - Dev moves story to 'review', then Dev runs code-review (fresh context, ideally different LLM)
+# - Retrospective appends its action items to action_items; sprint-status surfaces open ones
 
 # EXAMPLE STRUCTURE (your actual epics/stories will replace these):
 
@@ -54,3 +60,10 @@ development_status:
   2-2-chat-interface: backlog
   2-3-llm-integration: backlog
   epic-2-retrospective: optional
+
+# Action items committed during retrospectives (section created by the retrospective workflow)
+action_items:
+  - epic: 1
+    action: "Add error-handling review to the code review checklist"
+    owner: "Charlie"
+    status: open

src/bmm-skills/4-implementation/bmad-sprint-status/SKILL.md

@@ -112,12 +112,14 @@ Run `/bmad:bmm:workflows:sprint-planning` to generate it, then rerun sprint-stat
   <action>Map legacy epic status "contexted" → "in-progress"</action>
   <action>Count epic statuses: backlog, in-progress, done</action>
   <action>Count retrospective statuses: optional, done</action>
+  <action>Parse action_items list if present. Set open_action_items = entries with status "open" or "in-progress"</action>
 
 <action>Validate all statuses against known values:</action>
 
 - Valid story statuses: backlog, ready-for-dev, in-progress, review, done, drafted (legacy)
 - Valid epic statuses: backlog, in-progress, done, contexted (legacy)
 - Valid retrospective statuses: optional, done
+- Valid action item statuses: open, in-progress, done
 
   <check if="any status is unrecognized">
     <output>
@@ -132,6 +134,7 @@ Run `/bmad:bmm:workflows:sprint-planning` to generate it, then rerun sprint-stat
 - Stories: backlog, ready-for-dev, in-progress, review, done
 - Epics: backlog, in-progress, done
 - Retrospectives: optional, done
+- Action items: open, in-progress, done
   </output>
   <ask>How should these be corrected?
   {{#each invalid_entries}}
@@ -181,6 +184,14 @@ Enter corrections (e.g., "1=in-progress, 2=backlog") or "skip" to continue witho
 
 **Next Recommendation:** /bmad:bmm:workflows:{{next_workflow_id}} ({{next_story_id}})
 
+{{#if open_action_items}}
+**Open Action Items:**
+{{#each open_action_items}}
+
+- {{action}} — {{status}} (epic {{epic}}, owner: {{owner}})
+  {{/each}}
+  {{/if}}
+
 {{#if risks}}
 **Risks:**
 {{#each risks}}
@@ -243,6 +254,7 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
   <template-output>epic_backlog = {{epic_backlog}}</template-output>
   <template-output>epic_in_progress = {{epic_in_progress}}</template-output>
   <template-output>epic_done = {{epic_done}}</template-output>
+  <template-output>open_action_items = {{open_action_items}}</template-output>
   <template-output>risks = {{risks}}</template-output>
   <action>Return to caller</action>
 </step>
@@ -283,6 +295,7 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
 - Stories: backlog, ready-for-dev, in-progress, review, done (legacy: drafted)
 - Epics: backlog, in-progress, done (legacy: contexted)
 - Retrospectives: optional, done
+- Action items (if present): open, in-progress, done
   <check if="any invalid status found">
   <template-output>is_valid = false</template-output>
   <template-output>error = "Invalid status values: {{invalid_entries}}"</template-output>

src/bmm-skills/module-help.csv

@@ -17,8 +17,8 @@ BMad Method,bmad-product-brief,Create Brief,CB,An expert guided experience to na
 BMad Method,bmad-prfaq,PRFAQ Challenge,WB,Working Backwards guided experience to forge and stress-test your product concept to ensure you have a great product that users will love and need through the PRFAQ gauntlet to determine feasibility and alignment with user needs. alternative to product brief.,,-H,1-analysis,,,false,planning_artifacts,prfaq document
 BMad Method,bmad-prd,Create Edit and Review PRD,PRD,"Facilitated PRD workflow — create a new PRD via coached discovery, update an existing one against a change signal, or validate a finished PRD against a checklist with an HTML findings report.",,,2-planning,bmad-product-brief,,true,planning_artifacts,prd
 BMad Method,bmad-ux,Create UX,CU,"Guidance through realizing the plan for your UX, strongly recommended if a UI is a primary piece of the proposed project.",,,2-planning,bmad-prd,,false,planning_artifacts,ux design
-BMad Method,bmad-create-architecture,Create Architecture,CA,Guided workflow to document technical decisions.,,,3-solutioning,,,true,planning_artifacts,architecture
+BMad Method,bmad-architecture,Architecture,CA,Offer once requirements exist (a PRD or spec; plus UX if present) and the user is ready to move from what to how. Also offer any time independently-built parts risk diverging. Produces the architecture spine: the invariants that keep features epics and stories consistent. Comes before epics and stories and scales from a quick spine to a full architecture (brownfield: ratifies the existing codebase).,,,3-solutioning,,,true,planning_artifacts,architecture
-BMad Method,bmad-create-epics-and-stories,Create Epics and Stories,CE,,,,3-solutioning,bmad-create-architecture,,true,planning_artifacts,epics and stories
+BMad Method,bmad-create-epics-and-stories,Create Epics and Stories,CE,,,,3-solutioning,bmad-architecture,,true,planning_artifacts,epics and stories
 BMad Method,bmad-check-implementation-readiness,Check Implementation Readiness,IR,Ensure PRD UX Architecture and Epics Stories are aligned.,,,3-solutioning,bmad-create-epics-and-stories,,true,planning_artifacts,readiness report
 BMad Method,bmad-sprint-planning,Sprint Planning,SP,Kicks off implementation by producing a plan the implementation agents will follow in sequence for every story.,,,4-implementation,,,true,implementation_artifacts,sprint status
 BMad Method,bmad-sprint-status,Sprint Status,SS,Anytime: Summarize sprint status and route to next workflow.,,,4-implementation,bmad-sprint-planning,,false,,

src/core-skills/bmad-module/scripts/install.mjs

@@ -206,7 +206,15 @@ export async function runInstall(opts) {
 // /tree/<ref> parsed from the source) pins; --channel stable resolves the latest
 // non-prerelease GitHub tag, falling back to next (with a warning) when there are
 // no tags, the URL isn't a GitHub repo, or the tags API is unreachable.
+const VALID_CHANNELS = new Set(['stable', 'pinned', 'next']);
+
 export async function resolveCloneTarget(descriptor, opts) {
+  // Reject typo'd channels up front (e.g. `--channel stabl`) so they error
+  // instead of silently falling through the branches below to the `next` default.
+  if (opts.channel && !VALID_CHANNELS.has(opts.channel)) {
+    throw new BmadModuleError(EXIT.USAGE, `unknown --channel "${opts.channel}" (expected: stable, pinned, next)`);
+  }
+
   if (descriptor.kind !== 'git') {
     return { ref: null, channel: null, version: null };
   }

src/core-skills/bmad-module/scripts/lib/source.mjs

@@ -1,7 +1,7 @@
 import fs from 'node:fs/promises';
 import path from 'node:path';
 import os from 'node:os';
-import { copyDir } from './fs-safe.mjs';
+import { copyDir, safePathInsideRoot } from './fs-safe.mjs';
 import { ensureCachedRepo } from './cache.mjs';
 import { EXIT, BmadModuleError } from './exit.mjs';
 
@@ -210,7 +210,12 @@ export async function materializeSource(descriptor, opts = {}) {
       await cleanup();
       throw new BmadModuleError(EXIT.USAGE, `local source not a directory: ${descriptor.path}`);
     }
-    await copyDir(descriptor.path, dir, STAGE_IGNORE);
+    try {
+      await copyDir(descriptor.path, dir, STAGE_IGNORE);
+    } catch (e) {
+      await cleanup();
+      throw e;
+    }
     return { dir, sha: null, ref: null, cleanup };
   }
 
@@ -224,13 +229,28 @@ export async function materializeSource(descriptor, opts = {}) {
     throw e;
   }
 
-  const moduleRoot = descriptor.subdir ? path.join(cached.repoDir, descriptor.subdir) : cached.repoDir;
+  // A subdir parsed from the source URL (/tree/<ref>/<subdir> or ?path=) is
+  // untrusted: reject `..`/absolute/symlink escapes so it can't copy out of the
+  // shared clone cache. safePathInsideRoot returns null on any escape.
+  let moduleRoot = cached.repoDir;
+  if (descriptor.subdir) {
+    moduleRoot = safePathInsideRoot(cached.repoDir, descriptor.subdir);
+    if (!moduleRoot) {
+      await cleanup();
+      throw new BmadModuleError(EXIT.PATH_TRAVERSAL, `subdirectory "${descriptor.subdir}" escapes the repository root`);
+    }
+  }
   const rootStat = await fs.stat(moduleRoot).catch(() => null);
   if (!rootStat || !rootStat.isDirectory()) {
     await cleanup();
     throw new BmadModuleError(EXIT.USAGE, `subdirectory "${descriptor.subdir}" not found in ${descriptor.displayName}`);
   }
 
-  await copyDir(moduleRoot, dir, STAGE_IGNORE);
+  try {
+    await copyDir(moduleRoot, dir, STAGE_IGNORE);
+  } catch (e) {
+    await cleanup();
+    throw e;
+  }
   return { dir, sha: cached.sha, ref: cached.ref, cleanup };
 }

src/core-skills/bmad-module/scripts/lib/vendor/ide-sync.mjs

@@ -10250,9 +10250,25 @@ var require_ide_sync = __commonJS({
         const sourceDir = path.dirname(path.join(bmadDir, relativePath));
         if (await fs.pathExists(sourceDir)) {
           await fs.remove(sourceDir);
+          await removeEmptyParents(path.dirname(sourceDir), bmadDir);
         }
       }
     }
+    async function removeEmptyParents(dir, bmadDir) {
+      let current = dir;
+      while (true) {
+        const rel = path.relative(bmadDir, current);
+        if (rel === "" || rel.startsWith("..") || path.isAbsolute(rel)) break;
+        try {
+          const entries = await fs.readdir(current);
+          if (entries.length > 0) break;
+          await fs.rmdir(current);
+        } catch {
+          break;
+        }
+        current = path.dirname(current);
+      }
+    }
     async function readSelectedIdes(bmadDir) {
       const yaml = require_dist();
       const manifestPath = path.join(bmadDir, "_config", "manifest.yaml");

src/core-skills/bmad-module/scripts/lib/vendor/platform-codes.yaml

@@ -70,6 +70,13 @@ platforms:
       target_dir: .agents/skills
       global_target_dir: ~/.codex/skills
 
+  codewhale:
+    name: "CodeWhale"
+    preferred: false
+    installer:
+      target_dir: .codewhale/skills
+      global_target_dir: ~/.codewhale/skills
+
   codebuddy:
     name: "CodeBuddy"
     preferred: false

src/core-skills/bmad-module/scripts/remove.mjs

@@ -2,7 +2,7 @@ import fs from 'node:fs/promises';
 import path from 'node:path';
 import { EXIT, BmadModuleError } from './lib/exit.mjs';
 import { findBmadDir } from './lib/bmad-dir.mjs';
-import { pruneEmptyDirs } from './lib/fs-safe.mjs';
+import { pruneEmptyDirs, safePathInsideRoot } from './lib/fs-safe.mjs';
 import {
   readManifestYaml,
   removeModuleFromManifest,
@@ -53,11 +53,21 @@ export async function runRemove(opts) {
     process.stderr.write(`[bmad-module] warning: failed to update config for removal of ${code}: ${e.message}\n`);
   }
 
+  // Resolve the module root with a containment check, so a traversal-tainted
+  // code (e.g. from a hand-edited manifest) can never delete outside _bmad/.
+  const moduleRoot = safePathInsideRoot(bmadDir, code);
+  if (!moduleRoot) {
+    throw new BmadModuleError(EXIT.PATH_TRAVERSAL, `module code "${code}" escapes _bmad/`);
+  }
+
   // Delete each file tracked in files-manifest.csv; prune empty dirs after.
   const fileEntries = await readFileEntriesForModule(bmadDir, code);
-  const moduleRoot = path.join(bmadDir, code);
   for (const fe of fileEntries) {
-    const abs = path.join(bmadDir, fe.path);
+    const abs = safePathInsideRoot(bmadDir, fe.path);
+    if (!abs) {
+      process.stderr.write(`[bmad-module] warn: skipping files-manifest path that escapes _bmad/: ${fe.path}\n`);
+      continue;
+    }
     try {
       await fs.rm(abs, { force: true });
       await pruneEmptyDirs(path.dirname(abs), moduleRoot);
@@ -72,8 +82,8 @@ export async function runRemove(opts) {
 
   // Optionally purge custom overrides.
   if (opts.purge) {
-    const customDir = path.join(bmadDir, 'custom', code);
+    const customDir = safePathInsideRoot(path.join(bmadDir, 'custom'), code);
-    await fs.rm(customDir, { recursive: true, force: true });
+    if (customDir) await fs.rm(customDir, { recursive: true, force: true });
   }
 
   // Drop manifest rows.

src/core-skills/bmad-module/scripts/update.mjs

@@ -4,7 +4,7 @@ import { findBmadDir } from './lib/bmad-dir.mjs';
 import { parseSource, materializeSource } from './lib/source.mjs';
 import { readAndValidateManifest } from './lib/plugin-json.mjs';
 import { readUserIgnores, buildIgnoreMatcher, buildCopyPlan, rewriteManifestPaths, validateDeclaredPaths } from './lib/install-plan.mjs';
-import { stageCopyPlan, atomicSwapDir, sha256File, pruneEmptyDirs } from './lib/fs-safe.mjs';
+import { stageCopyPlan, atomicSwapDir, sha256File, pruneEmptyDirs, safePathInsideRoot } from './lib/fs-safe.mjs';
 import {
   readManifestYaml,
   addModuleToManifest,
@@ -88,7 +88,8 @@ async function updateOne(bmadDir, projectDir, entry, opts) {
     const oldEntries = await readFileEntriesForModule(bmadDir, code);
     const modified = [];
     for (const fe of oldEntries) {
-      const abs = path.join(bmadDir, fe.path);
+      const abs = safePathInsideRoot(bmadDir, fe.path);
+      if (!abs) continue; // an entry that escapes _bmad/ is not a tracked file
       const current = await sha256File(abs);
       if (current === null) continue;
       if (fe.hash && current !== fe.hash) modified.push(fe.path);
@@ -113,7 +114,10 @@ async function updateOne(bmadDir, projectDir, entry, opts) {
     await stageCopyPlan(materialized.dir, stagedDir, plan, {
       '.claude-plugin/plugin.json': rewrittenManifestJson,
     });
-    const targetDir = path.join(bmadDir, code);
+    const targetDir = safePathInsideRoot(bmadDir, code);
+    if (!targetDir) {
+      throw new BmadModuleError(EXIT.PATH_TRAVERSAL, `module code "${code}" escapes _bmad/`);
+    }
     try {
       await atomicSwapDir(stagedDir, targetDir);
     } catch (e) {

src/core-skills/bmad-module/tests/fixtures/examples/comprehensive/acme-devlog/.mcp.json

@@ -0,0 +1,11 @@
+{
+  "mcpServers": {
+    "devlog-history": {
+      "command": "node",
+      "args": ["${CLAUDE_PLUGIN_ROOT}/scripts/mcp-server.js"],
+      "env": {
+        "DEVLOG_PATH": "${CLAUDE_PLUGIN_DATA}/devlog"
+      }
+    }
+  }
+}

src/core-skills/bmad-party-mode/SKILL.md

@@ -1,11 +1,13 @@
 ---
 name: bmad-party-mode
-description: 'Orchestrates lively group discussions between installed BMAD agents or other personas. Use when the user requests party mode, a roundtable, or multiple agent perspectives.'
+description: 'Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel.'
 ---
 
 # Party Mode
 
-Run a roundtable where BMAD agents talk to each other, and to the user, like a real group of distinct people in conversation. Your job as orchestrator is to make it feel like a genuine conversation: fast, in-character, opinionated, and fun. Everything below is an objective, not a script. Use whatever mechanism your model and harness make available to hit it.
+Run a round-table where BMAD agents talk to each other, and to the user, like a real group of distinct people in conversation. Your job as orchestrator is to make it feel like a genuine conversation: fast, in-character, opinionated, and fun. Everything below is an objective, not a script. Use whatever mechanism your model and harness make available to hit it.
+
+**Two intents.** Usually the user wants to *run* a party — that's everything below. If instead they want to *create or configure* one — invent a cast, add a persona, distill customer data into a focus-group panel, set a default, or **edit an existing custom party** (retune a member, add someone to a group) — load `references/create-party.md` and follow it. Detect which from how they invoke the skill; when it's unclear, ask. Neither intent has a headless contract: running a party is the live conversation itself, and the authoring path's only write goes through `bmad-customize`, which gates it.
 
 ## What "Good" Feels Like
 
@@ -16,60 +18,60 @@ Run a roundtable where BMAD agents talk to each other, and to the user, like a r
 
 If a round comes back feeling like four essays stapled together, you missed the objective. Tighten it the next round.
 
+## Conventions
+
+- Bare paths (e.g. `references/create-party.md`) resolve from `{skill-root}`, where `customize.toml` lives; `{project-root}`-prefixed paths from the project working directory.
+
 ## Setup
 
-1. Load `{project-root}/_bmad/core/config.yaml`: greet with `{user_name}`, speak in `{communication_language}`.
+1. **Resolve customization:** `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`. On failure, read `{skill-root}/customize.toml` directly and use its defaults. Then run each `{workflow.activation_steps_prepend}` entry, and hold each `{workflow.persistent_facts}` entry as session-long context (`file:`-prefixed entries are paths/globs under `{project-root}` whose contents load as facts; `skill:`-prefixed entries name a skill to consult; all others are facts verbatim).
-2. Resolve the roster:
+2. Load `{project-root}/_bmad/core/config.yaml`: greet with `{user_name}`, speak in `{communication_language}`, and resolve `{output_folder}` and `{date}` for the wrap-up keepsake.
-   ```bash
+3. **Resolve the active roster:** `python3 {skill-root}/scripts/resolve_party.py --project-root {project-root} --skill {skill-root}`. It returns the active group's full member detail (the `{workflow.default_party}` group if set, else the installed agents), the other group names, and the resolved `{workflow.party_mode}`. If the group carries a `scene`, open already in it and let it shape how the room behaves (who's loose or hostile, who pushes hardest); the same members play differently from one scene to the next. If flagged `open_cast`, cast the room on the fly from the universe its `scene` names — choosing who fits the moment and varying them as the topic shifts; listed members, if any, anchor the room. If `installed_agents_resolved` is false or codes come back `unresolved`, tell the user and carry on with what returned.
-   python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key agents
+4. **Roster overrides:**
-   ```
+   - If the invocation names a cast or characters inline (e.g. "include the main cast of Cheers circa 1982"), that named cast *is* the roster for this session — conjure them from what you know, go straight into the party, and once it's rolling offer once to save them as a custom party (the `references/create-party.md` write path), without stalling. Ephemeral; this path skips the script.
-   Each entry is keyed by `code` and carries `name`, `title`, `icon`, `description`, `module`, and `team`.
+   - A runtime `--party <id>` (alias `--group <id>`) overrides any configured `default_party`: run `resolve_party.py --party <id>` for that group's full detail. An unknown id comes back with the available group names — show them and ask which.
-3. Welcome the user, show who's in the room (icon, name, one-line role), and ask what they want to get into, unless it's already obvious from how they invoked party mode.
+   - Run `resolve_party.py --list-groups` for just the menu (id + name) when the user asks who else is around.
-4. This is theater of the mind here, so set the stage and vibe, emote and have fun with it - but specifically, dont say things about the mechanics of the party mode and break the 4th wall. Don't say "you have 4 agents in the room" or "agent X says". Instead, just let them talk, and let the user feel like they're in a lively group chat with a bunch of distinct personalities. Dont tell the user you are orchestrating a party mode, just run the party mode. The user should feel like they walked into a room where these people are already talking, not that you just spawned them to talk.
+   - Mid-session the same levers apply: the user can switch rooms ("switch to the writers' room") — re-run `resolve_party.py --party <id>`, set the new group's `scene`, and carry the thread over so the new faces react to where things stand — or summon any member of the *collective* (installed agents plus your custom `party_members`) by name, even one not in the current room.
+5. Welcome the user and show who's in the room (icon, name, one-line role). If other groups exist, you may note they can switch rooms. Then ask what they want to get into, unless it's already obvious from how they invoked party mode.
+
+Then run each `{workflow.activation_steps_append}` entry; if either hook list was non-empty, confirm every entry ran before continuing.
+
+**Hold this the whole run:** it's theater of the mind, so set the stage and play it straight — never break the fourth wall about the mechanism (no "you have 4 agents in the room", no "I'm orchestrating a party"). Let them talk; the user should feel they walked into a room where these people are already in conversation, not that you just spawned them.
 
 ## How It Runs
 
-**Default: you voice the room.** Pick 2 to 4 personas whose perspective fits the moment and let them talk directly, in one flowing exchange, fully in character. This is what keeps it fast and conversational. Vary who shows up round to round and let different voices interject as the topic shifts. Don't fall back on the same three agents every time.
+Use `{workflow.party_mode}` for the session unless the user passed `--mode <session|auto|subagent|agent-team>` (the older `--subagents` means `subagent`) — runtime intent always wins. One mode is active at a time; if its mechanism isn't available in your harness, fall back to `session` without comment.
 
-Each turn opens with `{icon} **{name}:**` and then that persona speaks. Present turns back to back so it reads as one conversation. Don't summarize, blend, or narrate what they "would" say. Let them say it.
+- **`session`** — voice every persona inline, one mind behind every voice. The floor every other mode degrades to; needs no extra instructions.
+- **`auto`** — voice inline for ordinary back-and-forth, spawn real agents only when independent thinking changes the outcome. Load `references/mode-auto.md` for that call; when it says to spawn, follow `references/mode-subagent.md`.
+- **`subagent`** — spawn a real agent per substantive round so each persona thinks independently. Load `references/mode-subagent.md`.
+- **`agent-team`** — stand the personas up as a persistent team who address each other directly (Claude Code only). Load `references/mode-agent-team.md`.
 
-**When independence matters, spawn them for real.** If a round's value depends on genuinely independent thinking (deep analysis, an honest review, perspectives that shouldn't be colored by one mind voicing them all), spawn the personas as separate agents using whatever your harness offers. Give each one the objective, their persona, the context, and what the others said if they're reacting. Trust their *thinking*: let them decide what to read and how to reach a view, and don't script their substance with do-and-don't checklists — that's what produces lifeless blobs. But do hold the *form*: a length cap (usually a sentence or three) and the instruction to react to what was just said rather than file a report. Constraining length and stance protects the conversation; constraining their reasoning kills it. Stay in character throughout; a persona goes long only when the user asked it to dig in.
+**Voicing the room** (every mode presents this way). Pick 2–3 personas whose perspective fits the moment and let them talk directly, in character; vary who shows up round to round so it isn't the same voices every time. Each turn opens with `{icon} **{name}:**`, and turns run back to back so it reads as one exchange. Don't summarize, blend, or narrate what a persona "would" say — let them say it.
-
-Spawn in parallel for independent first-takes — everyone reacts to the topic fresh, fast. Spawn sequentially when you want them reacting to each other's actual words: a real rebuttal has to have heard the thing it's rebutting, and parallel agents can't, so left raw they monologue side by side instead of arguing. Sequential is slower but it's the only way subagents genuinely engage. Either way, keep it to 2–3 voices a round; more reads as a crowd, not a conversation.
-
-By default you voice the room — for ordinary back-and-forth it's faster and feels more alive — and you reach for spawning when a round genuinely needs independent minds. But when the user asks for subagents (a launch flag like `--subagents`, or just saying so), that's a standing directive for the session: spawn for every substantive round until they say otherwise. Don't relitigate it round by round, and don't fall back to voicing because a moment felt light — the opening banter still gets spawned. A user who pinned the mode already made that call for you.
-
-**Model choice:** match the model to the round. Something quick for banter, something stronger for deep work. If the user pins a model (for example, `--model <name>`), use it for everyone.
 
 ## Make It Feel Like One Conversation
 
-Whether you voiced the room or spawned subagents, your job before presenting is the same: make it read like people responding to each other, not a row of separate answers all aimed at the user.
+Present one exchange, not a row of answers aimed at the user. The hard rule: never change what an agent argued — add staging and connective tissue, but don't invent positions, soften a stance, or put words in a persona's mouth. Weave delivery, preserve substance; it still reads like that specific character, quirks and speech patterns and all.
 
-This matters most with subagents. Each one only saw the user's message and the context you handed it, so left raw they all reply to the user in parallel and never to one another. Stitch them together. Reorder turns so a rebuttal lands right after the thing it rebuts. Add the connective phrasing real conversation has ("Hold on, Winston, that's backwards", "Sally's right about the API, but she's missing the cost"). Let one persona pick up a thread another dropped, or cut in mid-thought.
+## Always Holds
 
-Raw subagent output is raw material, never the final render — you cut it, interleave it, trim it. If a turn is still a full self-contained paragraph after you've woven it, you haven't woven it. The reader should feel a fast exchange, not a panel of separate statements read aloud in a row.
+- **Scene and persona are binding.** A group's `scene` and any behavioral instructions inside a member's `persona` are direction to follow exactly, not flavor to gesture at — play the staging and the character as written. When you spawn or stand up agents, carry both into their brief.
-
+- **Search when you're past your cutoff.** For anything that could have changed since training, use web search rather than guessing, and pass the same instruction into any subagent or team brief.
-The hard rule: never change what an agent actually argued. You add the connective tissue and the staging; you do not invent positions, soften a stance, or put words in a persona's mouth they didn't say. Weave the delivery, preserve the substance, and always the output reads like that specific character, quirks or speech patterns and all.
 
 ## Following the User's Lead
 
-The user steers. Whatever they raise, serve the conversation:
+The user steers — whatever they raise, serve the conversation: any combination, any time, from one voice to the whole table.
-
-- A new topic: fresh voices, keep it moving.
-- "Winston, what do you make of Sally's take?": just Winston, reacting to Sally.
-- "Bring in Amelia": Amelia joins, caught up on what's been said.
-- "Go deeper on that, John": this is the cue to let John stretch out. Depth is earned by a direct ask.
-- A question to the whole room: everyone relevant chimes in.
-
-Any combination, any time, from one voice to the whole table.
 
 ## Keeping It Healthy
 
-- **Everyone agreeing?** Drop in a contrarian, or hand someone the devil's-advocate hat.
 - **Going in circles?** Name the impasse and ask the user where to point next.
 - **User's gone quiet?** Ask straight: keep going, switch topics, or wrap up?
-- **A flat turn?** Don't retry it. Move on; the user will ask for more if they want it.
+- **A flat turn?** Don't retry it — move on; the user will ask for more if they want it.
+
+## Keep It Feeling Like a Party
+
+It is your goal to keep party mode feeling like a party, a good party. fun, engaging, simulating, insightful, or whatever the user came for. If the energy flags, or it drifts into a Q&A, or it feels like work, course-correct: bring in a new voice, crack a joke, call out the vibe and ask what they want to do about it. Inject some randomness and unexpectedness occasionally. Don't let it become a report. The user can always ask for a summary or key takeaways if they want them; you don't have to force it into the flow. Let it be what it is: a conversation between these people, in this scene, on this topic, in this scenario.
 
 ## Wrapping Up
 
-When the user signals they're done (any phrasing: "thanks", "that's all", "end party"), give a quick read-back of the best takeaways and drop back to normal mode. Read the room; don't wait for a magic word.
+When the user signals they're done, give a quick read-back of the best takeaways and offer them a keepsake: a single self-contained HTML document of the session to keep. If they want it, make it genuinely nice rather than a transcript dump — lay the conversation out by persona (their icons, names, voice), and reach for inline SVG and light animation where it lifts the piece. Write it as a standalone `.html` into `{workflow.output_dir}/` (a `{date}`-stamped, topic-named file), or wherever they ask. Then run `{workflow.on_complete}` if non-empty (a string scalar is one instruction, an array is a sequence run in order) and drop back to normal mode. Read the room; don't wait for a magic word.

src/core-skills/bmad-party-mode/customize.toml

@@ -0,0 +1,150 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Workflow customization surface for bmad-party-mode.
+#
+# Override files (not edited here):
+#   {project-root}/_bmad/custom/bmad-party-mode.toml         (team)
+#   {project-root}/_bmad/custom/bmad-party-mode.user.toml    (personal)
+
+[workflow]
+
+# --- Configurable below. Overrides merge per BMad structural rules: ---
+#   scalars: override wins • plain arrays: append
+#   arrays of tables keyed by `code`/`id`: matching key replaces, new keys append
+
+# Steps to run before the standard activation (config load, greet).
+# Use for pre-flight loads, compliance checks, etc.
+activation_steps_prepend = []
+
+# Steps to run after greet but before the room comes alive.
+activation_steps_append = []
+
+# Persistent facts the orchestrator keeps in mind for the whole session
+# (house rules, running gags, topics to avoid). Each entry is a literal
+# sentence, a `skill:`-prefixed reference, or a `file:`-prefixed path/glob whose
+# contents load as facts. Default picks up project-context.md if one exists.
+persistent_facts = [
+  "file:{project-root}/**/project-context.md",
+]
+
+# Which party loads when the user just says "party mode" with no override.
+# Empty = the installed BMAD agents — exactly the default behavior of a plain
+# install. Custom members defined below join the POOL (usable in groups, and
+# summonable by name) but do NOT crowd this default room. Set this to a
+# `party_groups` id to pin a curated room as the default instead. A runtime
+# `--party <id>` always wins.
+#
+# Example (set in team/user override TOML):  default_party = "writers-room"
+default_party = ""
+
+# How the room is run — who does the talking. A runtime `--mode <value>` wins for
+# the session; an unsupported mode (e.g. agent-team outside Claude Code) falls back
+# to "session". SKILL.md "How It Runs" is the authority on what each mode does.
+#   "session"    (default) never spawn — one mind voices every persona inline
+#   "auto"       voice inline for light rounds, spawn subagents when independent thinking matters
+#   "subagent"   spawn a real subagent per substantive round, so each persona thinks independently
+#   "agent-team" persistent agent team addressing each other directly (Claude Code only)
+party_mode = "session"
+
+# Where the optional end-of-session keepsake is written. The self-contained HTML
+# document lands in `{output_dir}/`. `{output_folder}` and `{date}` come from core
+# config; point this elsewhere in your team/user override to redirect keepsakes.
+output_dir = "{output_folder}/party-mode"
+
+# Executed when the party wraps (after the read-back, before dropping to normal
+# mode). String scalar = one instruction; array = instructions run in order.
+on_complete = ""
+
+# ---------------------------------------------------------------------------
+# Custom party members — personas, added to the POOL alongside the installed
+# agents. The default room stays installed-only; a custom member shows up when a
+# group uses them or you summon one by name. Keyed by `code`: an override entry
+# with a matching code replaces the base one (retune a shipped member), a new
+# code appends. Fields:
+#   code         short unique handle, used in party_groups and to summon them
+#   name         display name
+#   icon         single emoji shown on their turns
+#   title        one-line role/identity
+#   persona      voice, humor, ethos, pet peeves, how they argue — the meat;
+#                what makes them unmistakably themselves
+#   capabilities (optional) what they can do when spawned as a real subagent;
+#                woven into their spawn prompt as guidance, not a hard tool grant
+#   model        (optional) model to use when this member is spawned
+#
+# The members below ship the "Code Review Crew" (see the party_groups section).
+# They cost nothing until summoned — the default room never includes them.
+# ---------------------------------------------------------------------------
+
+[[workflow.party_members]]
+code = "sec-hawk"
+name = "Vex"
+icon = "🔒"
+title = "Security Engineer"
+persona = "Threat-models everything. Hunts injection, broken authz, leaked secrets, SSRF, supply-chain risk. Assumes every input is hostile and every dependency compromised until proven otherwise. Names the exploit path concretely — 'here's how I'd own this box' — never hand-waves 'might be insecure.'"
+capabilities = "Reads the code and traces data flow from untrusted input to sink before judging."
+
+[[workflow.party_members]]
+code = "adversary"
+name = "Grumbal"
+icon = "😤"
+title = "The Adversary"
+persona = "Assumes the code is broken and his job is to prove it. Grumpy, blunt, zero praise sandwiches. Starts from 'this will page someone at 3am' and works backward to the line that does it. Allergic to optimism and 'should be fine.'"
+
+[[workflow.party_members]]
+code = "edge-hunter"
+name = "Boundary"
+icon = "🌶️"
+title = "Edge-Case Hunter"
+persona = "Walks every branch and boundary. Empty input, null, the off-by-one, the huge payload, the concurrent call, the unicode name, the timezone, the retry storm. Method-driven, not mean: 'what happens when this is called twice at once?'"
+
+[[workflow.party_members]]
+code = "craftsman"
+name = "Yui"
+icon = "🎯"
+title = "The Craftsman"
+persona = "Cares about simplicity, naming, and reuse. Allergic to cleverness and duplication. 'You reimplemented something that already exists,' 'this name lies about what it does,' 'three nested abstractions where one would do.' Wants the boring, obvious, maintainable version."
+
+[[workflow.party_members]]
+code = "shipper"
+name = "Dana"
+icon = "🚢"
+title = "The Pragmatist"
+persona = "Counters the perfectionists so the room isn't a pile-on. 'Does this actually matter to a user? Ship the 80%, file the rest.' Pushes back on gold-plating and theoretical risks, forces everyone to rank what's real versus what's a nit."
+
+# ---------------------------------------------------------------------------
+# Named party groups — curated rooms picked at runtime with `--party <id>`
+# (alias `--group <id>`) or switched to mid-session. Keyed by `id`.
+#
+# `members` is a list of codes — installed agent codes, custom member codes, or
+# a mix. Override by `id` to retune a group; new ids append.
+#
+# An optional `scene` sets the stage: a freeform line (or a few) describing the
+# setting, what's happening, how the room behaves, and any in-the-moment
+# character notes — who's had a few, who's hostile to whom, who pressure-tests
+# hardest. The same members can power many scenes; define a member once, then
+# drop them into different rooms. No fixed vocabulary — the model reads it and
+# plays it.
+#
+# `members` is OPTIONAL. Leave it off and the group is open-cast: the `scene`
+# names a pool or universe and the room is cast on the fly — you don't enumerate
+# who shows up; the model picks who fits and can vary them by topic. List a few
+# members AND a scene to anchor some faces while the scene invites others in.
+#
+# More examples to drop into your override TOML:
+#   [[workflow.party_groups]]            # anchored room with a scene
+#   id = "writers-room"
+#   name = "The Writers' Room"
+#   scene = "Late-night room, everyone a little punchy. Pitch hard, kill darlings faster."
+#   members = ["analyst", "tech-writer", "morpheus"]
+#
+#   [[workflow.party_groups]]            # open-cast room (no roster; the scene casts it)
+#   id = "star-wars-rebels"
+#   name = "Star Wars Rebels"
+#   scene = "Aboard the Ghost. Figures from the Rebels universe drop in depending on the situation — pick whoever fits the topic, and let the roster shift as the conversation moves."
+# ---------------------------------------------------------------------------
+
+[[workflow.party_groups]]
+id = "code-review-crew"
+name = "Code Review Crew"
+scene = "Adversarial code review. Each reviewer attacks from their own lens and they argue with each other about what actually matters — security versus shipping, elegance versus pragmatism. No rubber-stamping, no praise sandwiches: surface the real problems before they ship. Point at the line, name the failure mode, and defend it when someone pushes back. Best run with `--mode subagent` so each lens reviews independently before they clash."
+members = ["sec-hawk", "adversary", "edge-hunter", "craftsman", "shipper"]

src/core-skills/bmad-party-mode/references/create-party.md

@@ -0,0 +1,65 @@
+# Creating a Party
+
+A guided authoring flow that turns an idea — a themed cast, a one-off persona, or a pile of raw profile data — into custom party members and groups, written to the user's customize.toml override. The output is configuration; `bmad-customize` does the actual write.
+
+## What you're producing
+
+Sparse `[workflow]` override entries for `bmad-party-mode`:
+
+- `[[workflow.party_members]]` — one per persona: `code`, `name`, `icon`, `title`, `persona`, optional `capabilities`, optional `model`.
+- `[[workflow.party_groups]]` — when the personas form a named room: `id`, `name`, an optional freeform `scene`, and `members` (codes). `members` is optional: leave it off for an open-cast room whose `scene` names a pool the model casts from on the fly.
+- `default_party` — set only if the user wants this group to load by default.
+
+A `scene` is one freeform line (or a few) that sets the stage for a room: the setting, what's happening, how the room behaves, and any in-the-moment character notes — who's three drinks in, who's hostile to whom, who pressure-tests hardest. It's how the same members power many different rooms (a bridge crew on duty vs. the same crew off-duty in the lounge vs. a hostile buyer panel). Define each member once; vary the `scene` per group rather than redefining people. There's no fixed vocabulary — write it plainly and the model plays it.
+
+The `persona` field is the whole game. A flat title produces a flat voice; the detail you elicit is what makes a member unmistakably themselves at the table.
+
+## Find the shape
+
+Open by understanding what they're building. Three common shapes — stay open, anything that yields distinct voices is fair game:
+
+- **A cast** — a themed ensemble ("the Star Trek TOS bridge crew", "a board of famous investors"). Several members plus a group that holds them.
+- **One-offs** — a persona or two added to the collective, no group needed.
+- **Distilled from data** — the user hands you source material (a spreadsheet of customer profiles, survey exports, interview notes) to compress into N stereotypical personas. This is how you stand up an AI focus group for product ideation or feedback.
+- **A panel of lenses** — purpose-built reviewers, each a sharp critical angle (a security engineer, an adversarial skeptic who assumes it's broken, an edge-case hunter, a craftsman who hates cleverness and duplication, a pragmatist who counters perfectionism). The group's `scene` tells them to attack from their lens and argue with each other about what actually matters. A great adversarial-review or red-team room.
+- **Open-cast** — no fixed roster at all. The group's `scene` names a pool or universe ("figures from the Star Wars Rebels universe drop in depending on the situation") and the room is cast on the fly. Leave `members` off; the model already knows the universe and picks who fits the moment. Anchor a face or two by listing them if some should always be present.
+
+Ask which they're after if it isn't obvious, then proceed.
+
+**Persisting a cast already in play.** When you arrive here from a live session — the user spun up an ad-hoc cast inline and wants to keep it — the personas are already drafted and voiced. Don't re-interrogate: capture them as they've been playing, give the group an `id` and name, ask the default question, and go straight to the write.
+
+## Editing an existing party
+
+When the user wants to change a party that already exists (retune a member's persona, add someone to a group, swap the default), read the current state first so you change rather than clobber: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow` returns the merged `party_members`, `party_groups`, and `default_party`. Show the member or group being touched, capture only the delta with the user, and hand that sparse change to `bmad-customize` — it replaces a `party_members`/`party_groups` entry whose `code`/`id` matches and appends the rest, so an edit is just the changed entry, never a full rewrite.
+
+## Distill from source data (when provided)
+
+When the user points you at data — a file path, a pasted table, exported profiles — read it and compress it into the requested number of representative personas. Cluster by what actually differentiates behavior (goals, budget, pains, adoption posture), not surface demographics alone. Each cluster becomes one persona with a real name and face. Name your reasoning: tell the user which segments you found and which traits drove the split, so they can correct the cut before you flesh the personas out. If they didn't say how many, propose a number from the spread in the data and let them adjust.
+
+For a focus-group panel, independent answers matter more than banter, so offer to set `party_mode` to `subagent` (or remind them `--mode subagent` does it per session) — otherwise one mind voices every customer and they bleed together.
+
+## Flesh out each persona
+
+Draft, don't interrogate. Propose a first cut of each persona and let the user react — far faster than a questionnaire. Push each one until it has a voice you could pick out blind. The dimensions that earn their place:
+
+- **Identity** — name, a one-line title, an emoji that fits.
+- **Voice & ethos** — how they talk, what they value, how they argue, their pet peeves.
+- **Agenda** — what they're really after in any conversation; what they push for.
+- **Quirks** — the specific, human details (a catchphrase, a bias, a blind spot).
+- For focus-group personas, also **likes and dislikes**: what would make them champion or reject an idea, and their relationship to the product space.
+- **Capabilities** (optional) — if this persona should research or read files when spawned, note it; it becomes soft guidance in their spawn prompt.
+
+Keep pushing for specificity. "Skeptical CFO" is a placeholder; "won't approve anything without a payback under 18 months, and says so in the first thirty seconds" is a persona.
+
+## Close it out
+
+- Ask straight: **anything else about this party to specify** before you write it — a house dynamic, a missing voice, a member who should lead.
+- Ask whether **this group should be the default party going forward**. Yes → set `default_party` to the group's id. One-offs with no group can't be a default; skip the ask.
+
+## Write via bmad-customize
+
+**First, check for code collisions.** A custom member whose `code` matches an installed agent silently *overrides* that agent in the collective. Before composing, resolve the collective once — `python3 {skill-root}/scripts/resolve_party.py --project-root {project-root} --skill {skill-root}` — and check each new member's `code` against the returned members. On a collision, surface it ("`analyst` would override the installed Analyst — intended, or pick a different code?") and let the user confirm or rename. One check, not a gate.
+
+Compose the sparse override and hand it to `bmad-customize` to place, confirm, and write — target skill `bmad-party-mode`, `[workflow]` surface. Default to the **user** override (`bmad-party-mode.user.toml`); offer the **team** file when the party is meant to be shared. Hand it the exact entries: the `party_members` tables, any `party_groups` table, and `default_party` if the user opted in. Keep it sparse — only the new entries, never a copy of the base customize.toml. `bmad-customize` shows the TOML, waits for an explicit yes, writes, and verifies the merge; don't write the file yourself.
+
+After it lands, tell the user how to use it: `--party <id>` to summon the group, or that it's now the default if they set it.

src/core-skills/bmad-party-mode/references/mode-agent-team.md

@@ -0,0 +1,11 @@
+# Agent-Team Mode
+
+Active when `{workflow.party_mode}` resolves to `agent-team` (or a `--mode agent-team` override). Stand the personas up as a persistent agent team whose members address each other directly, so the back-and-forth happens for real instead of being stitched together after. Claude Code only — if your harness can't stand up a team, fall back to `subagent`, and if that fails too, to `session`.
+
+Your job shifts from weaving to hosting: kick off the topic, keep turns short and in character, pull the thread back when it wanders, and surface the exchange to the user. Voice, brevity, and clash still hold.
+
+In each member's standing brief, carry: their persona; the group's `scene` and any behavioral instructions in the persona as binding direction; their `model` if one is set (a session `--model` pin wins for everyone); and the instruction to check anything that could be stale since the model's training cutoff with web search rather than guessing.
+
+## Model choice
+
+Match the model to the work: something quick for banter, something stronger for deep work. A per-member `model` is used when set; a session `--model <name>` pin overrides it for everyone.

src/core-skills/bmad-party-mode/references/mode-auto.md

@@ -0,0 +1,13 @@
+# Auto Mode
+
+Active when `{workflow.party_mode}` resolves to `auto` (or a `--mode auto` override). The blend: voice the room inline by default — fast and conversational — and spawn real independent agents only for the rounds where independence changes the answer. When you do spawn, follow `references/mode-subagent.md` for the mechanics. If your harness can't spawn agents, auto is just `session`.
+
+## When to spawn vs. voice
+
+Spawn independent agents when divergent, uncolored thinking is the value of the round:
+
+- A genuine evaluation, review, or critique — the kind that fails if one mind voices every side and they drift into agreement (code review, red-team, a hard look at a plan).
+- The personas would plausibly reach *different* conclusions, and that divergence is the point.
+- The user asked someone to dig in, analyze, or research — depth earned by a direct ask.
+
+Voice inline for everything else: banter, reactions, quick takes, the connective back-and-forth that is most of a conversation. When in doubt, voice — spawning is the exception you reach for, not the default.

src/core-skills/bmad-party-mode/references/mode-subagent.md

@@ -0,0 +1,19 @@
+# Subagent Mode
+
+Active when `{workflow.party_mode}` resolves to `subagent` (or a `--mode subagent` override). Spawn a real agent for every substantive round, the opening banter included, so each persona thinks independently — not one mind voicing them all. A standing directive: don't relitigate it round to round, and don't fall back to voicing because a moment felt light. If your harness can't spawn agents, fall back to `session`.
+
+## Spawning
+
+Give each agent the objective, their persona, the context, and what the others said if they're reacting. For a custom member, hand them their `persona` as their character and fold their `capabilities` note into the brief; spawn them with their `model` if one is set (a session `--model` pin wins for everyone). Always carry two things into the brief: the group's `scene` and any behavioral instructions in the persona are binding direction, and anything that could be stale since the model's training cutoff should be checked with web search rather than guessed.
+
+Trust their *thinking*: let them decide what to read and how to reach a view; don't script their substance with do-and-don't checklists — that's what produces lifeless blobs. But hold the *form*: a length cap (usually a sentence or three) and the instruction to react to what was just said rather than file a report. Constraining length and stance protects the conversation; constraining their reasoning kills it. Stay in character throughout; a persona goes long only when the user asked it to dig in.
+
+Spawn in parallel for independent first-takes; spawn sequentially when you want them reacting to each other's actual words. Keep it to a few voices a round — more reads as a crowd, not a conversation.
+
+## Weave the replies into one conversation
+
+Each agent saw only the user's message and the context you handed it, so left raw they reply in parallel and never to one another. Reorder turns so a rebuttal lands right after what it rebuts, add the connective phrasing real talk has ("Hold on, Winston, that's backwards", "Sally's right about the API, but she's missing the cost"), and let one persona pick up a thread another dropped. Never change what an agent argued — weave delivery, preserve substance.
+
+## Model choice
+
+Match the model to the round: something quick for banter, something stronger for deep work. A per-member `model` is used when set; a session `--model <name>` pin overrides it for everyone.

src/core-skills/bmad-party-mode/scripts/resolve_party.py

@@ -0,0 +1,267 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.11"
+# ///
+"""Resolve the party-mode roster, lazily.
+
+Merges the installed BMAD agents with the user's custom `party_members`
+into one collective, then projects only what the moment needs:
+
+  * default (no flag) — the active roster to load on entry: the
+    `default_party` group if one is configured, else the whole collective.
+    Other groups come back as names only, so nothing you aren't using is
+    loaded into the party.
+  * --list-groups — just id + name + size for every configured group. The
+    cheap menu for "which room?", with no member detail.
+  * --party <id> — full member detail for one chosen group, on demand
+    (e.g. when the user switches rooms). Unknown id returns the available
+    names instead of an error wall.
+
+The merge is deterministic (a keyed union; a custom member whose code
+matches an installed agent overrides it), so the orchestrator consumes a
+resolved roster instead of re-deriving it every session.
+
+Stdlib only (Python 3.11+ for tomllib). Shells out to the project's
+resolve_config.py and resolve_customization.py; falls back to reading
+customize.toml directly if the customization resolver is unavailable.
+
+  resolve_party.py --project-root P --skill S
+  resolve_party.py --project-root P --skill S --list-groups
+  resolve_party.py --project-root P --skill S --party writers-room
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+try:
+    import tomllib
+except ImportError:  # pragma: no cover - guarded for <3.11
+    sys.stderr.write("error: Python 3.11+ is required (stdlib `tomllib`).\n")
+    sys.exit(3)
+
+
+def _run_json(cmd):
+    """Run a resolver script and parse its JSON stdout. None on any failure."""
+    try:
+        out = subprocess.run(cmd, capture_output=True, text=True, timeout=60)
+    except (OSError, subprocess.SubprocessError):
+        return None
+    if out.returncode != 0 or not out.stdout.strip():
+        return None
+    try:
+        return json.loads(out.stdout)
+    except json.JSONDecodeError:
+        return None
+
+
+def load_agents(project_root: Path):
+    """Installed agents as {code: entry}. Empty dict (with a flag) on failure."""
+    script = project_root / "_bmad" / "scripts" / "resolve_config.py"
+    data = _run_json([sys.executable, str(script), "--project-root", str(project_root), "--key", "agents"])
+    if data is None:
+        return {}, False
+    return data.get("agents", {}) or {}, True
+
+
+def load_workflow(project_root: Path, skill_root: Path):
+    """Merged [workflow] table. Falls back to the skill's base customize.toml."""
+    script = project_root / "_bmad" / "scripts" / "resolve_customization.py"
+    data = _run_json([sys.executable, str(script), "--skill", str(skill_root), "--key", "workflow"])
+    if data is not None and "workflow" in data:
+        return data["workflow"]
+    # Fallback: read the skill's base customize.toml directly (no override merge).
+    toml_path = skill_root / "customize.toml"
+    if toml_path.exists():
+        try:
+            with toml_path.open("rb") as f:
+                return tomllib.load(f).get("workflow", {})
+        except (OSError, tomllib.TOMLDecodeError):
+            pass
+    return {}
+
+
+def _alias(code: str) -> str:
+    """Short alias for an installed agent code: bmad-agent-analyst -> analyst."""
+    for prefix in ("bmad-agent-", "bmad-"):
+        if code.startswith(prefix):
+            return code[len(prefix):]
+    return code
+
+
+def build_collective(agents: dict, party_members: list):
+    """One pool keyed by code. Custom members override matching installed agents.
+
+    Returns (collective, index, installed_codes):
+      * collective — every member (installed + custom), the pool groups draw
+        from and the orchestrator can summon by name.
+      * index — maps every resolvable token (code, prefix-stripped alias,
+        lower-cased name) to a canonical code.
+      * installed_codes — the codes occupying an installed-agent slot, in
+        order. This is the DEFAULT room: installed agents (with any custom
+        override applied in place), and NOT the pure-custom additions. So
+        shipping or defining custom members grows the pool without crowding
+        the default party.
+    """
+    collective = {}
+    index = {}
+    installed_codes = []
+
+    def register(code, entry):
+        collective[code] = entry
+        index[code] = code
+        index[code.lower()] = code
+        index[_alias(code).lower()] = code
+        name = entry.get("name")
+        if name:
+            index[name.lower()] = code
+
+    for code, info in agents.items():
+        register(code, {
+            "code": code,
+            "name": info.get("name", code),
+            "icon": info.get("icon", ""),
+            "title": info.get("title", ""),
+            "description": info.get("description", ""),
+            "module": info.get("module", ""),
+            "team": info.get("team", ""),
+            "source": "installed",
+        })
+        installed_codes.append(code)
+
+    for m in party_members or []:
+        code = m.get("code")
+        if not code:
+            continue
+        # A custom member overrides an installed agent it matches by code/alias/name.
+        canonical = index.get(code) or index.get(code.lower()) or code
+        entry = {"code": canonical, "source": "custom"}
+        for field in ("name", "icon", "title", "persona", "capabilities", "model"):
+            if m.get(field) is not None:
+                entry[field] = m[field]
+        entry.setdefault("name", canonical)
+        register(canonical, entry)
+        # An override keeps the installed slot; a brand-new custom does not join it.
+
+    return collective, index, installed_codes
+
+
+def resolve_members(member_tokens, collective, index):
+    """(resolved entries in listed order, unresolved tokens)."""
+    resolved, unresolved = [], []
+    for token in member_tokens or []:
+        code = index.get(token) or index.get(str(token).lower())
+        if code and code in collective:
+            resolved.append(collective[code])
+        else:
+            unresolved.append(token)
+    return resolved, unresolved
+
+
+def group_menu(groups):
+    """Names only — the cheap menu. Open-cast groups (no roster) are flagged."""
+    out = []
+    for g in groups or []:
+        if not isinstance(g, dict) or not g.get("id"):
+            continue
+        members = g.get("members", []) or []
+        entry = {"id": g["id"], "name": g.get("name", g["id"]),
+                 "member_count": len(members)}
+        if not members:
+            entry["open_cast"] = True
+        out.append(entry)
+    return out
+
+
+def find_group(groups, group_id):
+    for g in groups or []:
+        if isinstance(g, dict) and g.get("id") == group_id:
+            return g
+    return None
+
+
+def group_detail(g, collective, index):
+    """Full detail for one group: resolved members + the optional scene.
+
+    `scene` is a freeform line the orchestrator plays — setting, what's
+    happening, room dynamics, in-the-moment character notes. Surfaced only
+    here (when a group is the active/chosen roster), never in the menu.
+
+    `members` is optional. With none, the group is open-cast: `open_cast`
+    is flagged and the scene describes the pool the orchestrator casts from
+    on the fly (e.g. "figures from the Star Wars Rebels universe"). A few
+    listed members anchor the room; the scene can still invite more.
+    """
+    raw_members = g.get("members", []) or []
+    members, unresolved = resolve_members(raw_members, collective, index)
+    detail = {"active": g["id"], "name": g.get("name", g["id"]),
+              "members": members, "unresolved": unresolved}
+    if g.get("scene"):
+        detail["scene"] = g["scene"]
+    if not raw_members:
+        detail["open_cast"] = True
+    return detail
+
+
+def main():
+    ap = argparse.ArgumentParser(description="Resolve the party-mode roster, lazily.")
+    ap.add_argument("--project-root", required=True)
+    ap.add_argument("--skill", required=True, help="Path to the bmad-party-mode skill dir")
+    ap.add_argument("--party", help="Resolve full detail for this group id")
+    ap.add_argument("--list-groups", action="store_true", help="Group names only")
+    args = ap.parse_args()
+
+    project_root = Path(args.project_root).resolve()
+    skill_root = Path(args.skill).resolve()
+
+    workflow = load_workflow(project_root, skill_root)
+    groups = workflow.get("party_groups", []) or []
+    default_party = workflow.get("default_party", "") or ""
+    party_mode = workflow.get("party_mode", "session") or "session"
+
+    # Group menu never needs the (more expensive) installed-agent resolve.
+    if args.list_groups:
+        _emit({
+            "party_mode": party_mode,
+            "default_party": default_party,
+            "groups": group_menu(groups),
+        })
+        return
+
+    agents, agents_ok = load_agents(project_root)
+    collective, index, installed_codes = build_collective(agents, workflow.get("party_members", []))
+
+    if args.party:
+        g = find_group(groups, args.party)
+        if g is None:
+            _emit({"error": "unknown_group", "requested": args.party,
+                   "available": group_menu(groups)})
+            return
+        _emit({**group_detail(g, collective, index), "party_mode": party_mode})
+        return
+
+    # Default: the active roster to load on entry.
+    result = {"party_mode": party_mode, "groups": group_menu(groups),
+              "installed_agents_resolved": agents_ok}
+    g = find_group(groups, default_party) if default_party else None
+    if g is not None:
+        result.update(group_detail(g, collective, index))
+    else:
+        # No default group: the installed agents (custom additions stay in the
+        # pool but don't crowd the default room), exactly like a plain install.
+        result.update({"active": "installed",
+                       "members": [collective[c] for c in installed_codes]})
+    _emit(result)
+
+
+def _emit(obj):
+    reconfigure = getattr(sys.stdout, "reconfigure", None)
+    if reconfigure is not None:
+        reconfigure(encoding="utf-8")
+    sys.stdout.write(json.dumps(obj, indent=2, ensure_ascii=False) + "\n")
+
+
+if __name__ == "__main__":
+    main()

src/core-skills/bmad-party-mode/scripts/tests/test-resolve_party.py

@@ -0,0 +1,138 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.11"
+# ///
+"""Unit tests for resolve_party.py — merge, alias, override, group resolution."""
+
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+import resolve_party as rp  # noqa: E402
+
+AGENTS = {
+    "bmad-agent-analyst": {"name": "Mary", "icon": "📊", "title": "Analyst"},
+    "bmad-agent-pm": {"name": "John", "icon": "📋", "title": "PM"},
+}
+
+
+class TestAlias(unittest.TestCase):
+    def test_strips_known_prefixes(self):
+        self.assertEqual(rp._alias("bmad-agent-analyst"), "analyst")
+        self.assertEqual(rp._alias("bmad-foo"), "foo")
+
+    def test_passes_through_unprefixed(self):
+        self.assertEqual(rp._alias("morpheus"), "morpheus")
+
+
+class TestBuildCollective(unittest.TestCase):
+    def test_installed_agents_indexed_by_code_alias_and_name(self):
+        col, idx, _ = rp.build_collective(AGENTS, [])
+        self.assertEqual(set(col), {"bmad-agent-analyst", "bmad-agent-pm"})
+        self.assertEqual(idx["analyst"], "bmad-agent-analyst")      # alias
+        self.assertEqual(idx["mary"], "bmad-agent-analyst")         # name (ci)
+        self.assertEqual(idx["bmad-agent-pm"], "bmad-agent-pm")     # full code
+        self.assertEqual(col["bmad-agent-analyst"]["source"], "installed")
+
+    def test_custom_member_appends(self):
+        col, _, _ = rp.build_collective(AGENTS, [{"code": "morpheus", "name": "Morpheus", "persona": "riddles"}])
+        self.assertIn("morpheus", col)
+        self.assertEqual(col["morpheus"]["source"], "custom")
+        self.assertEqual(col["morpheus"]["persona"], "riddles")
+
+    def test_custom_overrides_installed_by_alias(self):
+        col, _, _ = rp.build_collective(AGENTS, [{"code": "analyst", "name": "Mary-Custom", "persona": "p"}])
+        # Override lands on the canonical installed code, not a new "analyst" entry.
+        self.assertNotIn("analyst", col)
+        self.assertEqual(col["bmad-agent-analyst"]["source"], "custom")
+        self.assertEqual(col["bmad-agent-analyst"]["name"], "Mary-Custom")
+
+    def test_member_without_code_skipped(self):
+        col, _, _ = rp.build_collective(AGENTS, [{"name": "Nameless"}])
+        self.assertEqual(set(col), {"bmad-agent-analyst", "bmad-agent-pm"})
+
+
+class TestResolveMembers(unittest.TestCase):
+    def setUp(self):
+        self.col, self.idx, _ = rp.build_collective(AGENTS, [{"code": "morpheus", "name": "Morpheus"}])
+
+    def test_resolves_in_listed_order_and_flags_unknowns(self):
+        resolved, unresolved = rp.resolve_members(["morpheus", "analyst", "ghost"], self.col, self.idx)
+        self.assertEqual([m["code"] for m in resolved], ["morpheus", "bmad-agent-analyst"])
+        self.assertEqual(unresolved, ["ghost"])
+
+    def test_empty(self):
+        self.assertEqual(rp.resolve_members([], self.col, self.idx), ([], []))
+
+
+class TestGroups(unittest.TestCase):
+    GROUPS = [
+        {"id": "wr", "name": "Writers", "members": ["analyst", "morpheus"]},
+        {"id": "bad"},  # no name -> falls back to id; no members -> count 0
+        {"name": "no-id"},  # dropped from menu
+    ]
+
+    def test_menu_is_names_only_with_counts_and_open_cast_flag(self):
+        menu = rp.group_menu(self.GROUPS)
+        self.assertEqual(menu, [
+            {"id": "wr", "name": "Writers", "member_count": 2},
+            {"id": "bad", "name": "bad", "member_count": 0, "open_cast": True},
+        ])
+
+    def test_find_group(self):
+        self.assertEqual(rp.find_group(self.GROUPS, "wr")["name"], "Writers")
+        self.assertIsNone(rp.find_group(self.GROUPS, "missing"))
+
+
+class TestGroupDetail(unittest.TestCase):
+    def setUp(self):
+        self.col, self.idx, _ = rp.build_collective(AGENTS, [{"code": "morpheus", "name": "Morpheus"}])
+
+    def test_scene_passes_through_when_present(self):
+        g = {"id": "tos-10-forward", "name": "Ten Forward", "members": ["morpheus"],
+             "scene": "Late evening, a few rounds in."}
+        d = rp.group_detail(g, self.col, self.idx)
+        self.assertEqual(d["scene"], "Late evening, a few rounds in.")
+        self.assertEqual([m["code"] for m in d["members"]], ["morpheus"])
+
+    def test_scene_omitted_when_absent_or_empty(self):
+        for g in ({"id": "g", "members": ["morpheus"]},
+                  {"id": "g", "members": ["morpheus"], "scene": ""}):
+            self.assertNotIn("scene", rp.group_detail(g, self.col, self.idx))
+
+    def test_anchored_group_is_not_open_cast(self):
+        g = {"id": "g", "members": ["morpheus"]}
+        self.assertNotIn("open_cast", rp.group_detail(g, self.col, self.idx))
+
+    def test_open_cast_group_flagged_with_empty_members(self):
+        g = {"id": "rebels", "name": "Star Wars Rebels",
+             "scene": "Figures from the Rebels universe drop in as the topic calls for them."}
+        d = rp.group_detail(g, self.col, self.idx)
+        self.assertTrue(d["open_cast"])
+        self.assertEqual(d["members"], [])
+        self.assertEqual(d["scene"][:7], "Figures")
+
+
+class TestInstalledCodesIsDefaultRoom(unittest.TestCase):
+    """The default room is installed agents only; pure customs stay in the pool."""
+
+    def test_pure_custom_excluded_override_kept_in_default_room(self):
+        col, _, installed = rp.build_collective(AGENTS, [
+            {"code": "morpheus", "name": "Morpheus"},                 # pure custom
+            {"code": "analyst", "name": "Mary-Custom", "persona": "p"},  # override
+            {"code": "sec-hawk", "name": "Vex"},                      # shipped crew member
+        ])
+        # Pure customs are in the pool...
+        self.assertIn("morpheus", col)
+        self.assertIn("sec-hawk", col)
+        # ...but NOT in the default room.
+        self.assertEqual(installed, ["bmad-agent-analyst", "bmad-agent-pm"])
+        default_room = [col[c]["code"] for c in installed]
+        self.assertEqual(default_room, ["bmad-agent-analyst", "bmad-agent-pm"])
+        # An override keeps its installed slot (and its custom content).
+        self.assertEqual(col["bmad-agent-analyst"]["name"], "Mary-Custom")
+
+
+if __name__ == "__main__":
+    unittest.main()

src/core-skills/bmad-spec/SKILL.md

@@ -43,22 +43,38 @@ Inside the spec folder:
 
 ```
 <spec-folder>/
-  SPEC.md                  ← uppercase, the kernel
+  SPEC.md                  ← uppercase, the kernel — DERIVED from .memlog.md, never hand-edited
-  <companion-1>.md         ← optional, content-typed (e.g. glossary.md)
+  <companion-1>.md         ← optional, content-typed (e.g. glossary.md); spec-authored ones are derived too
   <companion-2>.md
-  .decision-log.md         ← canonical memory for this spec
+  .memlog.md               ← canonical, append-only memory; what SPEC.md is distilled from
 ```
 
+## Memory and derivation
+
+`.memlog.md` is canonical — an append-only, chronological record of every decision, constraint, capability (with its stable `CAP-N`), assumption, open question, and bit of user direction, one line each in the order it happened, never edited or reordered. `SPEC.md` and every spec-authored companion are **derived on each run** from the memlog (the decision-of-record) plus the sources it cites for raw content — never hand-patched.
+
+Deriving the contract from a living log instead of editing the contract in place is what lets the steps around the spec (PRD, UX, architecture, epics) run in any order and feed the same spec without merge drift: the log only accumulates, the artifact is re-rendered. So the spec is updated *only* by re-deriving it here — bmad-spec is its single writer; a hand-edit to `SPEC.md` from outside is unsupported and is overwritten on the next derive.
+
+Writes go through the shared script — `{project-root}/_bmad/scripts/memlog.py`, the same location as `resolve_customization.py` (atomic; never read it back except to resume):
+
+- `python3 {project-root}/_bmad/scripts/memlog.py init --workspace {spec-folder} --field topic="<what is being specced>"` — once, at create.
+- `python3 {project-root}/_bmad/scripts/memlog.py append --workspace {spec-folder} --type <decision|constraint|capability|assumption|question|direction|note|event> --text "<one-line gist, reason included>"` — as each lands.
+- Terminal moments (a validation verdict, "spec finalized") are `--type event` entries; the memlog carries no status field.
+
 ## The Operation
 
-Read the input and its ancillary linked materials. If there is no input, follow the no-input branch in **Workspace** (ask or block). If a prior `SPEC.md` exists at the target folder, read it too — the operation becomes an update. Preserve capability IDs; new capabilities get the next unused `CAP-N`; never reuse retired IDs. Otherwise this is a create.
+Read the input and its ancillary linked materials. If there is no input, follow the no-input branch in **Workspace** (ask or block). If a prior `.memlog.md` exists at the target folder, read it — the operation becomes an update, and the memlog (not the rendered `SPEC.md`) is the authority on what was decided and on capability IDs. Preserve those IDs; new capabilities get the next unused `CAP-N`; never reuse retired IDs. Otherwise this is a create, and the first move is `memlog.py init`.
 
 When the input is structured and pre-sorted (a PRD with an addendum, a GDD, a brief produced by an upstream BMad skill), trust the authored separation: lift kernel-fitting content into SPEC.md, lift overflow into appropriately-named companions. When the input is mixed (a brain dump, a transcript, an RFC, a customer email), do the sorting yourself: walk each claim, apply the three-lens load-bearing test (Spec Law rule 7), and route to the kernel field or a companion.
 
 Distill the input into the five-field kernel using `{workflow.spec_template}` as the skeleton. When input is rich, extract directly — no elicitation. When input is sparse, choose: **express** (best-effort distill, every gap becomes an `open_questions[]` entry) or **guided** (walk the five fields with the user one at a time). Headless defaults to express and logs the choice. Interactive asks.
 
+A recognized domain implication the input leaves unaddressed *is* such a gap — name it as an `open_questions[]` entry (healthcare input silent on PHI/HIPAA, payments silent on PCI, control systems silent on fail-safe) and move on. Flag it; never invent the answer or coach toward it. If these dominate, the input is too thin — suggest `bmad-prd`.
+
 Write lean from the first pass: every sentence must earn its place. Decoration costs tokens and dilutes downstream readers.
 
+Log each decision, capability, constraint, and accepted change to `.memlog.md` as it is made — that running record is what the render reads. Because the log is append-only, a later entry supersedes an earlier one on the same point while the history stays intact. When two currently-live sources or companions disagree on the same field, or an either/or never got resolved, surface it to the user rather than silently choosing — the resolution is itself a new memlog entry.
+
 If the input is genuinely too thin to distill (e.g. "an app for hikers" with no surrounding context), stop and suggest `bmad-prd` (or sibling ceremony skill). This skill distills; it does not coach.
 
 ## Load-bearing
@@ -94,7 +110,7 @@ Every spec must satisfy these eight rules. The operation aims for them; the self
 5. **Success signal is concrete enough to test or demonstrate against.** "Users love it" doesn't qualify.
 6. **Capability IDs are stable and unique.** Never reused, never renumbered.
 7. **Preservation.** Every load-bearing source claim lands in SPEC.md or a companion. Wrapper ceremony does not.
-8. **Lean prose.** Every sentence carries load-bearing content. Cut decoration, hedges, backstory, throat-clearing. Applies to SPEC.md, companions, and `.decision-log.md`.
+8. **Lean prose.** Every sentence carries load-bearing content. Cut decoration, hedges, backstory, throat-clearing. Applies to SPEC.md, companions, and `.memlog.md`.
 
 ## Self-Validate
 
@@ -104,7 +120,7 @@ After every create or update, sweep the resulting artifact in **two passes** bef
 
 **Pass 2 — Preservation.** Walk the source claim by claim. Confirm each load-bearing claim landed in SPEC.md or a companion. Wrapper-ceremony drops are logged under "Wrapper-only content" so the drop is on the record, not silent.
 
-Append a one-paragraph verdict to `.decision-log.md` covering both passes. In interactive mode, review the verdict with the user. In headless mode, `.decision-log.md` is one of the files returned, so the caller (or its downstream LLM) reads the verdict there.
+Record the verdict for each pass to `.memlog.md` (`append --type event`). In interactive mode, review it with the user. In headless mode, `.memlog.md` is one of the files returned, so the caller (or its downstream LLM) reads the verdict there.
 
 ## Spec with no change signal
 
@@ -120,10 +136,10 @@ Run `{workflow.on_complete}` if set.
 
 ## After Spec is Output
 
-Any update to spec regarding assumptions, open questions, or other changes should be appended to that source's decision log also and offer to update the source.
+Any update to the spec — resolved assumptions, answered open questions, other changes — is appended to `.memlog.md` as it happens. When a change overrides something that came from a source input, offer to update that source too, so upstream and the spec don't silently diverge.
 
 ## Frontmatter conventions
 
 - `companions:` array of `.md` files downstream MUST read alongside SPEC.md to have the full contract. Paths may point inside the spec folder (spec-authored companions like `glossary.md`) or outside it (adopted companions like `../planning-artifacts/ux-designs/ux-foo-bar-2026-05-23/DESIGN.md`). The split between spec-authored and adopted is implicit by path; downstream treats both the same.
 - `sources:` array of paths to files that were **fully absorbed** into the SPEC, with no remaining downstream value (e.g., a PRD whose every load-bearing claim is now in the kernel). Listed for audit and for bmad-spec to re-read on update. Downstream does NOT read these. Files that downstream still needs to read belong in `companions:`, not here.
-- **Do not list** decision logs, README files, organizational artifacts, or any operational record of how upstream skills produced their artifacts. Those are not source content; they are process metadata that downstream consumers don't need.
+- **Do not list** the memlog, README files, organizational artifacts, or any operational record of how upstream skills produced their artifacts. Those are not source content; they are process metadata that downstream consumers don't need.

src/core-skills/bmad-spec/assets/headless-schemas.md

@@ -1,6 +1,6 @@
 # Headless JSON Response
 
-The default invocation is headless: input goes in, JSON comes out. The contract is intentionally tiny — return the outcome and the files touched. Anything else a caller needs is inside those files (SPEC.md, companions, `.decision-log.md`).
+The default invocation is headless: input goes in, JSON comes out. The contract is intentionally tiny — return the outcome and the files touched. Anything else a caller needs is inside those files (SPEC.md, companions, `.memlog.md`).
 
 ## Success
 
@@ -10,12 +10,12 @@ The default invocation is headless: input goes in, JSON comes out. The contract
   "files": [
     "_bmad-output/specs/spec-quarter-drop/SPEC.md",
     "_bmad-output/specs/spec-quarter-drop/glossary.md",
-    "_bmad-output/specs/spec-quarter-drop/.decision-log.md"
+    "_bmad-output/specs/spec-quarter-drop/.memlog.md"
   ]
 }
 ```
 
-`files` lists every file written or modified in this run, in any order. The spec folder, kernel filename, decision log location, capabilities, companions, and verdict are all readable from those files; no need to re-encode them in the response.
+`files` lists every file written or modified in this run, in any order. The spec folder, kernel filename, memlog location, capabilities, companions, and verdict are all readable from those files; no need to re-encode them in the response.
 
 ## Blocked
 

src/core-skills/bmad-spec/assets/spec-template.md

@@ -1,7 +1,7 @@
 ---
 id: SPEC-{slug}
 companions: []     # files downstream MUST read alongside SPEC.md. Paths may point inside the spec folder (spec-authored) or outside it (adopted from an upstream skill).
-sources: []        # files fully absorbed into the SPEC (audit only; downstream does NOT read these). Never decision logs.
+sources: []        # files fully absorbed into the SPEC (audit only; downstream does NOT read these). Never the memlog.
 ---
 
 > **Canonical contract.** This SPEC and the files in `companions:` are the complete, preservation-validated contract for what to build, test, and validate. Source documents listed in frontmatter are for traceability only — consult them only if you need narrative rationale or prose color this contract intentionally omits.

src/scripts/memlog.py

@@ -0,0 +1,224 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.8"
+# ///
+"""memlog — an append-only memory log: LLM-optimal working memory for a skill.
+
+A memlog is the dense, chronological record of everything that mattered in a piece of
+work — every item the user generated or accepted — kept minimal like human memory: only
+what's important, never bloated. It persists ACROSS sessions, so a fresh session can
+load it and continue. It is NOT a deliverable; downstream artifacts (a brief, a PRD, a
+deck, a report) are *derived* from it on demand. The host skill supplies the vocabulary
+by how it calls `append` — the tool stays neutral.
+
+It is a FLAT log: there are no sections or grouping. Every entry is one line, recorded
+at the END in the order it happened. The chronology itself is the structure — an event
+like "started technique X" is just another entry, same as an idea or an insight.
+
+Three invariants make it trustworthy:
+
+  1. Append-only, chronological. Entries land at the end, in the order they happen.
+     Nothing is ever inserted backward, reordered, edited, or removed. There is no
+     edit or delete subcommand by design; history is never rewritten.
+  2. Write-only / blind. Every command is an atomic, context-free write and echoes the
+     new state as one line of JSON, so the caller never re-reads the file mid-session.
+     The one time the file is read is on resume — and the caller reads it itself, not
+     via this script.
+  3. No lifecycle status. A memory log has no "complete" flag. Whether the work is done,
+     blocked, or paused is itself a fact that happened, so it is recorded as an entry
+     (e.g. `append --type event --text "session complete"`), never as frontmatter the
+     log would have to mutate. The chronology stays the single source of truth, and a
+     resume learns the state by reading the last entries — the same way it learns
+     everything else.
+
+Atomicity: every write goes to a temp file, is flushed and fsync'd, then atomically
+renamed over the target, so a crash never leaves a half-written entry.
+
+The file shape (.memlog.md):
+
+    ---
+    topic: Onboarding flow for a budgeting app
+    goal: lift week-1 retention
+    updated: 2026-06-07T14:22
+    ---
+
+    - (note) user picked techniques: SCAMPER, then Six Thinking Hats
+    - (technique) started SCAMPER
+    - (idea) skip the signup wall: let people try with sample data first
+    - (idea) auto-import one bank account so the first screen shows real numbers
+    - (question) is open-banking consent too heavy for step one?
+    - (insight) the "scary numbers" risk and the "real numbers" idea are one lever: show real data, pre-categorized
+    - (direction) optimize for the anxious first-timer, not the power user
+    - (decision) lead with one pre-categorized account; defer multi-account import
+    - (event) session complete
+
+Each entry may carry an optional `--type` — what KIND it is (idea, insight, question,
+decision, direction, assumption, gap, note, event, …) — and an optional `--by` naming
+who it came from (e.g. `user`, `coach`), for sessions where authorship matters. Both
+render into one short inline tag: `(idea)`, `(idea by user)`, `(by coach)`. Omit them
+for a plain note. The host skill names the vocabulary; the script does not enforce one.
+
+Commands:
+  init   (--workspace DIR | --path FILE) [--field k=v ...]    create the memlog (errors if it exists)
+  append (--workspace DIR | --path FILE) --text STR [--type T] [--by W]  append one entry at the end
+  set    (--workspace DIR | --path FILE) --key K --value V    set/replace a descriptive frontmatter field
+
+Addressing: `--workspace` is the run folder, and the memlog is always {workspace}/.memlog.md.
+`--path` points straight at the memlog file instead, for callers that already hold the path.
+"""
+from __future__ import annotations  # keep type-hint syntax lazy so the script runs on 3.8+
+
+import argparse
+import json
+import os
+import sys
+from datetime import datetime
+from pathlib import Path
+
+MEMLOG = ".memlog.md"
+
+
+def now() -> str:
+    return datetime.now().strftime("%Y-%m-%dT%H:%M")
+
+
+def resolve(args) -> Path:
+    """The memlog file, from either addressing mode: {workspace}/.memlog.md or an explicit --path."""
+    return Path(args.path) if args.path else Path(args.workspace) / MEMLOG
+
+
+def split(text: str) -> tuple[dict, str]:
+    """Return (frontmatter dict in source order, body str). Frontmatter is plain key: value.
+
+    The closing fence is the first line that is *exactly* `---`, so a `---` inside a
+    field value (topic/goal are free user text) never truncates the frontmatter.
+    """
+    lines = text.splitlines()
+    if not lines or lines[0] != "---":
+        raise ValueError(".memlog.md has no frontmatter")
+    end = next((i for i in range(1, len(lines)) if lines[i] == "---"), None)
+    if end is None:
+        raise ValueError(".memlog.md frontmatter is not terminated")
+    meta: dict[str, str] = {}
+    for line in lines[1:end]:
+        if ":" in line:
+            k, v = line.split(":", 1)
+            meta[k.strip()] = v.strip()
+    return meta, "\n".join(lines[end + 1:]).lstrip("\n")
+
+
+def render(meta: dict, body: str) -> str:
+    # Neutralize newlines in values so a multi-line field can't break the fence on re-read.
+    fm = "\n".join(f"{k}: {' '.join(str(v).splitlines())}" for k, v in meta.items())
+    return "---\n" + fm + "\n---\n\n" + body.rstrip("\n") + "\n"
+
+
+def touch(meta: dict) -> None:
+    """Stamp `updated` and keep it last so the field order stays predictable."""
+    meta.pop("updated", None)
+    meta["updated"] = now()
+
+
+def write_atomic(path: Path, text: str) -> None:
+    """Temp + flush + fsync + atomic rename, so a crash never half-writes an entry."""
+    tmp = path.with_suffix(path.suffix + ".tmp")
+    with open(tmp, "w", encoding="utf-8") as f:
+        f.write(text)
+        f.flush()
+        os.fsync(f.fileno())
+    os.replace(tmp, path)
+
+
+def entry_count(body: str) -> int:
+    return sum(1 for ln in body.splitlines() if ln.startswith("- "))
+
+
+def ack(path: Path, body: str) -> None:
+    """Echo new state so the caller never re-reads the file to know where it stands."""
+    print(json.dumps({
+        "ok": True,
+        "memlog": str(path),
+        "entries": entry_count(body),
+    }))
+
+
+def cmd_init(args) -> int:
+    path = resolve(args)
+    if path.exists():
+        print(f"error: {path} already exists; use append/set to update it", file=sys.stderr)
+        return 2
+    path.parent.mkdir(parents=True, exist_ok=True)
+    meta: dict[str, str] = {}
+    for pair in args.field or []:
+        if "=" not in pair:
+            print(f"error: --field expects key=value, got {pair!r}", file=sys.stderr)
+            return 2
+        k, v = pair.split("=", 1)
+        meta[k.strip()] = v.strip()
+    touch(meta)
+    write_atomic(path, render(meta, ""))
+    ack(path, "")
+    return 0
+
+
+def cmd_append(args) -> int:
+    path = resolve(args)
+    meta, body = split(path.read_text(encoding="utf-8"))
+    text = " ".join(args.text.split())  # collapse newlines/runs → one-line entry, no prose bloat
+    label = args.type or ""
+    if args.by:
+        label = f"{label} by {args.by}".strip()  # attribution: "(idea by user)" / "(by coach)"
+    tag = f"({label}) " if label else ""
+    entry = f"- {tag}{text}"
+    body = (body.rstrip("\n") + "\n" + entry) if body.strip() else entry  # always at the end
+    touch(meta)
+    write_atomic(path, render(meta, body))
+    ack(path, body)
+    return 0
+
+
+def cmd_set(args) -> int:
+    path = resolve(args)
+    meta, body = split(path.read_text(encoding="utf-8"))
+    meta[args.key] = args.value
+    touch(meta)
+    write_atomic(path, render(meta, body))
+    ack(path, body)
+    return 0
+
+
+def add_target(sp) -> None:
+    """Every command addresses the memlog the same way: a run folder or an explicit path."""
+    g = sp.add_mutually_exclusive_group(required=True)
+    g.add_argument("--workspace", help="run folder; the memlog is {workspace}/.memlog.md")
+    g.add_argument("--path", help="explicit memlog file path (alternative to --workspace)")
+
+
+def main(argv: list[str] | None = None) -> int:
+    p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    sub = p.add_subparsers(dest="cmd", required=True)
+
+    pi = sub.add_parser("init", help="create the memlog")
+    add_target(pi)
+    pi.add_argument("--field", action="append", metavar="KEY=VALUE", help="frontmatter field (repeatable)")
+    pi.set_defaults(func=cmd_init)
+
+    pa = sub.add_parser("append", help="append one entry at the end")
+    add_target(pa)
+    pa.add_argument("--text", required=True)
+    pa.add_argument("--type", help="entry kind, rendered as an inline tag")
+    pa.add_argument("--by", help="who the entry came from (e.g. user, coach); rendered into the tag")
+    pa.set_defaults(func=cmd_append)
+
+    pset = sub.add_parser("set", help="set a descriptive frontmatter field")
+    add_target(pset)
+    pset.add_argument("--key", required=True)
+    pset.add_argument("--value", required=True)
+    pset.set_defaults(func=cmd_set)
+
+    args = p.parse_args(argv)
+    return args.func(args)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

src/scripts/tests/test_memlog.py

@@ -0,0 +1,306 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = ["pytest>=8.0"]
+# ///
+"""Tests for memlog.py. Run: uv run --with pytest pytest scripts/tests/test_memlog.py
+
+The spine under test is the flat, append-only, chronological invariant: every entry is
+one line recorded at the end in the order it happened — no sections, no grouping, and no
+lifecycle status the log would have to mutate.
+"""
+import json
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+import memlog  # noqa: E402
+
+MEMLOG = ".memlog.md"
+
+
+@pytest.fixture
+def ws(tmp_path):
+    return str(tmp_path)
+
+
+def read(ws):
+    return (Path(ws) / MEMLOG).read_text(encoding="utf-8")
+
+
+def body_of(ws):
+    return memlog.split(read(ws))[1]
+
+
+def entries(ws):
+    return [ln for ln in body_of(ws).splitlines() if ln.startswith("- ")]
+
+
+def init(ws, **fields):
+    fields = fields or {"topic": "Reinvent the lunchbox", "goal": "ideas for a pitch"}
+    argv = ["init", "--workspace", ws]
+    for k, v in fields.items():
+        argv += ["--field", f"{k}={v}"]
+    assert memlog.main(argv) == 0
+
+
+def append(ws, text, entry_type=None, by=None):
+    argv = ["append", "--workspace", ws, "--text", text]
+    if entry_type:
+        argv += ["--type", entry_type]
+    if by:
+        argv += ["--by", by]
+    assert memlog.main(argv) == 0
+
+
+# --- init ---------------------------------------------------------------
+
+def test_init_writes_frontmatter_fields(ws):
+    init(ws)
+    meta, body = memlog.split(read(ws))
+    assert meta["topic"] == "Reinvent the lunchbox"
+    assert meta["goal"] == "ideas for a pitch"
+    assert "updated" in meta
+    assert body.strip() == ""
+
+
+def test_init_has_no_lifecycle_status(ws):
+    # A memory log carries no "status" flag; completion is an appended entry, not frontmatter.
+    init(ws)
+    meta, _ = memlog.split(read(ws))
+    assert "status" not in meta
+
+
+def test_init_arbitrary_fields(ws):
+    init(ws, topic="T", audience="board")
+    meta, _ = memlog.split(read(ws))
+    assert meta["audience"] == "board"
+
+
+def test_init_refuses_overwrite(ws):
+    init(ws)
+    assert memlog.main(["init", "--workspace", ws, "--field", "topic=other"]) == 2
+
+
+def test_init_creates_missing_workspace(tmp_path):
+    nested = str(tmp_path / "a" / "b")
+    assert memlog.main(["init", "--workspace", nested, "--field", "topic=T"]) == 0
+    assert (Path(nested) / MEMLOG).is_file()
+
+
+def test_init_rejects_malformed_field(ws):
+    assert memlog.main(["init", "--workspace", ws, "--field", "noequals"]) == 2
+
+
+# --- addressing: --workspace and --path are interchangeable --------------
+
+def test_path_addressing_targets_the_file_directly(tmp_path):
+    target = tmp_path / "run" / ".memlog.md"
+    assert memlog.main(["init", "--path", str(target), "--field", "topic=T"]) == 0
+    assert target.is_file()
+    assert memlog.main(["append", "--path", str(target), "--text", "an idea", "--type", "idea"]) == 0
+    body = memlog.split(target.read_text(encoding="utf-8"))[1]
+    assert "- (idea) an idea" in body
+
+
+def test_workspace_and_path_resolve_to_same_file(ws):
+    init(ws)
+    via_path = str(Path(ws) / MEMLOG)
+    assert memlog.main(["append", "--path", via_path, "--text", "from path"]) == 0
+    assert memlog.main(["append", "--workspace", ws, "--text", "from workspace"]) == 0
+    assert entries(ws) == ["- from path", "- from workspace"]
+
+
+def test_target_is_required(ws):
+    with pytest.raises(SystemExit):
+        memlog.main(["append", "--text", "orphan"])  # neither --workspace nor --path
+
+
+# --- append: flat chronological order is the whole point -----------------
+
+def test_append_lands_at_end_in_order(ws):
+    init(ws)
+    append(ws, "first")
+    append(ws, "second")
+    append(ws, "third")
+    assert entries(ws) == ["- first", "- second", "- third"]
+
+
+def test_no_sections_or_headings_ever(ws):
+    init(ws)
+    append(ws, "started foo", entry_type="technique")
+    append(ws, "an idea", entry_type="idea")
+    append(ws, "started bar", entry_type="technique")
+    assert "## " not in body_of(ws)  # the flat log never grows headings
+
+
+def test_type_renders_as_inline_tag(ws):
+    init(ws)
+    append(ws, "the earth revolves around the sun", entry_type="idea")
+    append(ws, "how do we handle stampede?", entry_type="question")
+    body = body_of(ws)
+    assert "- (idea) the earth revolves around the sun" in body
+    assert "- (question) how do we handle stampede?" in body
+
+
+def test_append_without_type_is_plain_note(ws):
+    init(ws)
+    append(ws, "bare entry")
+    assert entries(ws) == ["- bare entry"]
+
+
+def test_completion_is_an_entry_not_a_status(ws):
+    # The documented way to mark a session done: append it. Frontmatter never gains a status.
+    init(ws)
+    append(ws, "session complete", entry_type="event")
+    meta, _ = memlog.split(read(ws))
+    assert "status" not in meta
+    assert entries(ws)[-1] == "- (event) session complete"
+
+
+def test_append_collapses_newlines_into_one_line(ws):
+    init(ws)
+    append(ws, "line one\nline two\n  spaced   out")
+    assert entries(ws) == ["- line one line two spaced out"]
+
+
+def test_revisited_technique_is_just_a_later_entry(ws):
+    # the user's model: switching techniques is an entry, not a section to return to
+    init(ws)
+    append(ws, "started SCAMPER", entry_type="technique")
+    append(ws, "magnetic latch", entry_type="idea")
+    append(ws, "started Six Hats", entry_type="technique")
+    append(ws, "stale data risk", entry_type="idea")
+    append(ws, "started SCAMPER", entry_type="technique")  # back to SCAMPER — just appended again
+    append(ws, "stackable tiers", entry_type="idea")
+    assert entries(ws) == [
+        "- (technique) started SCAMPER",
+        "- (idea) magnetic latch",
+        "- (technique) started Six Hats",
+        "- (idea) stale data risk",
+        "- (technique) started SCAMPER",
+        "- (idea) stackable tiers",
+    ]
+
+
+def test_by_renders_attribution_in_tag(ws):
+    # Creative Partner mode must record whose idea each one was
+    init(ws)
+    append(ws, "magnetic latch lid", entry_type="idea", by="user")
+    append(ws, "lid doubles as a plate", entry_type="idea", by="coach")
+    body = body_of(ws)
+    assert "- (idea by user) magnetic latch lid" in body
+    assert "- (idea by coach) lid doubles as a plate" in body
+
+
+def test_by_without_type_renders_alone(ws):
+    init(ws)
+    append(ws, "off-the-cuff thought", by="coach")
+    assert entries(ws) == ["- (by coach) off-the-cuff thought"]
+
+
+def test_heterogeneous_entry_types_coexist(ws):
+    init(ws)
+    append(ws, "an idea", entry_type="idea")
+    append(ws, "an open question", entry_type="question")
+    append(ws, "a decision we made", entry_type="decision")
+    append(ws, "user wants mobile-first", entry_type="direction")
+    body = body_of(ws)
+    for tag in ("(idea)", "(question)", "(decision)", "(direction)"):
+        assert tag in body
+
+
+def test_free_vocabulary_is_not_enforced(ws):
+    # The tool is neutral: any --type the host skill names renders verbatim.
+    init(ws)
+    append(ws, "a custom kind", entry_type="crack")
+    append(ws, "another", entry_type="lock")
+    body = body_of(ws)
+    assert "- (crack) a custom kind" in body
+    assert "- (lock) another" in body
+
+
+# --- set: generic descriptive frontmatter, no lifecycle semantics --------
+
+def test_set_adds_field(ws):
+    init(ws)
+    memlog.main(["set", "--workspace", ws, "--key", "mode", "--value", "partner"])
+    assert memlog.split(read(ws))[0]["mode"] == "partner"
+
+
+def test_set_replaces_field(ws):
+    init(ws, topic="T", mode="facilitator")
+    memlog.main(["set", "--workspace", ws, "--key", "mode", "--value", "partner"])
+    assert memlog.split(read(ws))[0]["mode"] == "partner"
+
+
+def test_set_preserves_body(ws):
+    init(ws)
+    append(ws, "keep me", entry_type="idea")
+    memlog.main(["set", "--workspace", ws, "--key", "mode", "--value", "partner"])
+    meta, body = memlog.split(read(ws))
+    assert meta["mode"] == "partner"
+    assert "- (idea) keep me" in body
+
+
+def test_updated_stays_last(ws):
+    init(ws)
+    memlog.main(["set", "--workspace", ws, "--key", "owner", "--value", "BMad"])
+    meta = memlog.split(read(ws))[0]
+    assert list(meta)[-1] == "updated"
+
+
+# --- robustness ---------------------------------------------------------
+
+def test_roundtrip_render_is_stable(ws):
+    init(ws)
+    append(ws, "one", entry_type="idea")
+    first = read(ws)
+    meta, body = memlog.split(first)
+    assert memlog.render(meta, body) == first
+
+
+def test_commas_in_field_survive(ws):
+    init(ws, topic="cars, trains, and planes")
+    append(ws, "z", entry_type="idea")
+    meta, _ = memlog.split(read(ws))
+    assert meta["topic"] == "cars, trains, and planes"
+
+
+def test_triple_dash_in_field_does_not_corrupt_frontmatter(ws):
+    # A `---` inside a value must NOT be read as the closing fence: topic stays intact
+    # and the body never leaks frontmatter text.
+    init(ws, topic="Pricing --- tiers --- and add-ons")
+    append(ws, "an idea", entry_type="idea")
+    meta, body = memlog.split(read(ws))
+    assert meta["topic"] == "Pricing --- tiers --- and add-ons"
+    assert entries(ws) == ["- (idea) an idea"]
+    assert "topic:" not in body  # frontmatter never bled into the body
+
+
+def test_newline_in_field_is_neutralized(ws):
+    # A value carrying a newline can't break the fence on the next round-trip.
+    memlog.main(["init", "--workspace", ws, "--field", "topic=line one\nline two"])
+    append(ws, "x", entry_type="idea")
+    meta, _ = memlog.split(read(ws))
+    assert "\n" not in meta["topic"]
+
+
+def test_append_emits_json_ack(ws, capsys):
+    init(ws)
+    append(ws, "x", entry_type="idea")
+    out = json.loads(capsys.readouterr().out.strip().splitlines()[-1])
+    assert out["ok"] is True
+    assert out["entries"] == 1
+    assert out["memlog"].endswith(MEMLOG)
+    assert "status" not in out  # no lifecycle status
+    assert "section" not in out  # sections are gone
+
+
+def test_ack_entry_count_climbs(ws, capsys):
+    init(ws)
+    append(ws, "a")
+    append(ws, "b")
+    out = json.loads(capsys.readouterr().out.strip().splitlines()[-1])
+    assert out["entries"] == 2

test/test-installation-components.js

@@ -3274,9 +3274,311 @@ async function runTests() {
   console.log('');
 
   // ============================================================
-  // Test Suite 45: New module system (plugin.json#bmad) in the installer
+  // Test Suite 45: _cleanupSkillDirs prunes empty parent dirs (#empty-bmm-folders)
   // ============================================================
-  console.log(`${colors.yellow}Test Suite 45: New module system + legacy detection in custom-module install${colors.reset}\n`);
+  console.log(`${colors.yellow}Test Suite 45: cleanup prunes empty skill-group dirs${colors.reset}\n`);
+
+  let root45;
+  try {
+    root45 = await fs.mkdtemp(path.join(os.tmpdir(), 'bmad-cleanup-test-'));
+    const bmadDir45 = path.join(root45, '_bmad');
+    await fs.ensureDir(path.join(bmadDir45, '_config'));
+
+    // Two skills nested under the same grouping dir (1-analysis), plus a
+    // module-level file that must survive the cleanup.
+    await fs.writeFile(
+      path.join(bmadDir45, '_config', 'skill-manifest.csv'),
+      [
+        'canonicalId,name,description,module,path',
+        '"bmad-agent-analyst","bmad-agent-analyst","fixture","bmm","_bmad/bmm/1-analysis/bmad-agent-analyst/SKILL.md"',
+        '"bmad-research","bmad-research","fixture","bmm","_bmad/bmm/1-analysis/research/bmad-research/SKILL.md"',
+        '',
+      ].join('\n'),
+    );
+    await fs.ensureDir(path.join(bmadDir45, 'bmm', '1-analysis', 'bmad-agent-analyst'));
+    await fs.writeFile(path.join(bmadDir45, 'bmm', '1-analysis', 'bmad-agent-analyst', 'SKILL.md'), 'x');
+    await fs.ensureDir(path.join(bmadDir45, 'bmm', '1-analysis', 'research', 'bmad-research'));
+    await fs.writeFile(path.join(bmadDir45, 'bmm', '1-analysis', 'research', 'bmad-research', 'SKILL.md'), 'x');
+    await fs.writeFile(path.join(bmadDir45, 'bmm', 'config.yaml'), 'module: bmm\n');
+
+    const installer45 = new Installer();
+    await installer45._cleanupSkillDirs(bmadDir45);
+
+    assert(!(await fs.pathExists(path.join(bmadDir45, 'bmm', '1-analysis'))), 'empty skill-group dir is pruned after cleanup');
+    assert(!(await fs.pathExists(path.join(bmadDir45, 'bmm', '1-analysis', 'research'))), 'empty nested skill-group dir is pruned');
+    assert(await fs.pathExists(path.join(bmadDir45, 'bmm', 'config.yaml')), 'module-level files are preserved');
+    assert(await fs.pathExists(bmadDir45), 'bmad root is never removed');
+  } catch (error) {
+    console.log(`${colors.red}Test Suite 45 setup failed: ${error.message}${colors.reset}`);
+    console.log(error.stack);
+    failed++;
+  } finally {
+    if (root45) await fs.remove(root45).catch(() => {});
+  }
+
+  console.log('');
+
+  // ============================================================
+  // Test Suite 46: Python environment check (version parsing + classification)
+  // ============================================================
+  console.log(`${colors.yellow}Test Suite 46: python-check version parsing and classification${colors.reset}\n`);
+
+  try {
+    const { parsePythonVersion, classifyPython, detectPython } = require('../tools/installer/core/python-check');
+
+    // Version parsing
+    const v312 = parsePythonVersion('Python 3.12.1');
+    assert(v312 && v312.major === 3 && v312.minor === 12 && v312.patch === 1, 'parses "Python 3.12.1"');
+    const v311 = parsePythonVersion('Python 3.11.0\n');
+    assert(v311 && v311.raw === '3.11.0', 'parses with trailing newline');
+    const v2 = parsePythonVersion('\nPython 2.7.18');
+    assert(v2 && v2.major === 2, 'parses Python 2 output (stderr-style)');
+    const noPatch = parsePythonVersion('Python 3.13');
+    assert(noPatch && noPatch.patch === 0, 'missing patch defaults to 0');
+    assert(parsePythonVersion('') === null, 'empty output returns null');
+    assert(parsePythonVersion('command not found: python3') === null, 'non-version output returns null');
+    assert(parsePythonVersion(null) === null, 'null output returns null');
+
+    // Classification against feature requirements
+    assert(classifyPython({ major: 3, minor: 11 }) === 'full', '3.11 is full support (tomllib floor)');
+    assert(classifyPython({ major: 3, minor: 13 }) === 'full', '3.13 is full support');
+    assert(classifyPython({ major: 4, minor: 0 }) === 'full', 'hypothetical 4.0 is full support');
+    assert(classifyPython({ major: 3, minor: 10 }) === 'partial', '3.10 is partial (memlog yes, tomllib no)');
+    assert(classifyPython({ major: 3, minor: 8 }) === 'partial', '3.8 is partial (memlog floor)');
+    assert(classifyPython({ major: 3, minor: 7 }) === 'unsupported', '3.7 is unsupported');
+    assert(classifyPython({ major: 2, minor: 7 }) === 'unsupported', '2.7 is unsupported');
+    assert(classifyPython(null) === 'none', 'no python is none');
+
+    // Detection smoke test — must not throw, and if it finds a Python the
+    // result must be well-formed. (CI machines may or may not have Python.)
+    const detected = detectPython();
+    assert(
+      detected === null ||
+        (typeof detected.command === 'string' &&
+          typeof detected.version.raw === 'string' &&
+          typeof detected.isRuntimeCommand === 'boolean'),
+      'detectPython returns null or a well-formed result',
+    );
+
+    // checkPythonEnvironment branch coverage — stub detection, prompts, and
+    // process.exit so the assertions are deterministic regardless of the
+    // machine's Python. python-check resolves detectPython via module.exports
+    // and prompts via the shared module object, so swapping properties works.
+    const pythonCheck = require('../tools/installer/core/python-check');
+    const promptsModule = require('../tools/installer/prompts');
+    const real = {
+      detectPython: pythonCheck.detectPython,
+      log: promptsModule.log,
+      note: promptsModule.note,
+      select: promptsModule.select,
+      cancel: promptsModule.cancel,
+      exit: process.exit,
+    };
+    const stub = (detectResult, selectAnswer) => {
+      const seen = { success: [], warn: [], info: [], note: [], select: [], cancel: [], exit: [] };
+      pythonCheck.detectPython = () => detectResult;
+      promptsModule.log = {
+        success: async (m) => void seen.success.push(m),
+        warn: async (m) => void seen.warn.push(m),
+        info: async (m) => void seen.info.push(m),
+        error: async () => {},
+      };
+      promptsModule.note = async (m, t) => void seen.note.push(t || m);
+      promptsModule.select = async (opts) => {
+        seen.select.push(opts.message);
+        return selectAnswer;
+      };
+      promptsModule.cancel = async (m) => void seen.cancel.push(m);
+      process.exit = (code) => {
+        seen.exit.push(code);
+        throw new Error('__stub_exit__');
+      };
+      return seen;
+    };
+
+    try {
+      const v = (major, minor, patch) => ({ major, minor, patch, raw: `${major}.${minor}.${patch}` });
+
+      // Branch: full support via the runtime command — success, no prompt.
+      let seen = stub({ command: 'python3', version: v(3, 12, 1), isRuntimeCommand: true }, 'continue');
+      let result = await pythonCheck.checkPythonEnvironment();
+      assert(result.status === 'full' && seen.success.length === 1, 'full support via python3 logs success');
+      assert(seen.select.length === 0 && seen.warn.length === 0, 'full support via python3 skips warning and ack prompt');
+
+      // Branch: modern Python found, but not as `python3` — runtime mismatch.
+      seen = stub({ command: 'py -3', version: v(3, 12, 0), isRuntimeCommand: false }, 'continue');
+      result = await pythonCheck.checkPythonEnvironment();
+      assert(seen.success.length === 0, 'python3-mismatch never reports full support');
+      assert(
+        seen.warn.length === 1 && seen.warn[0].includes('python3') && seen.warn[0].includes('py -3'),
+        'python3-mismatch warns that scripts invoke python3',
+      );
+      assert(seen.select.length === 1 && result.status === 'full', 'python3-mismatch still requires the ack prompt');
+
+      // Branch: partial support (3.8–3.10) — warn + ack, continue returns.
+      seen = stub({ command: 'python3', version: v(3, 9, 5), isRuntimeCommand: true }, 'continue');
+      result = await pythonCheck.checkPythonEnvironment();
+      assert(
+        result.status === 'partial' && seen.warn.length === 1 && seen.warn[0].includes('3.11+'),
+        'partial support warns about tomllib floor',
+      );
+      assert(seen.select.length === 1 && seen.exit.length === 0, 'partial support prompts and continue proceeds');
+
+      // Branch: no Python, non-interactive — warn + info, never prompts.
+      seen = stub(null, 'continue');
+      result = await pythonCheck.checkPythonEnvironment({ nonInteractive: true });
+      assert(result.status === 'none' && seen.warn[0].includes('No Python found'), 'non-interactive with no Python warns');
+      assert(seen.select.length === 0 && seen.info.length === 1, 'non-interactive skips the ack prompt and logs continuation');
+
+      // Branch: no Python, interactive, user quits — cancel message + exit 0.
+      seen = stub(null, 'quit');
+      let threw = false;
+      try {
+        await pythonCheck.checkPythonEnvironment();
+      } catch (error) {
+        threw = error.message === '__stub_exit__';
+      }
+      assert(threw && seen.exit.length === 1 && seen.exit[0] === 0, 'quit choice exits 0 (user-cancel convention)');
+      assert(seen.cancel.length === 1, 'quit choice shows the cancel guidance');
+    } finally {
+      pythonCheck.detectPython = real.detectPython;
+      promptsModule.log = real.log;
+      promptsModule.note = real.note;
+      promptsModule.select = real.select;
+      promptsModule.cancel = real.cancel;
+      process.exit = real.exit;
+    }
+  } catch (error) {
+    console.log(`${colors.red}Test Suite 46 setup failed: ${error.message}${colors.reset}`);
+    console.log(error.stack);
+    failed++;
+  }
+
+  console.log('');
+
+  // ============================================================
+  // Test Suite 47: WSL shell using Windows Node guard
+  // ============================================================
+  console.log(`${colors.yellow}Test Suite 47: WSL Windows Node guard${colors.reset}\n`);
+
+  try {
+    const wslNodeCheck = require('../tools/installer/core/wsl-node-check');
+
+    let detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'win32',
+      env: { WSL_DISTRO_NAME: 'Ubuntu-26.04' },
+      cwd: String.raw`C:\Windows`,
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(detection.isMismatch === true, 'detects Windows Node launched from WSL via WSL_DISTRO_NAME');
+
+    detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'win32',
+      env: { PWD: '/home/devuser/projects/md2pdf' },
+      cwd: String.raw`\\wsl.localhost\Ubuntu-26.04\home\devuser\projects\md2pdf`,
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(detection.isMismatch === true, 'detects Windows Node launched from WSL via Linux PWD / WSL UNC cwd');
+
+    detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'win32',
+      env: {},
+      cwd: String.raw`\\wsl$\Ubuntu-26.04\home\devuser\projects\md2pdf`,
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(detection.isMismatch === true, 'detects Windows Node launched from WSL via legacy WSL UNC cwd');
+
+    detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'linux',
+      env: { WSL_DISTRO_NAME: 'Ubuntu-26.04', PWD: '/home/devuser/projects/md2pdf' },
+      cwd: '/home/devuser/projects/md2pdf',
+      execPath: '/usr/bin/node',
+    });
+    assert(detection.isMismatch === false, 'allows native Linux Node inside WSL');
+
+    detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'win32',
+      env: { PWD: String.raw`C:\Users\devuser\project` },
+      cwd: String.raw`C:\Users\devuser\project`,
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(detection.isMismatch === false, 'allows normal Windows Node outside WSL');
+
+    detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'win32',
+      env: { PWD: '/c/Users/devuser/project' },
+      cwd: String.raw`C:\Users\devuser\project`,
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(detection.isMismatch === false, 'allows Git Bash Windows-drive PWD outside WSL');
+
+    detection = wslNodeCheck.detectWindowsNodeFromWsl({
+      platform: 'win32',
+      env: { PWD: '/cygdrive/c/Users/devuser/project' },
+      cwd: String.raw`C:\Users\devuser\project`,
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(detection.isMismatch === false, 'allows Cygwin Windows-drive PWD outside WSL');
+
+    const message = wslNodeCheck.formatWindowsNodeFromWslMessage({
+      isMismatch: true,
+      reason: 'WSL_DISTRO_NAME is set',
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    assert(message.includes('Install Node.js inside WSL'), 'guard message tells user to install Node.js inside WSL');
+    assert(message.includes(String.raw`C:\Program Files\nodejs\node.exe`), 'guard message includes detected Windows Node path');
+
+    const promptsModule = require('../tools/installer/prompts');
+    const real = {
+      detectWindowsNodeFromWsl: wslNodeCheck.detectWindowsNodeFromWsl,
+      log: promptsModule.log,
+      exit: process.exit,
+    };
+    const seen = { errors: [], exit: [] };
+    wslNodeCheck.detectWindowsNodeFromWsl = () => ({
+      isMismatch: true,
+      reason: 'WSL_INTEROP is set',
+      execPath: String.raw`C:\Program Files\nodejs\node.exe`,
+    });
+    promptsModule.log = {
+      error: async (m) => void seen.errors.push(m),
+      info: async () => {},
+      success: async () => {},
+      warn: async () => {},
+      message: async () => {},
+      step: async () => {},
+    };
+    process.exit = (code) => {
+      seen.exit.push(code);
+      throw new Error('__stub_exit__');
+    };
+
+    try {
+      let threw = false;
+      try {
+        await wslNodeCheck.checkWindowsNodeFromWsl();
+      } catch (error) {
+        threw = error.message === '__stub_exit__';
+      }
+      assert(threw && seen.exit[0] === 1, 'guard exits with code 1 when Windows Node is launched from WSL');
+      assert(seen.errors[0].includes('Windows Node.js was launched from a WSL shell'), 'guard logs the mismatch explanation');
+    } finally {
+      wslNodeCheck.detectWindowsNodeFromWsl = real.detectWindowsNodeFromWsl;
+      promptsModule.log = real.log;
+      process.exit = real.exit;
+    }
+  } catch (error) {
+    console.log(`${colors.red}Test Suite 47 setup failed: ${error.message}${colors.reset}`);
+    console.log(error.stack);
+    failed++;
+  }
+
+  console.log('');
+
+  // ============================================================
+  // Test Suite 48: New module system (plugin.json#bmad) in the installer
+  // ============================================================
+  console.log(`${colors.yellow}Test Suite 48: New module system + legacy detection in custom-module install${colors.reset}\n`);
   try {
     const { PluginResolver } = require('../tools/installer/modules/plugin-resolver');
     const { CustomModuleManager } = require('../tools/installer/modules/custom-module-manager');
@@ -3473,7 +3775,7 @@ async function runTests() {
       await fs.remove(tmp).catch(() => {});
     }
   } catch (error) {
-    console.log(`${colors.red}Test Suite 45 setup failed: ${error.message}${colors.reset}`);
+    console.log(`${colors.red}Test Suite 48 setup failed: ${error.message}${colors.reset}`);
     console.log(error.stack);
     failed++;
   }

tools/installer/commands/install.js

@@ -75,6 +75,9 @@ module.exports = {
         return;
       }
 
+      const { checkWindowsNodeFromWsl } = require('../core/wsl-node-check');
+      await checkWindowsNodeFromWsl();
+
       // Set debug flag as environment variable for all components
       if (options.debug) {
         process.env.BMAD_DEBUG_MANIFEST = 'true';

tools/installer/core/ide-sync.js

@@ -83,10 +83,35 @@ async function cleanupBmadSkillDirs(bmadDir) {
     const sourceDir = path.dirname(path.join(bmadDir, relativePath));
     if (await fs.pathExists(sourceDir)) {
       await fs.remove(sourceDir);
+      await removeEmptyParents(path.dirname(sourceDir), bmadDir);
     }
   }
 }
 
+/**
+ * Remove now-empty parent directories left behind after skill dir cleanup.
+ * Walks up from dir, stopping at (and never removing) bmadDir. Best-effort:
+ * a directory that vanishes or fills in mid-walk just ends the walk.
+ * @param {string} dir - Directory to start walking up from
+ * @param {string} bmadDir - BMAD installation directory (boundary)
+ */
+async function removeEmptyParents(dir, bmadDir) {
+  let current = dir;
+  while (true) {
+    // Path-boundary check (not a string prefix, so siblings like _bmad2 don't match).
+    const rel = path.relative(bmadDir, current);
+    if (rel === '' || rel.startsWith('..') || path.isAbsolute(rel)) break;
+    try {
+      const entries = await fs.readdir(current);
+      if (entries.length > 0) break;
+      await fs.rmdir(current);
+    } catch {
+      break;
+    }
+    current = path.dirname(current);
+  }
+}
+
 /**
  * Read the selected IDE platform codes from _config/manifest.yaml.
  * @param {string} bmadDir

tools/installer/core/installer.js

@@ -622,6 +622,7 @@ class Installer {
   /**
    * Sync src/scripts/* → _bmad/scripts/ so shared Python scripts
    * (e.g. resolve_customization.py) are available at install time.
+   * Excludes dev-only tests and Python caches so they don't ship to users.
    * Wipes the destination first so files removed or renamed in source
    * don't linger and get recorded as installed. Also seeds
    * _bmad/custom/.gitignore on fresh installs so *.user.toml overrides
@@ -635,7 +636,12 @@ class Installer {
 
     await fs.remove(paths.scriptsDir);
     await fs.ensureDir(paths.scriptsDir);
-    await fs.copy(srcScriptsDir, paths.scriptsDir, { overwrite: true });
+    // Ship only the runtime scripts — dev-only tests and Python caches must not land in user projects.
+    const isInstallable = (srcPath) => {
+      const base = path.basename(srcPath);
+      return base !== 'tests' && base !== '__pycache__' && base !== '.pytest_cache' && !base.endsWith('.pyc');
+    };
+    await fs.copy(srcScriptsDir, paths.scriptsDir, { overwrite: true, filter: isInstallable });
     await this._trackFilesRecursive(paths.scriptsDir);
 
     const customGitignore = path.join(paths.customDir, '.gitignore');

tools/installer/core/python-check.js

@@ -0,0 +1,199 @@
+const { spawnSync } = require('node:child_process');
+const prompts = require('../prompts');
+
+// Python 3.11 added stdlib `tomllib` (PEP 680), which the shared scripts in
+// src/scripts/ (resolve_config.py, resolve_customization.py) require to read
+// BMAD's TOML config files. memlog.py is more lenient and runs on 3.8+.
+const PYTHON_FULL_SUPPORT = { major: 3, minor: 11 };
+const PYTHON_PARTIAL_SUPPORT = { major: 3, minor: 8 };
+
+// Every runtime call site (skill steps, on_complete hooks) invokes a literal
+// `python3`, so only that command's version vouches for BMAD features. The
+// fallback probes exist to tell the user "Python is installed, but not under
+// the name BMAD uses" instead of a misleading "No Python found".
+const RUNTIME_COMMAND = 'python3';
+const PROBE_CANDIDATES =
+  process.platform === 'win32'
+    ? [
+        { command: 'python3', args: ['--version'] },
+        { command: 'py', args: ['-3', '--version'] },
+        { command: 'python', args: ['--version'] },
+      ]
+    : [
+        { command: 'python3', args: ['--version'] },
+        { command: 'python', args: ['--version'] },
+      ];
+
+/**
+ * Parse a `python --version` output line into version parts.
+ * Python 3 prints to stdout; Python 2 printed to stderr — callers pass both.
+ * @param {string} output - Combined stdout/stderr from `python --version`
+ * @returns {{major: number, minor: number, patch: number, raw: string}|null}
+ */
+function parsePythonVersion(output) {
+  if (!output) return null;
+  const match = output.match(/Python\s+(\d+)\.(\d+)(?:\.(\d+))?/);
+  if (!match) return null;
+  return {
+    major: Number(match[1]),
+    minor: Number(match[2]),
+    patch: Number(match[3] || 0),
+    raw: `${match[1]}.${match[2]}.${match[3] || 0}`,
+  };
+}
+
+/**
+ * Classify a detected Python version against BMAD's feature requirements.
+ * @param {{major: number, minor: number}|null} version
+ * @returns {'full'|'partial'|'unsupported'|'none'}
+ */
+function classifyPython(version) {
+  if (!version) return 'none';
+  const { major, minor } = version;
+  if (major > PYTHON_FULL_SUPPORT.major || (major === PYTHON_FULL_SUPPORT.major && minor >= PYTHON_FULL_SUPPORT.minor)) {
+    return 'full';
+  }
+  if (major === PYTHON_PARTIAL_SUPPORT.major && minor >= PYTHON_PARTIAL_SUPPORT.minor) {
+    return 'partial';
+  }
+  return 'unsupported';
+}
+
+/**
+ * Run one probe candidate and return its parsed version, or null.
+ * @param {{command: string, args: string[]}} candidate
+ * @returns {{major: number, minor: number, patch: number, raw: string}|null}
+ */
+function probeVersion(candidate) {
+  const run = (extra = {}) =>
+    spawnSync(candidate.command, candidate.args, {
+      encoding: 'utf8',
+      timeout: 5000,
+      windowsHide: true,
+      ...extra,
+    });
+  let result = run();
+  // Node >=18.20/20.12 refuses to spawn .bat/.cmd without a shell
+  // (CVE-2024-27980 hardening) and reports EINVAL — pyenv-win ships its
+  // python shims as .bat. Args here are static literals, so a shell retry
+  // is injection-safe.
+  if (result.error && result.error.code === 'EINVAL' && process.platform === 'win32') {
+    result = run({ shell: true });
+  }
+  if (result.error) return null;
+  return parsePythonVersion(`${result.stdout || ''}\n${result.stderr || ''}`);
+}
+
+/**
+ * Probe the local environment for a Python interpreter.
+ * Tries each candidate command and returns the first that reports a version.
+ * `isRuntimeCommand` is true only when the match is `python3` — the command
+ * BMAD scripts actually invoke.
+ * @returns {{command: string, version: {major: number, minor: number, patch: number, raw: string}, isRuntimeCommand: boolean}|null}
+ */
+function detectPython() {
+  for (const candidate of PROBE_CANDIDATES) {
+    try {
+      const version = probeVersion(candidate);
+      if (version) {
+        const display = candidate.args.length > 1 ? `${candidate.command} ${candidate.args.slice(0, -1).join(' ')}` : candidate.command;
+        return { command: display, version, isRuntimeCommand: candidate.command === RUNTIME_COMMAND };
+      }
+    } catch {
+      // Candidate not runnable — try the next one.
+    }
+  }
+  return null;
+}
+
+function upgradeHints() {
+  return [
+    'How to get Python 3.11+ (as `python3`):',
+    '  macOS:        brew install python3',
+    '  Windows:      winget install Python.Python.3.12  (then ensure `python3` resolves, e.g. enable the python3 alias)',
+    '  Linux/WSL:    sudo apt install python3  (Ubuntu 24.04+ ships 3.12; older distros: use pyenv or deadsnakes)',
+    '  Docker:       add python3 to your image (e.g. apk add python3 / apt-get install -y python3)',
+  ].join('\n');
+}
+
+/**
+ * Check the local Python environment and warn about degraded BMAD features.
+ *
+ * Warn-don't-block: most of BMAD works without Python, so the install always
+ * may proceed — but the user must explicitly acknowledge the warning so it
+ * can't scroll past unseen. In non-interactive runs (--yes, or stdin is not
+ * a TTY) the warning is logged and the install continues without a prompt.
+ *
+ * @param {Object} [options]
+ * @param {boolean} [options.nonInteractive=false] - Skip the ack prompt (--yes, or no TTY)
+ * @returns {Promise<{status: string, detected: Object|null}>}
+ */
+async function checkPythonEnvironment({ nonInteractive = false } = {}) {
+  // Called via module.exports so tests can stub detection.
+  const detected = module.exports.detectPython();
+  const status = classifyPython(detected ? detected.version : null);
+
+  if (status === 'full' && detected.isRuntimeCommand) {
+    await prompts.log.success(`Python ${detected.version.raw} detected (${detected.command}) — all BMAD features supported.`);
+    return { status, detected };
+  }
+
+  if (detected && !detected.isRuntimeCommand) {
+    await prompts.log.warn(
+      `Python ${detected.version.raw} found via \`${detected.command}\`, but BMAD scripts invoke \`python3\`, which is not on PATH.\n` +
+        `Python-powered features (memlog session memory, TOML config resolution) won't run until \`python3\` resolves —\n` +
+        `add a python3 alias/shim, or reinstall Python with the python3 launcher enabled.`,
+    );
+  } else if (status === 'partial') {
+    await prompts.log.warn(
+      `Python ${detected.version.raw} detected (${detected.command}) — BMAD's TOML config tools need Python 3.11+ (stdlib tomllib).\n` +
+        `Works: memlog session memory. Won't work: config/customization resolution scripts.`,
+    );
+  } else {
+    const found =
+      status === 'unsupported' ? `Python ${detected.version.raw} detected (${detected.command}) — too old.` : 'No Python found on PATH.';
+    await prompts.log.warn(
+      `${found} BMAD installs fine without it, but Python-powered features\n` +
+        `(memlog session memory, TOML config resolution) won't run until Python 3.11+ is available.`,
+    );
+  }
+  await prompts.note(upgradeHints(), 'Python 3.11+ recommended');
+
+  if (nonInteractive) {
+    await prompts.log.info('Continuing anyway (non-interactive run). You can fix Python later — no reinstall needed.');
+    return { status, detected };
+  }
+
+  const choice = await prompts.select({
+    message: "BMAD's Python-powered features won't work yet. How do you want to proceed?",
+    choices: [
+      {
+        name: 'Continue install',
+        value: 'continue',
+        hint: 'BMAD works without Python — you can fix Python later, no reinstall needed',
+      },
+      {
+        name: 'Quit and fix Python first',
+        value: 'quit',
+        hint: 'make Python 3.11+ available as python3, then re-run the installer',
+      },
+    ],
+    default: 'continue',
+  });
+
+  if (choice === 'quit') {
+    await prompts.cancel('Make Python 3.11+ available as `python3` (see hints above), then re-run the installer.');
+    process.exit(0);
+  }
+
+  return { status, detected };
+}
+
+module.exports = {
+  checkPythonEnvironment,
+  detectPython,
+  parsePythonVersion,
+  classifyPython,
+  PYTHON_FULL_SUPPORT,
+  PYTHON_PARTIAL_SUPPORT,
+};

tools/installer/core/wsl-node-check.js

@@ -0,0 +1,109 @@
+const prompts = require('../prompts');
+
+const WSL_UNC_PATTERN = /^\\\\wsl(?:\.localhost|\$)?\\/i;
+
+function normalizePath(value) {
+  return typeof value === 'string' ? value.replaceAll('/', '\\').toLowerCase() : '';
+}
+
+function isLinuxStylePath(value) {
+  return (
+    typeof value === 'string' &&
+    value.startsWith('/') &&
+    !value.startsWith('//') &&
+    !/^\/[a-z](?:\/|$)/i.test(value) &&
+    !/^\/cygdrive\/[a-z](?:\/|$)/i.test(value)
+  );
+}
+
+function isWslUncPath(value) {
+  return WSL_UNC_PATTERN.test(value || '');
+}
+
+/**
+ * Detect the broken interop case where WSL resolved node/npx to Windows.
+ * @param {Object} [runtime]
+ * @param {string} [runtime.platform]
+ * @param {Object} [runtime.env]
+ * @param {string} [runtime.cwd]
+ * @param {string} [runtime.execPath]
+ * @returns {{isMismatch: boolean, reason: string|null, execPath: string}}
+ */
+function detectWindowsNodeFromWsl(runtime = {}) {
+  const platform = runtime.platform || process.platform;
+  const env = runtime.env || process.env;
+  const cwd = runtime.cwd || safeCwd();
+  const execPath = runtime.execPath || process.execPath || '';
+
+  if (platform !== 'win32') {
+    return { isMismatch: false, reason: null, execPath };
+  }
+
+  if (env.WSL_DISTRO_NAME) {
+    return { isMismatch: true, reason: 'WSL_DISTRO_NAME is set', execPath };
+  }
+
+  if (env.WSL_INTEROP) {
+    return { isMismatch: true, reason: 'WSL_INTEROP is set', execPath };
+  }
+
+  if (isLinuxStylePath(env.PWD)) {
+    return { isMismatch: true, reason: 'PWD is a Linux path', execPath };
+  }
+
+  if (isWslUncPath(cwd)) {
+    return { isMismatch: true, reason: 'current directory is a WSL UNC path', execPath };
+  }
+
+  const normalizedExecPath = normalizePath(execPath);
+  if (normalizedExecPath.includes('\\wsl$\\') || normalizedExecPath.includes('\\wsl.localhost\\')) {
+    return { isMismatch: true, reason: 'Node executable path is under a WSL UNC path', execPath };
+  }
+
+  return { isMismatch: false, reason: null, execPath };
+}
+
+function safeCwd() {
+  try {
+    return process.cwd();
+  } catch {
+    return '';
+  }
+}
+
+function formatWindowsNodeFromWslMessage(detection) {
+  const lines = [
+    'Windows Node.js was launched from a WSL shell.',
+    '',
+    'This usually means Node.js is not installed inside the WSL distro, so WSL resolved `node`/`npx` to Windows.',
+    'The installer cannot safely continue because Linux paths may be interpreted as Windows paths.',
+    '',
+    'Install Node.js inside WSL, then rerun the same command from the WSL terminal.',
+  ];
+
+  if (detection.execPath) {
+    lines.push('', `Detected Node executable: ${detection.execPath}`);
+  }
+
+  if (detection.reason) {
+    lines.push(`Detection signal: ${detection.reason}`);
+  }
+
+  return lines.join('\n');
+}
+
+async function checkWindowsNodeFromWsl() {
+  const detection = module.exports.detectWindowsNodeFromWsl();
+  if (!detection.isMismatch) {
+    return detection;
+  }
+
+  await prompts.log.error(formatWindowsNodeFromWslMessage(detection));
+  process.exit(1);
+}
+
+module.exports = {
+  checkWindowsNodeFromWsl,
+  detectWindowsNodeFromWsl,
+  formatWindowsNodeFromWslMessage,
+};

tools/installer/ui.js

@@ -162,6 +162,16 @@ class UI {
     const messageLoader = new MessageLoader();
     await messageLoader.displayStartMessage();
 
+    // Probe the local Python before any other prompts: several BMAD features
+    // (memlog session memory, TOML config resolution) need Python 3.11+ at
+    // runtime. Warn-don't-block, but require an explicit ack so the warning
+    // can't scroll past unseen. The installer runs in the destination
+    // environment, so probing PATH here tests the right machine.
+    // Skip the ack when stdin isn't a TTY (CI/Docker/piped): clack's select
+    // on closed stdin resolves to cancel, which would silently exit 0.
+    const { checkPythonEnvironment } = require('./core/python-check');
+    await checkPythonEnvironment({ nonInteractive: !!options.yes || !process.stdin.isTTY });
+
     // Parse channel flags (--channel/--all-*/--next=/--pin) once. Warnings
     // are surfaced immediately so the user sees them before any git ops run.
     const channelOptions = parseChannelOptions(options);

website/src/styles/custom.css

@@ -15,7 +15,7 @@
    ============================================ */
 :root {
   --ai-banner-height: 2.75rem;
-  --sl-nav-height: 6.25rem; /* Base nav height (~3.5rem) + banner height (2.75rem) */
+  --sl-nav-height: 9rem; /* Base nav (3.5rem) + two announcement banners (2.75rem each) */
 
   /* Full-width content - override Starlight's default 45rem/67.5rem */
   --sl-content-width: 65rem;