feat(quick-flow): add quick-dev2 experimental skeleton

Unified 5-step workflow with full BMM sharded workflow plumbing
and minimal step prompts. Steps: clarify/route, plan, implement,
review, present. 29 lines of instructions, 145 lines of plumbing.

src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-01-clarify-and-route.md

@@ -0,0 +1,40 @@
+---
+name: 'step-01-clarify-and-route'
+description: 'Capture intent, route to execution path'
+
+wipFile: '{implementation_artifacts}/tech-spec-wip.md'
+---
+
+# Step 1: Clarify and Route
+
+**Step 1 of 5**
+
+## RULES
+
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+- The skill argument IS the intent — not a hint.
+- Do NOT assume you start from zero.
+
+## CONTEXT
+
+- `ready-for-dev` spec in `{implementation_artifacts}`? → Confirm, skip to step 3.
+- `{wipFile}` exists? → Offer resume or archive.
+
+---
+
+## INSTRUCTIONS
+
+1. Clarify intent until: problem unambiguous, scope clear, no contradictions, you can explain back what you'll do.
+2. Backfill VC conventions to project-context if unknown.
+3. Route:
+   - **One-shot** — trivial (~3 files). `{execution_mode}` = "one-shot". → Step 3.
+   - **Plan-code-review** — normal. → Step 2.
+   - **Full BMM** — too big. Recommend and exit.
+   - Ambiguous? Default plan-code-review.
+
+---
+
+## NEXT
+
+- One-shot / ready-for-dev: `{installed_path}/steps/step-03-implement.md`
+- Plan-code-review: `{installed_path}/steps/step-02-plan.md`

src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-02-plan.md

@@ -0,0 +1,38 @@
+---
+name: 'step-02-plan'
+description: 'Investigate, generate spec, present for approval'
+
+wipFile: '{implementation_artifacts}/tech-spec-wip.md'
+templateFile: '{installed_path}/tech-spec-template.md'
+---
+
+# Step 2: Plan
+
+**Step 2 of 5 — Autonomous until checkpoint**
+
+## RULES
+
+- No intermediate approvals.
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+
+---
+
+## INSTRUCTIONS
+
+1. Investigate codebase.
+2. Generate spec from `{templateFile}` → `{wipFile}`.
+3. Self-review against READY FOR DEVELOPMENT standard.
+
+### CHECKPOINT 1
+
+Present summary. `[A] Approve  [E] Edit  [F] Full BMM`. HALT.
+
+- **A**: Rename to `tech-spec-{slug}.md`, status `ready-for-dev`, freeze Problem/Solution/Scope/Non-Goals/Golden Examples. → Step 3.
+- **E**: Apply changes, re-present.
+- **F**: Exit to full BMM.
+
+---
+
+## NEXT
+
+`{installed_path}/steps/step-03-implement.md`

src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-03-implement.md

@@ -0,0 +1,36 @@
+---
+name: 'step-03-implement'
+description: 'Branch, shard tasks, execute, commit. Local only.'
+
+tasksDir: '{implementation_artifacts}/tasks'
+sequenceFile: '{implementation_artifacts}/tasks/sequence.md'
+---
+
+# Step 3: Implement
+
+**Step 3 of 5 — Autonomous. Local only.**
+
+## RULES
+
+- No push. No remote ops.
+- Sequential execution only.
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+
+---
+
+## INSTRUCTIONS
+
+1. Baseline commit. Branch. Assert clean tree.
+2. Shard spec tasks → `{tasksDir}/task-NN.md`. Track in `{sequenceFile}`.
+3. Execute sequentially: read task fresh → implement → verify AC → mark complete → next.
+4. Self-check. Commit.
+
+One-shot: skip sharding, work from mental plan.
+
+Halt after 3 failures on same task, or blocking ambiguity.
+
+---
+
+## NEXT
+
+`{installed_path}/steps/step-04-review.md`

src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-04-review.md

@@ -0,0 +1,31 @@
+---
+name: 'step-04-review'
+description: 'Adversarial review, classify findings, optional spec loop'
+
+adversarial_review_task: '{project-root}/_bmad/core/tasks/review-adversarial-general.xml'
+specLoopCap: 5
+---
+
+# Step 4: Review
+
+**Step 4 of 5 — Autonomous**
+
+## RULES
+
+- Review subagents get NO conversation context.
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+
+---
+
+## INSTRUCTIONS
+
+1. Diff from `{baseline_commit}`. Review in context-free subagents: intent audit (skip for one-shot) + adversarial code review via `{adversarial_review_task}`.
+2. Classify findings: intent > spec > patch > defer > reject.
+3. Spec-class? Amend spec, re-derive, re-review. Max `{specLoopCap}` iterations.
+4. Auto-fix patches. Commit.
+
+---
+
+## NEXT
+
+`{installed_path}/steps/step-05-present.md`

src/bmm/workflows/bmad-quick-flow/quick-dev2/steps/step-05-present.md

@@ -0,0 +1,29 @@
+---
+name: 'step-05-present'
+description: 'Present findings, get approval, create PR'
+---
+
+# Step 5: Present
+
+**Step 5 of 5 — Final**
+
+## RULES
+
+- NEVER auto-push.
+- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+
+---
+
+## INSTRUCTIONS
+
+Present classified findings. `[A] Approve  [E] Edit  [R] Reject`. HALT.
+
+- **A**: Commit patches. Print push command. Wait. Create PR.
+- **E**: Apply changes, re-present.
+- **R**: Route back.
+
+---
+
+## NEXT
+
+Workflow complete.

src/bmm/workflows/bmad-quick-flow/quick-dev2/tech-spec-template.md

@@ -0,0 +1,50 @@
+---
+title: '{title}'
+slug: '{slug}'
+created: '{date}'
+status: 'in-progress'
+---
+
+# {title}
+
+## Problem
+
+{problem}
+
+## Solution
+
+{solution}
+
+## Scope
+
+**In:** {in_scope}
+
+**Out:** {out_of_scope}
+
+## Non-Goals
+
+{non_goals}
+
+## Tasks
+
+- [ ] Task 1: `{file}` -- {action} -- {rationale}
+
+## Acceptance Criteria
+
+- [ ] AC 1: Given {precondition}, when {action}, then {expected_result}
+
+## Technical Decisions
+
+{technical_decisions}
+
+## Golden Examples
+
+{golden_examples}
+
+## Spec Change Log
+
+<!-- Appended by the review loop. Each entry: what changed, what triggered it, what bad state it avoids, KEEP instructions. Empty until step 4. -->
+
+## Notes
+
+{notes}

src/bmm/workflows/bmad-quick-flow/quick-dev2/workflow.md

@@ -0,0 +1,84 @@
+---
+name: quick-dev2
+description: 'Unified quick flow - clarify intent, plan, implement, review, present.'
+main_config: '{project-root}/_bmad/bmm/config.yaml'
+
+# Related workflows
+advanced_elicitation: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml'
+party_mode_exec: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+
+# Review building block
+adversarial_review_task: '{project-root}/_bmad/core/tasks/review-adversarial-general.xml'
+---
+
+# Quick Dev 2 Workflow
+
+**Goal:** Take a user request from intent through implementation, adversarial review, and PR creation in a single unified flow.
+
+**Your Role:** You are an elite developer. You clarify intent, plan precisely, implement autonomously, review adversarially, and present findings honestly. Minimum ceremony, maximum signal.
+
+---
+
+## READY FOR DEVELOPMENT STANDARD
+
+A specification is "Ready for Development" when:
+
+- **Actionable**: Every task has a file path and specific action.
+- **Logical**: Tasks ordered by dependency.
+- **Testable**: All ACs use Given/When/Then.
+- **Complete**: No placeholders or TBDs.
+- **Self-Contained**: A fresh agent can implement from the spec alone.
+
+---
+
+## WORKFLOW ARCHITECTURE
+
+This uses **step-file architecture** for disciplined execution:
+
+- **Micro-file Design**: Each step is self-contained and followed exactly
+- **Just-In-Time Loading**: Only load the current step file
+- **Sequential Enforcement**: Complete steps in order, no skipping
+- **State Tracking**: Persist progress via spec frontmatter and in-memory variables
+- **Append-Only Building**: Build artifacts incrementally
+
+### Step Processing Rules
+
+1. **READ COMPLETELY**: Read the entire step file before acting
+2. **FOLLOW SEQUENCE**: Execute sections in order
+3. **WAIT FOR INPUT**: Halt at checkpoints and wait for human
+4. **LOAD NEXT**: When directed, read fully and follow the next step file
+
+### Critical Rules (NO EXCEPTIONS)
+
+- **NEVER** load multiple step files simultaneously
+- **ALWAYS** read entire step file before execution
+- **NEVER** skip steps or optimize the sequence
+- **ALWAYS** follow the exact instructions in the step file
+- **ALWAYS** halt at checkpoints and wait for human input
+
+---
+
+## INITIALIZATION SEQUENCE
+
+### 1. Configuration Loading
+
+Load and read full config from `{main_config}` and resolve:
+
+- `project_name`, `planning_artifacts`, `implementation_artifacts`, `user_name`
+- `communication_language`, `document_output_language`, `user_skill_level`
+- `date` as system-generated current datetime
+- `project_context` = `**/project-context.md` (load if exists)
+- CLAUDE.md / memory files (load if exist)
+
+YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`.
+
+### 2. Paths
+
+- `installed_path` = `{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-dev2`
+- `templateFile` = `{installed_path}/tech-spec-template.md`
+- `wipFile` = `{implementation_artifacts}/tech-spec-wip.md`
+- `tasksDir` = `{implementation_artifacts}/tasks`
+
+### 3. First Step Execution
+
+Read fully and follow: `{installed_path}/steps/step-01-clarify-and-route.md` to begin the workflow.