Merge 12e0840c62 into 355ccebca2

workflow-status can call workflow init
BMad Agents menu items are logically ordered and marked with optional or recommended and some required tags
2025-11-27 17:44:02 -05:00 · 2025-11-26 19:48:47 -06:00 · 2025-11-26 18:22:24 -06:00 · 2025-11-26 17:46:26 -06:00 · 2025-11-26 17:07:09 -06:00 · 2025-11-26 16:47:15 -06:00
24 changed files with 2231 additions and 1931 deletions
--- a/docs/agent-preflight-protocol.md
+++ b/docs/agent-preflight-protocol.md
@ -0,0 +1,383 @@
+# BMad Method PR #2: Agent Task Pre-Flight Protocol
+
+**Feature Type**: Safety & quality framework
+**Status**: Draft for community review
+**Origin**: tellingCube project learnings (masemIT e.U.)
+**Author**: Mario Semper (@sempre)
+**Date**: 2025-11-23
+
+---
+
+## Summary
+
+**Agent Task Pre-Flight Protocol** establishes mandatory safety checks for high-risk agent tasks (marketing, legal, deployment) to prevent factual errors, trademark violations, privacy breaches, and assumption-based mistakes.
+
+---
+
+## Problem Statement
+
+### Real-World Failure Case
+
+**Scenario**: Marketing agent (Sophie) created LinkedIn launch posts for tellingCube without:
+- Reading existing project documentation
+- Verifying pricing against actual implementation
+- Checking trademark compliance rules
+- Reviewing privacy guidelines
+
+**Result**: Multiple critical errors:
+- ❌ Mentioned user's day job title (privacy/legal risk)
+- ❌ Used family member's name (privacy violation)
+- ❌ Claimed "60 seconds" generation time (factually wrong)
+- ❌ Advertised "€9/month" pricing (doesn't exist - actual: €29-€999 ONE-TIME)
+- ❌ Used "IBCS-compliant" (trademark violation - should be "inspired by IBCS©")
+
+**Root Cause**: Agent operated independently without pre-task verification protocol.
+
+---
+
+## Current BMad Behavior (Risky)
+
+```yaml
+User: "Sophie, create LinkedIn launch posts"
+
+Sophie:
+  1. Generates content based on general knowledge
+  2. Makes assumptions about features/pricing
+  3. Uses marketing best practices
+  4. Presents to user
+
+❌ Problem: No verification step before creation
+```
+
+---
+
+## Proposed Solution: Pre-Flight Protocol
+
+### Mandatory Checks Before High-Risk Tasks
+
+```yaml
+Agent Task Pre-Flight Protocol:
+
+BEFORE executing tasks with external impact:
+  1. Discover Critical Context
+     - Search for CRITICAL-GUIDELINES.md or similar
+     - Read recent related work in project
+     - Check actual implementation (code, configs, not assumptions)
+
+  2. Verify Assumptions
+     - Pricing: Read Stripe config / pricing components
+     - Features: Grep codebase for actual capabilities
+     - Legal/Trademark: Check documented compliance rules
+     - Privacy: Verify no personal info in public content
+
+  3. Cross-Agent Review (for high-risk outputs)
+     - Orchestrator reviews before user sees
+     - Fact-checker agent validates claims
+     - Minimum 2 agents verify before publishing
+
+  4. User Approval Gate
+     - Present content as DRAFT
+     - Highlight assumptions made
+     - Get explicit approval before finalizing
+```
+
+---
+
+## High-Risk Task Categories
+
+### 1. Marketing & Public Content
+**Examples**: LinkedIn posts, press releases, demo videos, website copy
+
+**Pre-Flight Required**:
+- [ ] Read `CRITICAL-GUIDELINES.md` (legal, trademark, privacy rules)
+- [ ] Verify pricing from actual Stripe/payment config
+- [ ] Verify features from actual codebase (not roadmap ideas)
+- [ ] Check trademark compliance (e.g., "IBCS©" usage rules)
+- [ ] Privacy review (no personal identifiers without consent)
+- [ ] Cross-agent fact-check before presenting to user
+
+### 2. Legal & Compliance
+**Examples**: Terms of service, privacy policy, license agreements
+
+**Pre-Flight Required**:
+- [ ] Read existing legal docs (don't start from scratch)
+- [ ] Check jurisdiction-specific requirements
+- [ ] Verify against actual product behavior (data handling, cookies, etc.)
+- [ ] Legal expert review (human or specialized agent)
+- [ ] User final approval required
+
+### 3. Deployment & Infrastructure
+**Examples**: Database migrations, production deployments, DNS changes
+
+**Pre-Flight Required**:
+- [ ] Read deployment runbooks/checklists
+- [ ] Verify current production state
+- [ ] Check for breaking changes
+- [ ] Backup strategy confirmed
+- [ ] Rollback plan documented
+- [ ] User explicit approval with understanding of risks
+
+### 4. Financial & Billing
+**Examples**: Stripe configuration, pricing changes, refund policies
+
+**Pre-Flight Required**:
+- [ ] Read current Stripe dashboard state
+- [ ] Verify tax/legal implications
+- [ ] Check grandfather clause impacts
+- [ ] Financial impact assessment
+- [ ] User approval with revenue projections
+
+---
+
+## Implementation Guidelines
+
+### For Agent Developers
+
+**In agent YAML definition**:
+
+```yaml
+agent:
+  name: Sophie
+  id: marketing
+  high_risk_tasks: true  # Triggers pre-flight protocol
+
+pre_flight:
+  required_reads:
+    - docs/marketing/CRITICAL-GUIDELINES.md
+    - components/landing/PricingSection.tsx
+    - docs/_masemIT/readme.md
+
+  verification_steps:
+    - Grep for actual pricing tiers in codebase
+    - Check trademark compliance rules
+    - Privacy scan (no personal names/details)
+
+  cross_check:
+    agents: [river, mary]
+    approval_required: true
+
+tasks:
+  create-linkedin-post:
+    pre_flight_mandatory: true
+    approval_gate: user
+```
+
+### For Orchestrators (River-like agents)
+
+**Orchestrator responsibilities**:
+
+```python
+def execute_high_risk_task(agent, task, user_request):
+    # Step 1: Pre-flight checks
+    critical_docs = discover_critical_guidelines()
+    agent.read(critical_docs)
+
+    # Step 2: Agent executes with verification
+    draft_output = agent.execute_task(task)
+
+    # Step 3: Cross-agent review
+    fact_check_agent = get_agent("mary")
+    verification = fact_check_agent.verify(draft_output, codebase)
+
+    # Step 4: Present as DRAFT to user
+    if verification.has_issues:
+        present_issues_to_user(verification.issues)
+
+    present_as_draft(draft_output)
+
+    # Step 5: User approval gate
+    approval = get_user_approval()
+
+    if approval:
+        finalize(draft_output)
+```
+
+---
+
+## Example: Correct Marketing Flow
+
+### Before (Risky)
+
+```
+User: "Create LinkedIn launch posts"
+Sophie: [Generates 3 posts with assumptions]
+Sophie: "Here are your posts!"
+
+❌ Contains errors user must catch
+```
+
+### After (Safe)
+
+```
+User: "Create LinkedIn launch posts"
+
+River: "Sophie, this is a high-risk task. Running pre-flight..."
+
+Sophie:
+  ✅ Read CRITICAL-GUIDELINES.md
+  ✅ Read PricingSection.tsx (actual pricing: €29-€999)
+  ✅ Checked IBCS© compliance rules (must say "inspired by")
+  ✅ Privacy check (no "Product Owner", no "brother")
+
+Sophie: [Generates 3 posts with verified facts]
+
+River: "Mary, fact-check Sophie's output..."
+
+Mary:
+  ✅ Pricing correct (€29-€999 lifetime)
+  ✅ No trademark violations ("inspired by IBCS©")
+  ✅ No privacy issues
+  ✅ Generation time accurate ("minutes")
+
+River: "Sempre, here's the DRAFT (pre-flight verified). Approve?"
+
+User: [Reviews, approves]
+
+✅ No errors, factually accurate
+```
+
+---
+
+## Critical Guidelines Template
+
+**Every project should have**: `docs/PROJECT-NAME/CRITICAL-GUIDELINES.md`
+
+```markdown
+# CRITICAL Guidelines for [Project Name]
+
+## ❌ NEVER MENTION
+- Confidential info (list specific items)
+- Personal details (family, private life)
+- Competitor names (if under NDA)
+
+## ✅ ALWAYS VERIFY
+- Pricing: Check [file path]
+- Features: Grep [codebase location]
+- Legal: Comply with [trademark/license rules]
+
+## Trademark Compliance
+- "IBCS©" → Always say "inspired by IBCS©" (not "compliant")
+- [Other trademarks...]
+
+## Privacy Rules
+- No personal job titles in public content
+- No family member names
+- [Other privacy rules...]
+
+## Approval Requirements
+- Marketing content: River + Mary review
+- Legal docs: Legal expert review
+- Deployment: User explicit approval
+```
+
+---
+
+## Benefits
+
+✅ **Prevents costly mistakes** - Catches errors before they're public
+✅ **Protects legal compliance** - Trademark, privacy, licensing
+✅ **Ensures factual accuracy** - Features/pricing match reality
+✅ **Builds user trust** - Agents don't hallucinate facts
+✅ **Scalable safety** - Works across all BMad projects
+
+---
+
+## Tradeoffs & Considerations
+
+### Slower Task Execution
+- **Before**: Agent outputs in 30 seconds
+- **After**: Pre-flight adds 1-2 minutes
+- **Worth it?**: YES for high-risk tasks (marketing, legal, deployment)
+
+### More Agent Coordination
+- Requires orchestrator (River) to manage pre-flight
+- Cross-agent reviews add complexity
+- **Mitigation**: Only for high-risk tasks, not every task
+
+### User Approval Friction
+- Adds approval gate before finalization
+- **Mitigation**: Present as DRAFT with verification status
+- User can fast-track if comfortable
+
+---
+
+## Rollout Strategy
+
+### Phase 1: Opt-In (Recommended)
+- Projects mark agents as `high_risk_tasks: true`
+- Orchestrators enforce pre-flight for marked agents
+- Community feedback on friction/benefits
+
+### Phase 2: Default for Risky Categories
+- Marketing, legal, deployment agents default to pre-flight
+- Other agents opt-in if needed
+
+### Phase 3: Configurable Per-Task
+- Users set risk level per task
+- `*create-post --risk high` triggers pre-flight
+- `*create-post --risk low` skips for drafts
+
+---
+
+## Real-World Validation
+
+**Origin Project**: tellingCube (masemIT e.U.)
+
+**Failure Scenario**:
+- Marketing agent created launch posts without verification
+- 5 critical errors caught by user (should have been caught earlier)
+- 30 minutes of rework to fix
+
+**After Implementing Protocol**:
+- CRITICAL-GUIDELINES.md created
+- Pre-flight checklist enforced
+- Cross-agent review (River → Sophie → Mary → User)
+- **Result**: Zero errors in final content
+
+**User Feedback (Mario Semper)**:
+> "I love BMad, but I don't want to repeat the ChatGPT hallucination nightmare. This protocol gives me confidence that agents verify facts before presenting them."
+
+---
+
+## Open Questions for Community
+
+1. **Scope**: Which task types should default to pre-flight?
+2. **Performance**: Is 1-2 minute overhead acceptable for high-risk tasks?
+3. **Configurability**: Per-project, per-agent, or per-task risk settings?
+4. **Tooling**: Should pre-flight be a separate tool or built into agent execution?
+5. **Enforcement**: Optional best practice or mandatory for certain agents?
+
+---
+
+## Next Steps
+
+1. **Community feedback** on protocol design
+2. **Reference implementation** in BMad core
+3. **Agent template updates** to include pre-flight hooks
+4. **Documentation** with examples for common scenarios
+5. **Testing** across different project types
+
+---
+
+## Comparison to Similar Patterns
+
+| Pattern | Focus | When to Use |
+|---------|-------|-------------|
+| **Pre-Flight Protocol** | Safety & accuracy | High-risk external outputs |
+| **Code Review** | Code quality | Before merging code |
+| **QA Gates** | Testing | Before production deployment |
+| **Approval Workflows** | Governance | Multi-stakeholder decisions |
+
+**Pre-Flight Protocol** = "Code review + QA gate" for **agent outputs**.
+
+---
+
+## References
+
+- **Source Project**: tellingCube (https://github.com/masemIT/telling-cube) [if public]
+- **Failure Case**: `docs/bmad-contributions/` (this document)
+- **Implementation**: `docs/marketing/CRITICAL-GUIDELINES.md` (tellingCube)
+
+---
+
+**Contribution ready for review.** This came from painful real-world experience - let's make BMad safer for everyone! 🛡️
--- a/docs/ring-of-fire-sessions.md
+++ b/docs/ring-of-fire-sessions.md
@ -0,0 +1,256 @@
+# BMad Method PR #1: Ring of Fire (ROF) Sessions
+
+**Feature Type**: Core workflow enhancement
+**Status**: Draft for community review
+**Origin**: tellingCube project (masemIT e.U.)
+**Author**: Mario Semper (@sempre)
+**Date**: 2025-11-23
+
+---
+
+## Summary
+
+**Ring of Fire (ROF) Sessions** enable multi-agent collaborative sessions that run in parallel to the user's main workflow, allowing users to delegate complex multi-perspective analysis while continuing other work.
+
+---
+
+## Problem Statement
+
+Current BMad Method requires **sequential agent interaction**. When users need multiple agents to collaborate on a complex topic, they must:
+- Manually orchestrate each agent conversation
+- Stay in the loop for every exchange
+- Wait for sequential responses before proceeding
+- Context-switch constantly between tasks
+
+This creates **bottlenecks** and prevents **parallel work streams**.
+
+---
+
+## Proposed Solution: Ring of Fire Sessions
+
+A new command pattern that enables **scoped multi-agent collaboration sessions** that run while the user continues other work.
+
+### Command Syntax
+
+```bash
+*rof "<topic>" --agents <agent-list> [--report brief|detailed|live]
+```
+
+### Example Usage
+
+```bash
+*rof "API Refactoring Strategy" --agents dev,architect,qa --report brief
+```
+
+**What happens**:
+1. Dev, Architect, and QA agents enter a collaborative session
+2. They analyze the topic together (code review, design discussion, testing concerns)
+3. When agents need tool access (read files, run commands), they request user approval
+4. User continues working on other tasks in parallel
+5. Session ends with consolidated report (brief: just recommendations, detailed: full transcript)
+
+---
+
+## Key Features
+
+### 1. User-Controlled Scope
+- **Small**: 2 agents, 5-minute quick discussion
+- **Large**: 10 agents, 2-hour deep analysis
+- User decides granularity based on complexity
+
+### 2. Approval-Gated Tool Access
+- Agents can **discuss** freely within the session
+- When agents need **tools** (read files, execute commands, make changes), they:
+  - Pause the session
+  - Request user approval
+  - Resume after user decision
+
+**Why**: Maintains user control, prevents runaway agent actions
+
+### 3. Flexible Reporting
+
+| Mode | Description | Use Case |
+|------|-------------|----------|
+| `brief` | Final recommendations only | "Just tell me what to do" |
+| `detailed` | Full transcript + recommendations | "Show me the reasoning" |
+| `live` | Real-time updates as agents discuss | "I want to observe" |
+
+**Default**: `brief` with Q&A available
+
+### 4. Parallel Workflows
+- User works on **Task A** while ROF session tackles **Task B**
+- No context-switching overhead
+- Efficient use of time
+
+---
+
+## Use Cases
+
+### 1. Architecture Reviews
+```bash
+*rof "Evaluate microservices vs monolith for new feature" --agents architect,dev,qa
+```
+**Agents collaborate on**: Design trade-offs, implementation complexity, testing implications
+
+### 2. Code Refactoring
+```bash
+*rof "Refactor authentication module" --agents dev,architect --report detailed
+```
+**Agents collaborate on**: Current code analysis, refactoring approach, migration strategy
+
+### 3. Feature Planning
+```bash
+*rof "Plan user notifications feature" --agents pm,ux,dev --report brief
+```
+**Agents collaborate on**: Requirements, UX flow, technical feasibility, timeline
+
+### 4. Quality Gates
+```bash
+*rof "Investigate test failures in CI/CD" --agents qa,dev --report live
+```
+**Agents collaborate on**: Root cause analysis, fix recommendations, regression prevention
+
+### 5. Documentation Sprints
+```bash
+*rof "Document API endpoints" --agents dev,pm,ux
+```
+**Agents collaborate on**: Technical accuracy, user-friendly examples, completeness
+
+---
+
+## User Experience Flow
+
+```mermaid
+sequenceDiagram
+    User->>River: *rof "Topic" --agents dev,architect
+    River->>Dev: Join ROF session
+    River->>Architect: Join ROF session
+    River->>User: Session started, continue your work
+
+    Dev->>Architect: Discuss approach
+    Architect->>Dev: Suggest alternatives
+
+    Dev->>User: Need to read auth.ts - approve?
+    User->>Dev: Approved
+    Dev->>Architect: After reading file...
+
+    Architect->>Dev: Recommendation
+    Dev->>River: Session complete
+    River->>User: Brief report: [Recommendations]
+```
+
+---
+
+## Implementation Considerations
+
+### Technical Requirements
+- **Session state management**: Track active ROF sessions, participating agents
+- **Agent context sharing**: Agents share knowledge within session scope
+- **User approval workflow**: Clear prompt for tool requests
+- **Report generation**: Brief/detailed/live output formatting
+- **Workflow integration**: Link ROF findings to existing workflow plans/todos
+
+### Open Questions for Community
+
+1. **Integration**: Core BMad feature or plugin/extension?
+2. **Concurrency**: How to handle file conflicts if multiple agents want to edit?
+3. **Cost Model**: Guidance for LLM call budgeting with multiple agents?
+4. **Session Limits**: Recommended max agents/duration?
+5. **Agent Communication**: Free-form discussion or structured turn-taking?
+
+---
+
+## Real-World Validation
+
+**Origin Project**: tellingCube (BI dashboard, masemIT e.U.)
+
+**Validation Scenario**:
+- **Topic**: "Next steps for tellingCube after validation test"
+- **Agents**: River (orchestrator), Mary (analyst), Winston (architect)
+- **Report Mode**: Brief
+- **Outcome**: Successfully analyzed post-validation roadmap with 3 scenarios (GO/CHANGE/NO-GO), delivered consolidated recommendations in 5 minutes
+
+**User Feedback (Mario Semper)**:
+> "This is exactly what I needed - I wanted multiple perspectives without having to orchestrate every conversation. The brief report gave me actionable next steps immediately."
+
+**Documentation**: `docs/_masemIT/readme.md` in tellingCube repository
+
+---
+
+## Proposed Documentation Structure
+
+```
+.bmad-core/
+  features/
+    ring-of-fire.md              # Feature specification
+
+docs/
+  guides/
+    using-rof-sessions.md        # User guide with examples
+
+  architecture/
+    agent-collaboration.md       # Technical design
+    rof-session-management.md    # State handling approach
+```
+
+---
+
+## Benefits
+
+✅ **Unlocks parallel workflows** - User productivity gains
+✅ **Reduces context-switching** - Cognitive load reduction
+✅ **Enables complex analysis** - Multi-perspective insights
+✅ **Maintains user control** - Approval gates for tools
+✅ **Scales flexibly** - From quick checks to deep dives
+
+---
+
+## Comparison to Existing Patterns
+
+| Feature | Standard Agent Use | ROF Session |
+|---------|-------------------|-------------|
+| Agent collaboration | Sequential (one at a time) | Parallel (multiple simultaneously) |
+| User involvement | Required for every exchange | Only for approvals |
+| Parallel work | No (user waits) | Yes (user continues tasks) |
+| Output | Chat transcript | Consolidated report |
+| Use case | Single-perspective tasks | Multi-perspective analysis |
+
+---
+
+## Next Steps
+
+1. **Community feedback** on approach and open questions
+2. **Technical design** refinement (state management, agent communication)
+3. **Prototype implementation** in BMad core or as extension
+4. **Beta testing** with real projects (beyond tellingCube)
+5. **Documentation** completion with examples
+
+---
+
+## Alternatives Considered
+
+### Alt 1: "Breakout Session"
+- **Pros**: Clear meeting metaphor
+- **Cons**: Less evocative, doesn't convey "continuous collaborative space"
+
+### Alt 2: "Agent Huddle"
+- **Pros**: Short, casual
+- **Cons**: Implies quick/informal only
+
+### Alt 3: "Lagerfeuer" (original German name)
+- **Pros**: Warm, campfire metaphor
+- **Cons**: Poor i18n, hard to pronounce/remember for non-German speakers
+
+**Chosen**: **Ring of Fire** - evokes continuous collaboration circle, internationally understood, memorable, shortcut "ROF" works well
+
+---
+
+## References
+
+- **Source Project**: tellingCube (https://github.com/masemIT/telling-cube) [if public]
+- **Documentation**: `docs/_masemIT/readme.md`
+- **Discussion**: [Link to BMad community discussion if applicable]
+
+---
+
+**Contribution ready for review.** Feedback welcome! 🔥
--- a/package-lock.json
+++ b/package-lock.json
@ -1,12 +1,12 @@
 {
  "name": "bmad-method",
-  "version": "6.0.0-alpha.11",
+  "version": "6.0.0-alpha.12",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "bmad-method",
-      "version": "6.0.0-alpha.11",
+      "version": "6.0.0-alpha.12",
      "license": "MIT",
      "dependencies": {
        "@kayvan/markdown-tree-parser": "^1.6.1",
@ -1023,9 +1023,9 @@
      }
    },
    "node_modules/@istanbuljs/load-nyc-config/node_modules/js-yaml": {
-      "version": "3.14.1",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz",
-      "integrity": "sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==",
+      "version": "3.14.2",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.2.tgz",
+      "integrity": "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg==",
      "dev": true,
      "license": "MIT",
      "dependencies": {
@ -1329,9 +1329,9 @@
      }
    },
    "node_modules/@jest/reporters/node_modules/glob": {
-      "version": "10.4.5",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
-      "integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
+      "version": "10.5.0",
+      "resolved": "https://registry.npmjs.org/glob/-/glob-10.5.0.tgz",
+      "integrity": "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==",
      "dev": true,
      "license": "ISC",
      "dependencies": {
@ -2618,9 +2618,9 @@
      }
    },
    "node_modules/c8/node_modules/glob": {
-      "version": "10.4.5",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
-      "integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
+      "version": "10.5.0",
+      "resolved": "https://registry.npmjs.org/glob/-/glob-10.5.0.tgz",
+      "integrity": "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==",
      "dev": true,
      "license": "ISC",
      "dependencies": {
@ -4103,14 +4103,14 @@
      }
    },
    "node_modules/glob": {
-      "version": "11.0.3",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-11.0.3.tgz",
-      "integrity": "sha512-2Nim7dha1KVkaiF4q6Dj+ngPPMdfvLJEOpZk/jKiUAkqKebpGAWQXAq9z1xu9HKu5lWfqw/FASuccEjyznjPaA==",
-      "license": "ISC",
+      "version": "11.1.0",
+      "resolved": "https://registry.npmjs.org/glob/-/glob-11.1.0.tgz",
+      "integrity": "sha512-vuNwKSaKiqm7g0THUBu2x7ckSs3XJLXE+2ssL7/MfTGPLLcrJQ/4Uq1CjPTtO5cCIiRxqvN6Twy1qOwhL0Xjcw==",
+      "license": "BlueOak-1.0.0",
      "dependencies": {
        "foreground-child": "^3.3.1",
        "jackspeak": "^4.1.1",
-        "minimatch": "^10.0.3",
+        "minimatch": "^10.1.1",
        "minipass": "^7.1.2",
        "package-json-from-dist": "^1.0.0",
        "path-scurry": "^2.0.0"
@ -4139,10 +4139,10 @@
      }
    },
    "node_modules/glob/node_modules/minimatch": {
-      "version": "10.0.3",
-      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-10.0.3.tgz",
-      "integrity": "sha512-IPZ167aShDZZUMdRk66cyQAW3qr0WzbHkPdMYa8bzZhlHhO3jALbKdxcaak7W9FfT2rZNpQuUu4Od7ILEpXSaw==",
-      "license": "ISC",
+      "version": "10.1.1",
+      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-10.1.1.tgz",
+      "integrity": "sha512-enIvLvRAFZYXJzkCYG5RKmPfrFArdLv+R+lbQ53BmIMLIry74bjKzX6iHAm8WYamJkhSSEabrWN5D97XnKObjQ==",
+      "license": "BlueOak-1.0.0",
      "dependencies": {
        "@isaacs/brace-expansion": "^5.0.0"
      },
@ -4808,9 +4808,9 @@
      }
    },
    "node_modules/jest-config/node_modules/glob": {
-      "version": "10.4.5",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
-      "integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
+      "version": "10.5.0",
+      "resolved": "https://registry.npmjs.org/glob/-/glob-10.5.0.tgz",
+      "integrity": "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==",
      "dev": true,
      "license": "ISC",
      "dependencies": {
@ -5181,9 +5181,9 @@
      }
    },
    "node_modules/jest-runtime/node_modules/glob": {
-      "version": "10.4.5",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
-      "integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
+      "version": "10.5.0",
+      "resolved": "https://registry.npmjs.org/glob/-/glob-10.5.0.tgz",
+      "integrity": "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg==",
      "dev": true,
      "license": "ISC",
      "dependencies": {
@ -5413,9 +5413,9 @@
      "license": "MIT"
    },
    "node_modules/js-yaml": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz",
-      "integrity": "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA==",
+      "version": "4.1.1",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.1.tgz",
+      "integrity": "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA==",
      "license": "MIT",
      "dependencies": {
        "argparse": "^2.0.1"
--- a/src/modules/bmm/_module-installer/assets/bmm-kb.md
+++ b/src/modules/bmm/_module-installer/assets/bmm-kb.md
@ -1 +0,0 @@
-# BMad Method Master Knowledge Base Index
--- a/src/modules/bmm/_module-installer/assets/technical-decisions.md
+++ b/src/modules/bmm/_module-installer/assets/technical-decisions.md
@ -1,30 +0,0 @@
-# Technical Decisions Log
-
-_Auto-updated during discovery and planning sessions - you can also add information here yourself_
-
-## Purpose
-
-This document captures technical decisions, preferences, and constraints discovered during project discussions. It serves as input for architecture.md and solution design documents.
-
-## Confirmed Decisions
-
-<!-- Technical choices explicitly confirmed by the team/user -->
-
-## Preferences
-
-<!-- Non-binding preferences mentioned during discussions -->
-
-## Constraints
-
-<!-- Hard requirements from infrastructure, compliance, or integration needs -->
-
-## To Investigate
-
-<!-- Technical questions that need research or architect input -->
-
-## Notes
-
- This file is automatically updated when technical information is mentioned
- Decisions here are inputs, not final architecture
- Final technical decisions belong in architecture.md
- Implementation details belong in solutions/\*.md and story context or dev notes.
--- a/src/modules/bmm/agents/analyst.agent.yaml
+++ b/src/modules/bmm/agents/analyst.agent.yaml
@ -18,21 +18,25 @@ agent:
      - Find if this exists, if it does, always treat it as the bible I plan and execute against: `**/project-context.md`

  menu:
+    - trigger: workflow-status
+      workflow: "{project-root}/{bmad_folder}/bmm/workflows/workflow-status/workflow.yaml"
+      description: Get workflow status or initialize a workflow if not already done (optional)
+
    - trigger: brainstorm-project
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/1-analysis/brainstorm-project/workflow.yaml"
-      description: Guided Brainstorming scoped to product development ideation and problem discovery
+      description: Guided Brainstorming session with final report (optional)

    - trigger: research
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/1-analysis/research/workflow.yaml"
-      description: Guided Research scoped to market and competitive analysis of a product or feature
+      description: Guided Research scoped to market and competitive analysis (optional)

    - trigger: product-brief
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/1-analysis/product-brief/workflow.yaml"
-      description: Create a Product Brief, a great input to then drive a PRD
+      description: Create a Product Brief (recommended input for PRD)

    - trigger: document-project
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/document-project/workflow.yaml"
-      description: Generate comprehensive documentation of an existing codebase, including architecture, data flows, and API contracts, and other details to aid project understanding.
+      description: Document your existing project (optional, but recommended for existing brownfield project efforts)

    - trigger: party-mode
      workflow: "{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.yaml"
--- a/src/modules/bmm/agents/architect.agent.yaml
+++ b/src/modules/bmm/agents/architect.agent.yaml
@ -18,25 +18,29 @@ agent:
      - Find if this exists, if it does, always treat it as the bible I plan and execute against: `**/project-context.md`

  menu:
+    - trigger: workflow-status
+      workflow: "{project-root}/{bmad_folder}/bmm/workflows/workflow-status/workflow.yaml"
+      description: Get workflow status or initialize a workflow if not already done (optional)
+
    - trigger: create-architecture
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/3-solutioning/architecture/workflow.yaml"
-      description: Produce a Scale Adaptive Architecture
+      description: Create an Architecture Document to Guide Development of a PRD (required for BMad Method projects)

    - trigger: validate-architecture
      validate-workflow: "{project-root}/{bmad_folder}/bmm/workflows/3-solutioning/architecture/workflow.yaml"
-      description: Validate Architecture Document
+      description: Validate Architecture Document (Recommended, use another LLM and fresh context for best results)

    - trigger: implementation-readiness
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/3-solutioning/implementation-readiness/workflow.yaml"
-      description: Validate implementation readiness - PRD, UX, Architecture, Epics aligned
+      description: Validate PRD, UX, Architecture, Epics and stories aligned (Optional but recommended before development)

    - trigger: create-excalidraw-diagram
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/diagrams/create-diagram/workflow.yaml"
-      description: Create system architecture or technical diagram (Excalidraw)
+      description: Create system architecture or technical diagram (Excalidraw) (Use any time you need a diagram)

    - trigger: create-excalidraw-dataflow
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/diagrams/create-dataflow/workflow.yaml"
-      description: Create data flow diagram (Excalidraw)
+      description: Create data flow diagram (Excalidraw) (Use any time you need a diagram)

    - trigger: party-mode
      workflow: "{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.yaml"
--- a/src/modules/bmm/agents/dev.agent.yaml
+++ b/src/modules/bmm/agents/dev.agent.yaml
@ -39,10 +39,6 @@ agent:
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/dev-story/workflow.yaml"
      description: "Execute Dev Story workflow (full BMM path with sprint-status)"

-    - trigger: story-done
-      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/story-done/workflow.yaml"
-      description: "Mark story done after DoD complete"
-
    - trigger: code-review
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/code-review/workflow.yaml"
-      description: "Perform a thorough clean context QA code review on a story flagged Ready for Review"
+      description: "Perform a thorough clean context code review (Highly Recommended, use fresh context and different LLM)"
--- a/src/modules/bmm/agents/pm.agent.yaml
+++ b/src/modules/bmm/agents/pm.agent.yaml
@ -19,21 +19,25 @@ agent:
      - Find if this exists, if it does, always treat it as the bible I plan and execute against: `**/project-context.md`

  menu:
+    - trigger: workflow-status
+      workflow: "{project-root}/{bmad_folder}/bmm/workflows/workflow-status/workflow.yaml"
+      description: Get workflow status or initialize a workflow if not already done (optional)
+
    - trigger: create-prd
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/2-plan-workflows/prd/workflow.yaml"
-      description: Create Product Requirements Document (PRD)
+      description: Create Product Requirements Document (PRD) (Required for BMad Method flow)

    - trigger: validate-prd
      validate-workflow: "{project-root}/{bmad_folder}/bmm/workflows/2-plan-workflows/prd/workflow.yaml"
-      description: Validate PRD
+      description: Validate PRD (Highly Recommended, use fresh context and different LLM for best results)

    - trigger: create-epics-and-stories
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/3-solutioning/create-epics-and-stories/workflow.yaml"
-      description: Create Epics and User Stories from PRD (Its recommended to not do this until the architecture is complete)
+      description: Create Epics and User Stories from PRD (Required for BMad Method flow AFTER the Architecture is completed)

    - trigger: correct-course
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/correct-course/workflow.yaml"
-      description: Course Correction Analysis
+      description: Course Correction Analysis (optional during implementation when things go off track)
      ide-only: true

    - trigger: party-mode
--- a/src/modules/bmm/agents/quick-flow-solo-dev.agent.yaml
+++ b/src/modules/bmm/agents/quick-flow-solo-dev.agent.yaml
@ -21,15 +21,15 @@ agent:
  menu:
    - trigger: create-tech-spec
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/bmad-quick-flow/create-tech-spec/workflow.yaml"
-      description: Architect a technical spec with implementation-ready stories
+      description: Architect a technical spec with implementation-ready stories (Required first step)

    - trigger: quick-dev
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/bmad-quick-flow/quick-dev/workflow.yaml"
-      description: Ship features from spec or direct instructions - no handoffs
+      description: Implement the tech spec end-to-end solo (Core of Quick Flow)

    - trigger: code-review
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/code-review/workflow.yaml"
-      description: Review code for quality, patterns, and acceptance criteria
+      description: Review code and improve it (Highly Recommended, use fresh context and different LLM for best results)

    - trigger: party-mode
      workflow: "{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.yaml"
--- a/src/modules/bmm/agents/sm.agent.yaml
+++ b/src/modules/bmm/agents/sm.agent.yaml
@ -26,24 +26,24 @@ agent:
  menu:
    - trigger: sprint-planning
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/sprint-planning/workflow.yaml"
-      description: Generate or update sprint-status.yaml from epic files
+      description: Generate or re-generate sprint-status.yaml from epic files (Required after Epics+Stories are created)

    - trigger: create-story
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/create-story/workflow.yaml"
-      description: Create a Draft Story
+      description: Create a Draft Story (Required to prepare stories for development)

    - trigger: validate-create-story
      validate-workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/create-story/workflow.yaml"
-      description: (Optional) Validate Story Draft with Independent Review
+      description: Validate Story Draft (Highly Recommended, use fresh context and different LLM for best results)

    - trigger: epic-retrospective
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/retrospective/workflow.yaml"
      data: "{project-root}/{bmad_folder}/_cfg/agent-manifest.csv"
-      description: (Optional) Facilitate team retrospective after an epic is completed
+      description: Facilitate team retrospective after an epic is completed (Optional)

    - trigger: correct-course
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/4-implementation/correct-course/workflow.yaml"
-      description: (Optional) Execute correct-course task
+      description: Execute correct-course task (When implementation is off-track)

    - trigger: party-mode
      workflow: "{project-root}/{bmad_folder}/core/workflows/party-mode/workflow.yaml"
--- a/src/modules/bmm/agents/ux-designer.agent.yaml
+++ b/src/modules/bmm/agents/ux-designer.agent.yaml
@ -25,7 +25,7 @@ agent:
  menu:
    - trigger: create-ux-design
      workflow: "{project-root}/{bmad_folder}/bmm/workflows/2-plan-workflows/create-ux-design/workflow.yaml"
-      description: Conduct Design Thinking Workshop to Define the User Specification with PRD as input
+      description: Generate a UX Design and UI Plan from a PRD (Recommended before creating Architecture)

    - trigger: validate-design
      validate-workflow: "{project-root}/{bmad_folder}/bmm/workflows/2-plan-workflows/create-ux-design/workflow.yaml"
--- a/src/modules/bmm/docs/images/workflow-method-greenfield.excalidraw
+++ b/src/modules/bmm/docs/images/workflow-method-greenfield.excalidraw
--- a/src/modules/bmm/docs/images/workflow-method-greenfield.svg
+++ b/src/modules/bmm/docs/images/workflow-method-greenfield.svg
--- a/src/modules/bmm/workflows/workflow-status/init/instructions.md
+++ b/src/modules/bmm/workflows/workflow-status/init/instructions.md
@ -3,7 +3,7 @@
 <critical>The workflow execution engine is governed by: {project-root}/{bmad_folder}/core/tasks/workflow.xml</critical>
 <critical>You MUST have already loaded and processed: workflow-init/workflow.yaml</critical>
 <critical>Communicate in {communication_language} with {user_name}</critical>
-<critical>This workflow handles BOTH new projects AND legacy projects being migrated to BMad Method</critical>
+<critical>This workflow handles BOTH new projects AND legacy projects following the BMad Method</critical>

 <workflow>

@ -12,7 +12,7 @@

 <action>Perform comprehensive scan for existing work:

- BMM artifacts: PRD, tech-spec, epics, architecture, UX, brief, research, brainstorm
+- BMM artifacts: PRD, epics, architecture, UX, brief, research, brainstorm
 - Implementation: stories, sprint-status, workflow-status
 - Codebase: source directories, package files, git repo
 - Check both {output_folder} and {sprint_artifacts} locations
@ -53,31 +53,31 @@ Happy building! 🚀</output>

 <ask>How would you like to proceed?

-a) **Continue** - Work with existing artifacts
-b) **Archive & Start Fresh** - Move old work to archive
-c) **Express Setup** - I know exactly what I need
-d) **Guided Setup** - Walk me through options
+1. **Continue** - Work with existing artifacts
+2. **Archive & Start Fresh** - Move old work to archive
+3. **Express Setup** - I know exactly what I need
+4. **Guided Setup** - Walk me through options

-Choice [a/b/c/d]:</ask>
+Choice [1-4]</ask>

-  <check if="choice == a">
+  <check if="choice == 1">
    <action>Set continuing_existing = true</action>
    <action>Store found artifacts</action>
    <action>Continue to step 7 (detect track from artifacts)</action>
  </check>

-  <check if="choice == b">
+  <check if="choice == 2">
    <ask>Archive existing work? (y/n)</ask>
    <action if="y">Move artifacts to {output_folder}/archive/</action>
    <output>Ready for fresh start!</output>
    <action>Continue to step 3</action>
  </check>

-  <check if="choice == c">
+  <check if="choice == 3">
    <action>Jump to step 3 (express path)</action>
  </check>

-  <check if="choice == d">
+  <check if="choice == 4">
    <action>Continue to step 4 (guided path)</action>
  </check>
 </check>
@ -85,16 +85,16 @@ Choice [a/b/c/d]:</ask>
 <check if="state == CLEAN">
  <ask>Setup approach:

-a) **Express** - I know what I need
-b) **Guided** - Show me the options
+1. **Express** - I know what I need
+2. **Guided** - Show me the options

-Choice [a/b]:</ask>
+Choice [1 or 2]:</ask>

-  <check if="choice == a">
+  <check if="choice == 1">
    <action>Continue to step 3 (express)</action>
  </check>

-  <check if="choice == b">
+  <check if="choice == 2">
    <action>Continue to step 4 (guided)</action>
  </check>
 </check>
@ -102,20 +102,22 @@ Choice [a/b]:</ask>

 <step n="3" goal="Express setup path">
 <ask>Is this for:
-1) **New project** (greenfield)
-2) **Existing codebase** (brownfield)
+1. **New project** (greenfield)
+2. **Existing codebase** (brownfield)

 Choice [1/2]:</ask>
 <action>Set field_type based on choice</action>

 <ask>Planning approach:

-1. **Quick Flow** - Minimal planning, fast to code
-2. **BMad Method** - Full planning for complex projects
-3. **Enterprise Method** - Extended planning with security/DevOps
+1. **BMad Method** - Full planning for complex projects
+2. **Enterprise Method** - Extended planning with security/DevOps

-Choice [1/2/3]:</ask>
-<action>Map to selected_track: quick-flow/method/enterprise</action>
+Choice [1/2]:</ask>
+<action>Map to selected_track: method/enterprise</action>
+
+<output>🚀 **For Quick Flow (minimal planning, straight to code):**
+Load the **quick-flow-solo-dev** agent instead - use Quick Flow agent for faster development</output>

 <template-output>field_type</template-output>
 <template-output>selected_track</template-output>
@ -135,8 +137,8 @@ Choice [1/2/3]:</ask>

 <check if="field_type unclear AND codebase exists">
  <ask>I see existing code. Are you:
-1) **Modifying** existing codebase (brownfield)
-2) **Starting fresh** - code is just scaffold (greenfield)
+1. **Modifying** existing codebase (brownfield)
+2. **Starting fresh** - code is just scaffold (greenfield)

 Choice [1/2]:</ask>
 <action>Set field_type based on answer</action>
@ -165,44 +167,60 @@ Continue with software workflows? (y/n)</output>
 </step>

 <step n="5" goal="Guided setup - select track">
-<output>Based on your project, here are your planning options:
+<output>Based on your project, here are your BMad Method planning options:

 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

-**1. Quick Flow** 🚀
-
- Minimal planning, straight to code
- Best for: Simple features, bug fixes
- Risk: Potential rework if complexity emerges
-
-**2. BMad Method** 🎯 {{#if recommended}}(RECOMMENDED){{/if}}
+**1. BMad Method** 🎯 {{#if recommended}}(RECOMMENDED){{/if}}

 - Full planning: PRD + UX + Architecture
 - Best for: Products, platforms, complex features
 - Benefit: AI agents have complete context for better results

-**3. Enterprise Method** 🏢
+**2. Enterprise Method** 🏢

 - Extended: Method + Security + DevOps + Testing
 - Best for: Enterprise, compliance, mission-critical
 - Benefit: Comprehensive planning for complex systems

+**🚀 For Quick Flow (minimal planning, straight to code):**
+Load the **quick-flow-solo-dev** agent instead - use Quick Flow agent for faster development
+
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

 {{#if brownfield}}
 💡 Architecture creates focused solution design from your codebase, keeping AI agents on track.
 {{/if}}</output>

-<ask>Which approach fits best?
+<ask>Which BMad Method approach fits best?

-1. Quick Flow
-2. BMad Method {{#if recommended}}(recommended){{/if}}
-3. Enterprise Method
-4. Help me decide
+1. BMad Method {{#if recommended}}(recommended){{/if}}
+2. Enterprise Method
+3. Help me decide
+4. Switch to Quick Flow (use quick-flow-solo-dev agent)

 Choice [1/2/3/4]:</ask>

 <check if="choice == 4">
+  <output>🚀 **Switching to Quick Flow!**
+
+Load the **quick-flow-solo-dev** agent instead:
+
+- Start a new chat
+- Load the quick-flow-solo-dev agent
+- Use Quick Flow for minimal planning and faster development
+
+Quick Flow is perfect for:
+
+- Simple features and bug fixes
+- Rapid prototyping
+- When you want to get straight to code
+
+Happy coding! 🚀</output>
+<action>Exit workflow</action>
+</check>
+
+<check if="choice == 3">
  <ask>What concerns you about choosing?</ask>
  <action>Provide tailored guidance based on concerns</action>
  <action>Loop back to choice</action>
@ -215,7 +233,7 @@ Choice [1/2/3/4]:</ask>
 <step n="6" goal="Discovery workflows selection (unified)">
 <action>Determine available discovery workflows based on:
 - field_type (greenfield gets product-brief option)
- selected_track (quick-flow skips product-brief)
+- selected_track (method/enterprise options)
 </action>

 <check if="field_type == greenfield AND selected_track in [method, enterprise]">
@ -229,7 +247,7 @@ Choice [1/2/3/4]:</ask>
 Enter numbers (e.g., "1,3" or "all" or "none"): </ask>
 </check>

-<check if="field_type == brownfield OR selected_track == quick-flow">
+<check if="field_type == brownfield AND selected_track in [method, enterprise]">
  <output>Optional discovery workflows:</output>
  <ask>Include any of these?

@ -250,7 +268,7 @@ Enter numbers (e.g., "1,2" or "none"): </ask>
 <template-output>research_requested</template-output>
 <template-output>product_brief_requested</template-output>

-<check if="brownfield AND selected_track != quick-flow">
+<check if="brownfield">
  <output>💡 **Note:** For brownfield projects, run document-project workflow first to analyze your codebase.</output>
 </check>
 </step>
@ -258,18 +276,18 @@ Enter numbers (e.g., "1,2" or "none"): </ask>
 <step n="7" goal="Detect track from artifacts" if="continuing_existing OR migrating_legacy">
 <action>Analyze artifacts to detect track:
 - Has PRD → BMad Method
- Has tech-spec only → Quick Flow
 - Has Security/DevOps → Enterprise Method
+- Has tech-spec only → Suggest switching to quick-flow-solo-dev agent
 </action>

 <output>Detected: **{{detected_track}}** based on {{found_artifacts}}</output>
 <ask>Correct? (y/n)</ask>

-<ask if="n">Which track instead?
+<ask if="n">Which BMad Method track instead?

-1. Quick Flow
-2. BMad Method
-3. Enterprise Method
+1. BMad Method
+2. Enterprise Method
+3. Switch to Quick Flow (use quick-flow-solo-dev agent)

 Choice:</ask>

@ -298,11 +316,8 @@ Choice:</ask>
 {{#if brownfield}}Prerequisites: document-project{{/if}}
 {{#if has_discovery}}Discovery: {{list_selected_discovery}}{{/if}}

-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-
 {{workflow_path_summary}}
-
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</output>
+</output>

 <ask>Create workflow tracking file? (y/n)</ask>

@ -326,9 +341,6 @@ To check progress: /bmad:bmm:workflows:workflow-status
 Happy building! 🚀</output>
 </check>

-<check if="n">
-  <output>No problem! Run workflow-init again when ready.</output>
-</check>
 </step>

 </workflow>
--- a/src/modules/bmm/workflows/workflow-status/instructions.md
+++ b/src/modules/bmm/workflows/workflow-status/instructions.md
@ -37,12 +37,19 @@
 <action>Search {output_folder}/ for file: bmm-workflow-status.yaml</action>

 <check if="no status file found">
-  <output>No workflow status found. To get started:
+  <output>No workflow status found.</output>
+  <ask>Would you like to run Workflow Init now? (y/n)</ask>

-Load analyst agent and run: `workflow-init`
+  <check if="response == y OR response == yes">
+    <action>Launching workflow-init to set up your project tracking...</action>
+    <invoke-workflow path="{project-root}/{bmad_folder}/bmm/workflows/workflow-status/init/workflow.yaml"></invoke-workflow>
+    <action>Exit workflow and let workflow-init take over</action>
+  </check>

-This will guide you through project setup and create your workflow path.</output>
-<action>Exit workflow</action>
+  <check if="else">
+    <output>No workflow status file. Run workflow-init when ready to enable progress tracking.</output>
+    <action>Exit workflow</action>
+  </check>
 </check>

 <check if="status file found">
--- a/src/modules/bmm/workflows/workflow-status/paths/quick-flow-brownfield.yaml
+++ b/src/modules/bmm/workflows/workflow-status/paths/quick-flow-brownfield.yaml
@ -1,67 +0,0 @@
-# BMad Quick Flow - Brownfield
-# Fast spec-driven development for existing codebases (1-10 stories typically)
-
-method_name: "BMad Quick Flow"
-track: "quick-flow"
-field_type: "brownfield"
-description: "Spec-driven development for brownfield projects - streamlined path with codebase context"
-
-phases:
-  - prerequisite: true
-    name: "Documentation"
-    conditional: "if_undocumented"
-    note: "NOT a phase - prerequisite for brownfield without docs"
-    workflows:
-      - id: "document-project"
-        required: true
-        agent: "analyst"
-        command: "document-project"
-        output: "Comprehensive project documentation"
-        purpose: "Generate codebase context for spec engineering"
-
-  - phase: 0
-    name: "Discovery (Optional)"
-    optional: true
-    note: "User-selected during workflow-init"
-    workflows:
-      - id: "brainstorm-project"
-        optional: true
-        agent: "analyst"
-        command: "brainstorm-project"
-        included_by: "user_choice"
-
-      - id: "research"
-        optional: true
-        agent: "analyst"
-        command: "research"
-        included_by: "user_choice"
-
-  - phase: 1
-    name: "Spec Engineering"
-    required: true
-    workflows:
-      - id: "create-tech-spec"
-        required: true
-        agent: "quick-flow-solo-dev"
-        command: "create-tech-spec"
-        output: "Technical Specification with implementation-ready stories"
-        note: "Stories include codebase context from document-project"
-
-  - phase: 2
-    name: "Implementation"
-    required: true
-    note: "Barry executes all stories, optional code-review after each"
-    workflows:
-      - id: "dev-spec"
-        required: true
-        repeat: true
-        agent: "quick-flow-solo-dev"
-        command: "dev-spec"
-        note: "Execute stories from spec - Barry is the one-man powerhouse"
-
-      - id: "code-review"
-        optional: true
-        repeat: true
-        agent: "quick-flow-solo-dev"
-        command: "code-review"
-        note: "Review completed story implementation"
--- a/src/modules/bmm/workflows/workflow-status/paths/quick-flow-greenfield.yaml
+++ b/src/modules/bmm/workflows/workflow-status/paths/quick-flow-greenfield.yaml
@ -1,56 +0,0 @@
-# BMad Quick Flow - Greenfield
-# Fast spec-driven development path (1-10 stories typically)
-
-method_name: "BMad Quick Flow"
-track: "quick-flow"
-field_type: "greenfield"
-description: "Spec-driven development for greenfield projects - streamlined path without sprint overhead"
-
-phases:
-  - phase: 0
-    name: "Discovery (Optional)"
-    optional: true
-    note: "User-selected during workflow-init"
-    workflows:
-      - id: "brainstorm-project"
-        optional: true
-        agent: "analyst"
-        command: "brainstorm-project"
-        included_by: "user_choice"
-
-      - id: "research"
-        optional: true
-        agent: "analyst"
-        command: "research"
-        included_by: "user_choice"
-        note: "Can have multiple research workflows"
-
-  - phase: 1
-    name: "Spec Engineering"
-    required: true
-    workflows:
-      - id: "create-tech-spec"
-        required: true
-        agent: "quick-flow-solo-dev"
-        command: "create-tech-spec"
-        output: "Technical Specification with implementation-ready stories"
-        note: "Stories contain all context for execution"
-
-  - phase: 2
-    name: "Implementation"
-    required: true
-    note: "Barry executes all stories, optional code-review after each"
-    workflows:
-      - id: "dev-spec"
-        required: true
-        repeat: true
-        agent: "quick-flow-solo-dev"
-        command: "dev-spec"
-        note: "Execute stories from spec - Barry is the one-man powerhouse"
-
-      - id: "code-review"
-        optional: true
-        repeat: true
-        agent: "quick-flow-solo-dev"
-        command: "code-review"
-        note: "Review completed story implementation"
--- a/tools/cli/commands/cleanup.js
+++ b/tools/cli/commands/cleanup.js
@ -0,0 +1,141 @@
+const chalk = require('chalk');
+const nodePath = require('node:path');
+const { Installer } = require('../installers/lib/core/installer');
+
+module.exports = {
+  command: 'cleanup',
+  description: 'Clean up obsolete files from BMAD installation',
+  options: [
+    ['-d, --dry-run', 'Show what would be deleted without actually deleting'],
+    ['-a, --auto-delete', 'Automatically delete non-retained files without prompts'],
+    ['-l, --list-retained', 'List currently retained files'],
+    ['-c, --clear-retained', 'Clear retained files list'],
+  ],
+  action: async (options) => {
+    try {
+      // Create installer and let it find the BMAD directory
+      const installer = new Installer();
+      const bmadDir = await installer.findBmadDir(process.cwd());
+
+      if (!bmadDir) {
+        console.error(chalk.red('❌ BMAD installation not found'));
+        process.exit(1);
+      }
+
+      const retentionPath = nodePath.join(bmadDir, '_cfg', 'user-retained-files.yaml');
+
+      // Handle list-retained option
+      if (options.listRetained) {
+        const fs = require('fs-extra');
+        const yaml = require('js-yaml');
+
+        if (await fs.pathExists(retentionPath)) {
+          const retentionContent = await fs.readFile(retentionPath, 'utf8');
+          const retentionData = yaml.load(retentionContent) || { retainedFiles: [] };
+
+          if (retentionData.retainedFiles.length > 0) {
+            console.log(chalk.cyan('\n📋 Retained Files:\n'));
+            for (const file of retentionData.retainedFiles) {
+              console.log(chalk.dim(`  - ${file}`));
+            }
+            console.log();
+          } else {
+            console.log(chalk.yellow('\n✨ No retained files found\n'));
+          }
+        } else {
+          console.log(chalk.yellow('\n✨ No retained files found\n'));
+        }
+
+        return;
+      }
+
+      // Handle clear-retained option
+      if (options.clearRetained) {
+        const fs = require('fs-extra');
+
+        if (await fs.pathExists(retentionPath)) {
+          await fs.remove(retentionPath);
+          console.log(chalk.green('\n✅ Cleared retained files list\n'));
+        } else {
+          console.log(chalk.yellow('\n✨ No retained files list to clear\n'));
+        }
+
+        return;
+      }
+
+      // Handle cleanup operations
+      if (options.dryRun) {
+        console.log(chalk.cyan('\n🔍 Legacy File Scan (Dry Run)\n'));
+
+        const legacyFiles = await installer.scanForLegacyFiles(bmadDir);
+        const allLegacyFiles = [
+          ...legacyFiles.backup,
+          ...legacyFiles.documentation,
+          ...legacyFiles.deprecated_task,
+          ...legacyFiles.unknown,
+        ];
+
+        if (allLegacyFiles.length === 0) {
+          console.log(chalk.green('✨ No legacy files found\n'));
+          return;
+        }
+
+        // Group files by category
+        const categories = [];
+        if (legacyFiles.backup.length > 0) {
+          categories.push({ name: 'Backup Files (.bak)', files: legacyFiles.backup });
+        }
+        if (legacyFiles.documentation.length > 0) {
+          categories.push({ name: 'Documentation', files: legacyFiles.documentation });
+        }
+        if (legacyFiles.deprecated_task.length > 0) {
+          categories.push({ name: 'Deprecated Task Files', files: legacyFiles.deprecated_task });
+        }
+        if (legacyFiles.unknown.length > 0) {
+          categories.push({ name: 'Unknown Files', files: legacyFiles.unknown });
+        }
+
+        for (const category of categories) {
+          console.log(chalk.yellow(`${category.name}:`));
+          for (const file of category.files) {
+            const size = (file.size / 1024).toFixed(1);
+            const date = file.mtime.toLocaleDateString();
+            let line = `  - ${file.relativePath} (${size}KB, ${date})`;
+            if (file.suggestedAlternative) {
+              line += chalk.dim(` → ${file.suggestedAlternative}`);
+            }
+            console.log(chalk.dim(line));
+          }
+          console.log();
+        }
+
+        console.log(chalk.cyan(`Found ${allLegacyFiles.length} legacy file(s) that could be cleaned up.\n`));
+        console.log(chalk.dim('Run "bmad cleanup" to actually delete these files.\n'));
+
+        return;
+      }
+
+      // Perform actual cleanup
+      console.log(chalk.cyan('\n🧹 Cleaning up legacy files...\n'));
+
+      const result = await installer.performCleanup(bmadDir, options.autoDelete);
+
+      if (result.message) {
+        console.log(chalk.dim(result.message));
+      } else {
+        if (result.deleted > 0) {
+          console.log(chalk.green(`✅ Deleted ${result.deleted} legacy file(s)`));
+        }
+        if (result.retained > 0) {
+          console.log(chalk.yellow(`⏭️  Retained ${result.retained} file(s)`));
+          console.log(chalk.dim('Run "bmad cleanup --list-retained" to see retained files\n'));
+        }
+      }
+
+      console.log();
+    } catch (error) {
+      console.error(chalk.red(`❌ Error: ${error.message}`));
+      process.exit(1);
+    }
+  },
+};
--- a/tools/cli/commands/install.js
+++ b/tools/cli/commands/install.js
@ -9,8 +9,8 @@ const ui = new UI();
 module.exports = {
  command: 'install',
  description: 'Install BMAD Core agents and tools',
-  options: [],
-  action: async () => {
+  options: [['--skip-cleanup', 'Skip automatic cleanup of legacy files']],
+  action: async (options) => {
    try {
      const config = await ui.promptInstall();

@ -44,6 +44,11 @@ module.exports = {
        config._requestedReinstall = true;
      }

+      // Add skip cleanup flag if option provided
+      if (options && options.skipCleanup) {
+        config.skipCleanup = true;
+      }
+
      // Regular install/update flow
      const result = await installer.install(config);

--- a/tools/cli/installers/lib/core/installer.js
+++ b/tools/cli/installers/lib/core/installer.js
@ -1018,6 +1018,23 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
        customFiles: customFiles.length > 0 ? customFiles : undefined,
      });

+      // Offer cleanup for legacy files (only for updates, not fresh installs, and only if not skipped)
+      if (!config.skipCleanup && config._isUpdate) {
+        try {
+          const cleanupResult = await this.performCleanup(bmadDir, false);
+          if (cleanupResult.deleted > 0) {
+            console.log(chalk.green(`\n✓ Cleaned up ${cleanupResult.deleted} legacy file${cleanupResult.deleted > 1 ? 's' : ''}`));
+          }
+          if (cleanupResult.retained > 0) {
+            console.log(chalk.dim(`Run 'bmad cleanup' anytime to manage retained files`));
+          }
+        } catch (cleanupError) {
+          // Don't fail the installation for cleanup errors
+          console.log(chalk.yellow(`\n⚠️  Cleanup warning: ${cleanupError.message}`));
+          console.log(chalk.dim('Run "bmad cleanup" to manually clean up legacy files'));
+        }
+      }
+
      return {
        success: true,
        path: bmadDir,
@ -1939,7 +1956,7 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:

      if (existingBmadFolderName === newBmadFolderName) {
        // Normal quick update - start the spinner
-        spinner.start('Updating BMAD installation...');
+        console.log(chalk.cyan('Updating BMAD installation...'));
      } else {
        // Folder name has changed - stop spinner and let install() handle it
        spinner.stop();
@ -2578,6 +2595,362 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
      }
    }
  }
+
+  /**
+   * Scan for legacy/obsolete files in BMAD installation
+   * @param {string} bmadDir - BMAD installation directory
+   * @returns {Object} Categorized files for cleanup
+   */
+  async scanForLegacyFiles(bmadDir) {
+    const legacyFiles = {
+      backup: [],
+      documentation: [],
+      deprecated_task: [],
+      unknown: [],
+    };
+
+    try {
+      // Load files manifest to understand what should exist
+      const manifestPath = path.join(bmadDir, 'files-manifest.csv');
+      const manifestFiles = new Set();
+
+      if (await fs.pathExists(manifestPath)) {
+        const manifestContent = await fs.readFile(manifestPath, 'utf8');
+        const lines = manifestContent.split('\n').slice(1); // Skip header
+        for (const line of lines) {
+          if (line.trim()) {
+            const relativePath = line.split(',')[0];
+            if (relativePath) {
+              manifestFiles.add(relativePath);
+            }
+          }
+        }
+      }
+
+      // Scan all files recursively
+      const allFiles = await this.getAllFiles(bmadDir);
+
+      for (const filePath of allFiles) {
+        const relativePath = path.relative(bmadDir, filePath);
+
+        // Skip expected files
+        if (this.isExpectedFile(relativePath, manifestFiles)) {
+          continue;
+        }
+
+        // Categorize legacy files
+        if (relativePath.endsWith('.bak')) {
+          legacyFiles.backup.push({
+            path: filePath,
+            relativePath: relativePath,
+            size: (await fs.stat(filePath)).size,
+            mtime: (await fs.stat(filePath)).mtime,
+          });
+        } else if (this.isDocumentationFile(relativePath)) {
+          legacyFiles.documentation.push({
+            path: filePath,
+            relativePath: relativePath,
+            size: (await fs.stat(filePath)).size,
+            mtime: (await fs.stat(filePath)).mtime,
+          });
+        } else if (this.isDeprecatedTaskFile(relativePath)) {
+          const suggestedAlternative = this.suggestAlternative(relativePath);
+          legacyFiles.deprecated_task.push({
+            path: filePath,
+            relativePath: relativePath,
+            size: (await fs.stat(filePath)).size,
+            mtime: (await fs.stat(filePath)).mtime,
+            suggestedAlternative,
+          });
+        } else {
+          legacyFiles.unknown.push({
+            path: filePath,
+            relativePath: relativePath,
+            size: (await fs.stat(filePath)).size,
+            mtime: (await fs.stat(filePath)).mtime,
+          });
+        }
+      }
+    } catch (error) {
+      console.warn(`Warning: Could not scan for legacy files: ${error.message}`);
+    }
+
+    return legacyFiles;
+  }
+
+  /**
+   * Get all files in directory recursively
+   * @param {string} dir - Directory to scan
+   * @returns {Array} Array of file paths
+   */
+  async getAllFiles(dir) {
+    const files = [];
+
+    async function scan(currentDir) {
+      const entries = await fs.readdir(currentDir);
+
+      for (const entry of entries) {
+        const fullPath = path.join(currentDir, entry);
+        const stat = await fs.stat(fullPath);
+
+        if (stat.isDirectory()) {
+          // Skip certain directories
+          if (!['node_modules', '.git', 'dist', 'build'].includes(entry)) {
+            await scan(fullPath);
+          }
+        } else {
+          files.push(fullPath);
+        }
+      }
+    }
+
+    await scan(dir);
+    return files;
+  }
+
+  /**
+   * Check if file is expected in installation
+   * @param {string} relativePath - Relative path from BMAD dir
+   * @param {Set} manifestFiles - Files from manifest
+   * @returns {boolean} True if expected file
+   */
+  isExpectedFile(relativePath, manifestFiles) {
+    // Core files in manifest
+    if (manifestFiles.has(relativePath)) {
+      return true;
+    }
+
+    // Configuration files
+    if (relativePath.startsWith('_cfg/') || relativePath === 'config.yaml') {
+      return true;
+    }
+
+    // Custom files
+    if (relativePath.startsWith('custom/') || relativePath === 'manifest.yaml') {
+      return true;
+    }
+
+    // Generated files
+    if (relativePath === 'manifest.csv' || relativePath === 'files-manifest.csv') {
+      return true;
+    }
+
+    // IDE-specific files
+    const ides = ['vscode', 'cursor', 'windsurf', 'claude-code', 'github-copilot', 'zsh', 'bash', 'fish'];
+    if (ides.some((ide) => relativePath.includes(ide))) {
+      return true;
+    }
+
+    // BMAD MODULE STRUCTURES - recognize valid module content
+    const modulePrefixes = ['bmb/', 'bmm/', 'cis/', 'core/', 'bmgd/'];
+    const validExtensions = ['.yaml', '.yml', '.json', '.csv', '.md', '.xml', '.svg', '.png', '.jpg', '.gif', '.excalidraw', '.js'];
+
+    // Check if this file is in a recognized module directory
+    for (const modulePrefix of modulePrefixes) {
+      if (relativePath.startsWith(modulePrefix)) {
+        // Check if it has a valid extension
+        const hasValidExtension = validExtensions.some((ext) => relativePath.endsWith(ext));
+        if (hasValidExtension) {
+          return true;
+        }
+      }
+    }
+
+    // Special case for core module resources
+    if (relativePath.startsWith('core/resources/')) {
+      return true;
+    }
+
+    // Special case for docs directory
+    if (relativePath.startsWith('docs/')) {
+      return true;
+    }
+
+    return false;
+  }
+
+  /**
+   * Check if file is documentation
+   * @param {string} relativePath - Relative path
+   * @returns {boolean} True if documentation
+   */
+  isDocumentationFile(relativePath) {
+    const docExtensions = ['.md', '.txt', '.pdf'];
+    const docPatterns = ['docs/', 'README', 'CHANGELOG', 'LICENSE'];
+
+    return docExtensions.some((ext) => relativePath.endsWith(ext)) || docPatterns.some((pattern) => relativePath.includes(pattern));
+  }
+
+  /**
+   * Check if file is deprecated task file
+   * @param {string} relativePath - Relative path
+   * @returns {boolean} True if deprecated
+   */
+  isDeprecatedTaskFile(relativePath) {
+    // Known deprecated files
+    const deprecatedFiles = ['adv-elicit-methods.csv', 'game-resources.json', 'ux-workflow.json'];
+
+    return deprecatedFiles.some((dep) => relativePath.includes(dep));
+  }
+
+  /**
+   * Suggest alternative for deprecated file
+   * @param {string} relativePath - Deprecated file path
+   * @returns {string} Suggested alternative
+   */
+  suggestAlternative(relativePath) {
+    const alternatives = {
+      'adv-elicit-methods.csv': 'Use the new structured workflows in src/modules/',
+      'game-resources.json': 'Resources are now integrated into modules',
+      'ux-workflow.json': 'UX workflows are now in src/modules/bmm/workflows/',
+    };
+
+    for (const [deprecated, alternative] of Object.entries(alternatives)) {
+      if (relativePath.includes(deprecated)) {
+        return alternative;
+      }
+    }
+
+    return 'Check src/modules/ for new alternatives';
+  }
+
+  /**
+   * Perform interactive cleanup of legacy files
+   * @param {string} bmadDir - BMAD installation directory
+   * @param {boolean} skipInteractive - Skip interactive prompts
+   * @returns {Object} Cleanup results
+   */
+  async performCleanup(bmadDir, skipInteractive = false) {
+    const inquirer = require('inquirer');
+    const yaml = require('js-yaml');
+
+    // Load user retention preferences
+    const retentionPath = path.join(bmadDir, '_cfg', 'user-retained-files.yaml');
+    let retentionData = { retainedFiles: [], history: [] };
+
+    if (await fs.pathExists(retentionPath)) {
+      const retentionContent = await fs.readFile(retentionPath, 'utf8');
+      retentionData = yaml.load(retentionContent) || retentionData;
+    }
+
+    // Scan for legacy files
+    const legacyFiles = await this.scanForLegacyFiles(bmadDir);
+    const allLegacyFiles = [...legacyFiles.backup, ...legacyFiles.documentation, ...legacyFiles.deprecated_task, ...legacyFiles.unknown];
+
+    if (allLegacyFiles.length === 0) {
+      return { deleted: 0, retained: 0, message: 'No legacy files found' };
+    }
+
+    let deletedCount = 0;
+    let retainedCount = 0;
+    const filesToDelete = [];
+
+    if (skipInteractive) {
+      // Auto-delete all non-retained files
+      for (const file of allLegacyFiles) {
+        if (!retentionData.retainedFiles.includes(file.relativePath)) {
+          filesToDelete.push(file);
+        }
+      }
+    } else {
+      // Interactive cleanup
+      console.log(chalk.cyan('\n🧹 Legacy File Cleanup\n'));
+      console.log(chalk.dim('The following obsolete files were found:\n'));
+
+      // Group files by category
+      const categories = [];
+      if (legacyFiles.backup.length > 0) {
+        categories.push({ name: 'Backup Files (.bak)', files: legacyFiles.backup });
+      }
+      if (legacyFiles.documentation.length > 0) {
+        categories.push({ name: 'Documentation', files: legacyFiles.documentation });
+      }
+      if (legacyFiles.deprecated_task.length > 0) {
+        categories.push({ name: 'Deprecated Task Files', files: legacyFiles.deprecated_task });
+      }
+      if (legacyFiles.unknown.length > 0) {
+        categories.push({ name: 'Unknown Files', files: legacyFiles.unknown });
+      }
+
+      for (const category of categories) {
+        console.log(chalk.yellow(`${category.name}:`));
+        for (const file of category.files) {
+          const size = (file.size / 1024).toFixed(1);
+          const date = file.mtime.toLocaleDateString();
+          let line = `  - ${file.relativePath} (${size}KB, ${date})`;
+          if (file.suggestedAlternative) {
+            line += chalk.dim(` → ${file.suggestedAlternative}`);
+          }
+          console.log(chalk.dim(line));
+        }
+        console.log();
+      }
+
+      const prompt = await inquirer.prompt([
+        {
+          type: 'confirm',
+          name: 'proceed',
+          message: 'Would you like to review these files for cleanup?',
+          default: true,
+        },
+      ]);
+
+      if (!prompt.proceed) {
+        return { deleted: 0, retained: allLegacyFiles.length, message: 'Cleanup cancelled by user' };
+      }
+
+      // Show selection interface
+      const selectionPrompt = await inquirer.prompt([
+        {
+          type: 'checkbox',
+          name: 'filesToDelete',
+          message: 'Select files to delete (use SPACEBAR to select, ENTER to continue):',
+          choices: allLegacyFiles.map((file) => {
+            const isRetained = retentionData.retainedFiles.includes(file.relativePath);
+            const description = `${file.relativePath} (${(file.size / 1024).toFixed(1)}KB)`;
+            return {
+              name: description,
+              value: file,
+              checked: !isRetained && !file.relativePath.includes('.bak'),
+            };
+          }),
+          pageSize: Math.min(allLegacyFiles.length, 15),
+        },
+      ]);
+
+      filesToDelete.push(...selectionPrompt.filesToDelete);
+    }
+
+    // Delete selected files
+    for (const file of filesToDelete) {
+      try {
+        await fs.remove(file.path);
+        deletedCount++;
+      } catch (error) {
+        console.warn(`Warning: Could not delete ${file.relativePath}: ${error.message}`);
+      }
+    }
+
+    // Count retained files
+    retainedCount = allLegacyFiles.length - deletedCount;
+
+    // Update retention data
+    const newlyRetained = allLegacyFiles.filter((f) => !filesToDelete.includes(f)).map((f) => f.relativePath);
+
+    retentionData.retainedFiles = [...new Set([...retentionData.retainedFiles, ...newlyRetained])];
+    retentionData.history.push({
+      date: new Date().toISOString(),
+      deleted: deletedCount,
+      retained: retainedCount,
+      files: filesToDelete.map((f) => f.relativePath),
+    });
+
+    // Save retention data
+    await fs.ensureDir(path.dirname(retentionPath));
+    await fs.writeFile(retentionPath, yaml.dump(retentionData), 'utf8');
+
+    return { deleted: deletedCount, retained: retainedCount };
+  }
 }

 module.exports = { Installer };
--- a/tools/cli/installers/lib/ide/github-copilot.js
+++ b/tools/cli/installers/lib/ide/github-copilot.js
@ -6,13 +6,13 @@ const { AgentCommandGenerator } = require('./shared/agent-command-generator');

 /**
 * GitHub Copilot setup handler
- * Creates chat modes in .github/chatmodes/ and configures VS Code settings
+ * Creates agents in .github/agents/ and configures VS Code settings
 */
 class GitHubCopilotSetup extends BaseIdeSetup {
  constructor() {
    super('github-copilot', 'GitHub Copilot', true); // preferred IDE
    this.configDir = '.github';
-    this.chatmodesDir = 'chatmodes';
+    this.agentsDir = 'agents';
    this.vscodeDir = '.vscode';
  }

@ -50,7 +50,8 @@ class GitHubCopilotSetup extends BaseIdeSetup {
          message: 'Maximum requests per session (1-50)?',
          default: '15',
          validate: (input) => {
-            const num = parseInt(input);
+            const num = parseInt(input, 10);
+            if (isNaN(num)) return 'Enter a valid number 1-50';
            return (num >= 1 && num <= 50) || 'Enter 1-50';
          },
        },
@ -97,10 +98,10 @@ class GitHubCopilotSetup extends BaseIdeSetup {
    const config = options.preCollectedConfig || {};
    await this.configureVsCodeSettings(projectDir, { ...options, ...config });

-    // Create .github/chatmodes directory
+    // Create .github/agents directory
    const githubDir = path.join(projectDir, this.configDir);
-    const chatmodesDir = path.join(githubDir, this.chatmodesDir);
-    await this.ensureDir(chatmodesDir);
+    const agentsDir = path.join(githubDir, this.agentsDir);
+    await this.ensureDir(agentsDir);

    // Clean up any existing BMAD files before reinstalling
    await this.cleanup(projectDir);
@ -109,29 +110,29 @@ class GitHubCopilotSetup extends BaseIdeSetup {
    const agentGen = new AgentCommandGenerator(this.bmadFolderName);
    const { artifacts: agentArtifacts } = await agentGen.collectAgentArtifacts(bmadDir, options.selectedModules || []);

-    // Create chat mode files with bmad- prefix
-    let modeCount = 0;
+    // Create agent files with bmd- prefix
+    let agentCount = 0;
    for (const artifact of agentArtifacts) {
      const content = artifact.content;
-      const chatmodeContent = await this.createChatmodeContent({ module: artifact.module, name: artifact.name }, content);
+      const agentContent = await this.createAgentContent({ module: artifact.module, name: artifact.name }, content);

-      // Use bmad- prefix: bmad-agent-{module}-{name}.chatmode.md
-      const targetPath = path.join(chatmodesDir, `bmad-agent-${artifact.module}-${artifact.name}.chatmode.md`);
-      await this.writeFile(targetPath, chatmodeContent);
-      modeCount++;
+      // Use bmd- prefix: bmd-custom-{module}-{name}.agent.md
+      const targetPath = path.join(agentsDir, `bmd-custom-${artifact.module}-${artifact.name}.agent.md`);
+      await this.writeFile(targetPath, agentContent);
+      agentCount++;

-      console.log(chalk.green(`  ✓ Created chat mode: bmad-agent-${artifact.module}-${artifact.name}`));
+      console.log(chalk.green(`  ✓ Created agent: bmd-custom-${artifact.module}-${artifact.name}`));
    }

    console.log(chalk.green(`✓ ${this.name} configured:`));
-    console.log(chalk.dim(`  - ${modeCount} chat modes created`));
-    console.log(chalk.dim(`  - Chat modes directory: ${path.relative(projectDir, chatmodesDir)}`));
+    console.log(chalk.dim(`  - ${agentCount} agents created`));
+    console.log(chalk.dim(`  - Agents directory: ${path.relative(projectDir, agentsDir)}`));
    console.log(chalk.dim(`  - VS Code settings configured`));
-    console.log(chalk.dim('\n  Chat modes available in VS Code Chat view'));
+    console.log(chalk.dim('\n  Agents available in VS Code Chat view'));

    return {
      success: true,
-      chatmodes: modeCount,
+      agents: agentCount,
      settings: true,
    };
  }
@ -187,9 +188,10 @@ class GitHubCopilotSetup extends BaseIdeSetup {
      // Manual configuration - use pre-collected settings
      const manual = options.manualSettings || {};

+      const maxRequests = parseInt(manual.maxRequests || '15', 10);
      bmadSettings = {
        'chat.agent.enabled': true,
-        'chat.agent.maxRequests': parseInt(manual.maxRequests || 15),
+        'chat.agent.maxRequests': isNaN(maxRequests) ? 15 : maxRequests,
        'github.copilot.chat.agent.runTasks': manual.runTasks === undefined ? true : manual.runTasks,
        'chat.mcp.discovery.enabled': manual.mcpDiscovery === undefined ? true : manual.mcpDiscovery,
        'github.copilot.chat.agent.autoFix': manual.autoFix === undefined ? true : manual.autoFix,
@ -206,9 +208,9 @@ class GitHubCopilotSetup extends BaseIdeSetup {
  }

  /**
-   * Create chat mode content
+   * Create agent content
   */
-  async createChatmodeContent(agent, content) {
+  async createAgentContent(agent, content) {
    // Extract metadata from launcher frontmatter if present
    const descMatch = content.match(/description:\s*"([^"]+)"/);
    const title = descMatch ? descMatch[1] : this.formatTitle(agent.name);
@ -226,30 +228,21 @@ class GitHubCopilotSetup extends BaseIdeSetup {
    // Reference: https://code.visualstudio.com/docs/copilot/reference/copilot-vscode-features#_chat-tools
    const tools = [
      'changes', // List of source control changes
-      'codebase', // Perform code search in workspace
-      'createDirectory', // Create new directory in workspace
-      'createFile', // Create new file in workspace
-      'editFiles', // Apply edits to files in workspace
+      'edit', // Edit files in your workspace including: createFile, createDirectory, editNotebook, newJupyterNotebook and editFiles
      'fetch', // Fetch content from web page
-      'fileSearch', // Search files using glob patterns
      'githubRepo', // Perform code search in GitHub repo
-      'listDirectory', // List files in a directory
      'problems', // Add workspace issues from Problems panel
-      'readFile', // Read content of a file in workspace
-      'runInTerminal', // Run shell command in integrated terminal
-      'runTask', // Run existing task in workspace
+      'runCommands', // Runs commands in the terminal including: getTerminalOutput, terminalSelection, terminalLastCommand and runInTerminal
+      'runTasks', // Runs tasks and gets their output for your workspace
      'runTests', // Run unit tests in workspace
-      'runVscodeCommand', // Run VS Code command
-      'search', // Enable file searching in workspace
-      'searchResults', // Get search results from Search view
-      'terminalLastCommand', // Get last terminal command and output
-      'terminalSelection', // Get current terminal selection
+      'search', // Search and read files in your workspace, including:fileSearch, textSearch, listDirectory, readFile, codebase and searchResults
+      'runSubagent', // Runs a task within an isolated subagent context. Enables efficient organization of tasks and context window management.
      'testFailure', // Get unit test failure information
-      'textSearch', // Find text in files
+      'todos', // Tool for managing and tracking todo items for task planning
      'usages', // Find references and navigate definitions
    ];

-    let chatmodeContent = `---
+    let agentContent = `---
 description: "${description.replaceAll('"', String.raw`\"`)}"
 tools: ${JSON.stringify(tools)}
 ---
@ -260,7 +253,7 @@ ${cleanContent}

 `;

-    return chatmodeContent;
+    return agentContent;
  }

  /**
@ -278,10 +271,10 @@ ${cleanContent}
   */
  async cleanup(projectDir) {
    const fs = require('fs-extra');
-    const chatmodesDir = path.join(projectDir, this.configDir, this.chatmodesDir);

+    // Clean up old chatmodes directory
+    const chatmodesDir = path.join(projectDir, this.configDir, 'chatmodes');
    if (await fs.pathExists(chatmodesDir)) {
-      // Only remove files that start with bmad- prefix
      const files = await fs.readdir(chatmodesDir);
      let removed = 0;

@ -293,7 +286,25 @@ ${cleanContent}
      }

      if (removed > 0) {
-        console.log(chalk.dim(`  Cleaned up ${removed} existing BMAD chat modes`));
+        console.log(chalk.dim(`  Cleaned up ${removed} old BMAD chat modes`));
+      }
+    }
+
+    // Clean up new agents directory
+    const agentsDir = path.join(projectDir, this.configDir, this.agentsDir);
+    if (await fs.pathExists(agentsDir)) {
+      const files = await fs.readdir(agentsDir);
+      let removed = 0;
+
+      for (const file of files) {
+        if (file.startsWith('bmd-') && file.endsWith('.agent.md')) {
+          await fs.remove(path.join(agentsDir, file));
+          removed++;
+        }
+      }
+
+      if (removed > 0) {
+        console.log(chalk.dim(`  Cleaned up ${removed} existing BMAD agents`));
      }
    }
  }
@ -307,13 +318,13 @@ ${cleanContent}
   * @returns {Object|null} Info about created command
   */
  async installCustomAgentLauncher(projectDir, agentName, agentPath, metadata) {
-    const chatmodesDir = path.join(projectDir, this.configDir, this.chatmodesDir);
+    const agentsDir = path.join(projectDir, this.configDir, this.agentsDir);

    if (!(await this.exists(path.join(projectDir, this.configDir)))) {
      return null; // IDE not configured for this project
    }

-    await this.ensureDir(chatmodesDir);
+    await this.ensureDir(agentsDir);

    const launcherContent = `You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

@ -353,7 +364,7 @@ ${cleanContent}
      'usages',
    ];

-    const chatmodeContent = `---
+    const agentContent = `---
 description: "Activates the ${metadata.title || agentName} agent persona."
 tools: ${JSON.stringify(copilotTools)}
 ---
@ -363,12 +374,12 @@ tools: ${JSON.stringify(copilotTools)}
 ${launcherContent}
 `;

-    const chatmodePath = path.join(chatmodesDir, `bmad-agent-custom-${agentName}.chatmode.md`);
-    await this.writeFile(chatmodePath, chatmodeContent);
+    const agentFilePath = path.join(agentsDir, `bmd-custom-${agentName}.agent.md`);
+    await this.writeFile(agentFilePath, agentContent);

    return {
-      path: chatmodePath,
-      command: `bmad-agent-custom-${agentName}`,
+      path: agentFilePath,
+      command: `bmd-custom-${agentName}`,
    };
  }
 }
--- a/tools/cli/installers/lib/ide/kilo.js
+++ b/tools/cli/installers/lib/ide/kilo.js
@ -123,6 +123,9 @@ class KiloSetup extends BaseIdeSetup {
    modeEntry += `   groups:\n`;
    modeEntry += `    - read\n`;
    modeEntry += `    - edit\n`;
+    modeEntry += `    - browser\n`;
+    modeEntry += `    - command\n`;
+    modeEntry += `    - mcp\n`;

    return modeEntry;
  }
--- a/tools/cli/lib/ui.js
+++ b/tools/cli/lib/ui.js
@ -720,8 +720,8 @@ class UI {
      {
        type: 'confirm',
        name: 'enableTts',
-        message: 'Enable AgentVibes TTS? (Claude Code only - Agents speak with unique voices in party mode)',
-        default: true, // Default to yes - recommended for best experience
+        message: 'Enable Agents to Speak Out loud (powered by Agent Vibes? Claude Code only currently)',
+        default: false, // Default to yes - recommended for best experience
      },
    ]);
Author	SHA1	Message	Date
Mario Semper	e02e1d9c01	Merge `12e0840c62` into `355ccebca2`	2025-11-27 17:44:02 -05:00
Brian Madison	355ccebca2	workflow-status can call workflow init	2025-11-26 19:48:47 -06:00
Brian Madison	dfc35f35f8	BMad Agents menu items are logically ordered and marked with optional or recommended and some required tags	2025-11-26 18:22:24 -06:00
Brian Madison	677c000820	github uses agents folder now instead of chatmodes	2025-11-26 17:46:26 -06:00
Brian Madison	3ac539b61f	npm vulnerabilities resolved	2025-11-26 17:07:09 -06:00
Brian Madison	331a67eeb3	installer allows cleanup of unneeded files in upgrades	2025-11-26 16:47:15 -06:00
Brian Madison	fbdb91b991	standard greenfield workflow updated diagrams	2025-11-26 15:14:34 -06:00
Jorge Castillo	54e6745a55	fix: update GitHub Copilot tools names for consistency (#880 ) Copilot was triggering warning or errors in the chatmode files due to some changes in tool names. - findTestFiles is internal tool, cannot be used. - Other tools have change names. - Added new tools: todos and runSubAgents. Co-authored-by: Brian <bmadcode@gmail.com>	2025-11-26 14:49:17 -06:00
Serhii	f793cf8fcd	fix: add radix parameter to parseInt() calls (#862 ) Add explicit radix=10 to parseInt() calls and NaN validation to prevent unexpected hex parsing and invalid config values. Changes: - Line 52: Add radix and NaN check in input validation - Line 189-192: Add radix and NaN fallback for config parsing Fixes potential issues: - Hex input (0x10) now rejected instead of parsed as 16 - Invalid strings return default value instead of NaN→null 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Brian <bmadcode@gmail.com>	2025-11-26 14:44:12 -06:00
fikri-kompanion	9223e2be21	fix: give kilocode tool access to bmad modes (#961 ) Co-authored-by: Ahmad Fikrizaman <ahmadfikrizaman@gmail.com> Co-authored-by: Brian <bmadcode@gmail.com>	2025-11-26 13:48:16 -06:00
Mario Semper	12e0840c62	feat: Agent Task Pre-Flight Protocol - Safety framework for high-risk tasks Introduces mandatory safety checks for high-risk agent tasks (marketing, legal, deployment) to prevent factual errors, trademark violations, and privacy breaches. Key features: - Mandatory verification before high-risk outputs - Cross-agent fact-checking - Critical guidelines framework - User approval gates Origin: Lessons from tellingCube project Prevents: Wrong pricing, trademark violations, privacy leaks, feature hallucinations Includes: CRITICAL-GUIDELINES.md template and implementation examples	2025-11-23 02:24:24 +01:00
Mario Semper	10dc25f43d	feat: Ring of Fire (ROF) Sessions - Multi-agent parallel collaboration Introduces Ring of Fire Sessions feature for BMad Method, enabling multi-agent collaborative sessions that run in parallel to user workflow. Key features: - User-controlled scope (2 agents/5min to 10 agents/2hrs) - Approval-gated tool access for safety - Flexible reporting (brief/detailed/live) - Parallel workflow support Origin: tellingCube project (masemIT e.U.) Real-world validated with successful multi-agent planning sessions. Command: *rof "<topic>" --agents <list> [--report mode]	2025-11-23 02:22:21 +01:00