bmad-method 4.37.0 → 4.39.0

package/dist/agents/bmad-orchestrator.txt

@@ -53,7 +53,6 @@ activation-instructions:
   - Assess user goal against available agents and workflows in this bundle
   - If clear match to an agent's expertise, suggest transformation with *agent command
   - If project-oriented, suggest *workflow-guidance to explore options
-  - Load resources only when needed - never pre-load
 agent:
   name: BMad Orchestrator
   id: bmad-orchestrator
@@ -77,21 +76,21 @@ persona:
     - Always remind users that commands require * prefix
 commands:
   help: Show this guide with available agents and workflows
+  agent: Transform into a specialized agent (list if name not specified)
   chat-mode: Start conversational mode for detailed assistance
+  checklist: Execute a checklist (list if name not specified)
+  doc-out: Output full document
   kb-mode: Load full BMad knowledge base
+  party-mode: Group chat with all agents
+  plan: Create detailed workflow plan before starting
+  plan-status: Show current workflow plan progress
+  plan-update: Update workflow plan status
   status: Show current context, active agent, and progress
-  agent: Transform into a specialized agent (list if name not specified)
-  exit: Return to BMad or exit session
   task: Run a specific task (list if name not specified)
   workflow: Start a specific workflow (list if name not specified)
   workflow-guidance: Get personalized help selecting the right workflow
-  plan: Create detailed workflow plan before starting
-  plan-status: Show current workflow plan progress
-  plan-update: Update workflow plan status
-  checklist: Execute a checklist (list if name not specified)
   yolo: Toggle skip confirmations mode
-  party-mode: Group chat with all agents
-  doc-out: Output full document
+  exit: Return to BMad or exit session
 help-display-template: |
   === BMad Orchestrator Commands ===
   All commands must start with * (asterisk)
@@ -160,13 +159,13 @@ workflow-guidance:
   - Only recommend workflows that actually exist in the current bundle
   - When *workflow-guidance is called, start an interactive session and list all available workflows with brief descriptions
 dependencies:
+  data:
+    - bmad-kb.md
+    - elicitation-methods.md
   tasks:
     - advanced-elicitation.md
     - create-doc.md
     - kb-mode-interaction.md
-  data:
-    - bmad-kb.md
-    - elicitation-methods.md
   utils:
     - workflow-management.md
 ```
@@ -405,7 +404,7 @@ Provide a user-friendly interface to the BMad knowledge base without overwhelmin
 
 ## Instructions
 
-When entering KB mode (*kb-mode), follow these steps:
+When entering KB mode (\*kb-mode), follow these steps:
 
 ### 1. Welcome and Guide
 
@@ -447,12 +446,12 @@ Or ask me about anything else related to BMad-Method!
 When user is done or wants to exit KB mode:
 
 - Summarize key points discussed if helpful
-- Remind them they can return to KB mode anytime with *kb-mode
+- Remind them they can return to KB mode anytime with \*kb-mode
 - Suggest next steps based on what was discussed
 
 ## Example Interaction
 
-**User**: *kb-mode
+**User**: \*kb-mode
 
 **Assistant**: I've entered KB mode and have access to the full BMad knowledge base. I can help you with detailed information about any aspect of BMad-Method.
 
@@ -775,7 +774,7 @@ You are the "Vibe CEO" - thinking like a CEO with unlimited resources and a sing
 
 - **Claude Code**: `/agent-name` (e.g., `/bmad-master`)
 - **Cursor**: `@agent-name` (e.g., `@bmad-master`)
-- **Windsurf**: `@agent-name` (e.g., `@bmad-master`)
+- **Windsurf**: `/agent-name` (e.g., `/bmad-master`)
 - **Trae**: `@agent-name` (e.g., `@bmad-master`)
 - **Roo Code**: Select mode from mode selector (e.g., `bmad-master`)
 - **GitHub Copilot**: Open the Chat view (`⌃⌘I` on Mac, `Ctrl+Alt+I` on Windows/Linux) and select **Agent** from the chat mode selector.
@@ -1019,7 +1018,7 @@ Each status change requires user verification and approval before proceeding.
 #### Greenfield Development
 
 - Business analysis and market research
-- Product requirements and feature definition  
+- Product requirements and feature definition
 - System architecture and design
 - Development execution
 - Testing and deployment
@@ -1128,8 +1127,11 @@ Templates with Level 2 headings (`##`) can be automatically sharded:
 
 ```markdown
 ## Goals and Background Context
-## Requirements  
+
+## Requirements
+
 ## User Interface Design Goals
+
 ## Success Metrics
 ```
 
@@ -1286,16 +1288,19 @@ Use the **expansion-creator** pack to build your own:
 ## Core Reflective Methods
 
 **Expand or Contract for Audience**
+
 - Ask whether to 'expand' (add detail, elaborate) or 'contract' (simplify, clarify)
 - Identify specific target audience if relevant
 - Tailor content complexity and depth accordingly
 
 **Explain Reasoning (CoT Step-by-Step)**
+
 - Walk through the step-by-step thinking process
 - Reveal underlying assumptions and decision points
 - Show how conclusions were reached from current role's perspective
 
 **Critique and Refine**
+
 - Review output for flaws, inconsistencies, or improvement areas
 - Identify specific weaknesses from role's expertise
 - Suggest refined version reflecting domain knowledge
@@ -1303,12 +1308,14 @@ Use the **expansion-creator** pack to build your own:
 ## Structural Analysis Methods
 
 **Analyze Logical Flow and Dependencies**
+
 - Examine content structure for logical progression
 - Check internal consistency and coherence
 - Identify and validate dependencies between elements
 - Confirm effective ordering and sequencing
 
 **Assess Alignment with Overall Goals**
+
 - Evaluate content contribution to stated objectives
 - Identify any misalignments or gaps
 - Interpret alignment from specific role's perspective
@@ -1317,12 +1324,14 @@ Use the **expansion-creator** pack to build your own:
 ## Risk and Challenge Methods
 
 **Identify Potential Risks and Unforeseen Issues**
+
 - Brainstorm potential risks from role's expertise
 - Identify overlooked edge cases or scenarios
 - Anticipate unintended consequences
 - Highlight implementation challenges
 
 **Challenge from Critical Perspective**
+
 - Adopt critical stance on current content
 - Play devil's advocate from specified viewpoint
 - Argue against proposal highlighting weaknesses
@@ -1331,12 +1340,14 @@ Use the **expansion-creator** pack to build your own:
 ## Creative Exploration Methods
 
 **Tree of Thoughts Deep Dive**
+
 - Break problem into discrete "thoughts" or intermediate steps
 - Explore multiple reasoning paths simultaneously
 - Use self-evaluation to classify each path as "sure", "likely", or "impossible"
 - Apply search algorithms (BFS/DFS) to find optimal solution paths
 
 **Hindsight is 20/20: The 'If Only...' Reflection**
+
 - Imagine retrospective scenario based on current content
 - Identify the one "if only we had known/done X..." insight
 - Describe imagined consequences humorously or dramatically
@@ -1345,6 +1356,7 @@ Use the **expansion-creator** pack to build your own:
 ## Multi-Persona Collaboration Methods
 
 **Agile Team Perspective Shift**
+
 - Rotate through different Scrum team member viewpoints
 - Product Owner: Focus on user value and business impact
 - Scrum Master: Examine process flow and team dynamics
@@ -1352,12 +1364,14 @@ Use the **expansion-creator** pack to build your own:
 - QA: Identify testing scenarios and quality concerns
 
 **Stakeholder Round Table**
+
 - Convene virtual meeting with multiple personas
 - Each persona contributes unique perspective on content
 - Identify conflicts and synergies between viewpoints
 - Synthesize insights into actionable recommendations
 
 **Meta-Prompting Analysis**
+
 - Step back to analyze the structure and logic of current approach
 - Question the format and methodology being used
 - Suggest alternative frameworks or mental models
@@ -1366,24 +1380,28 @@ Use the **expansion-creator** pack to build your own:
 ## Advanced 2025 Techniques
 
 **Self-Consistency Validation**
+
 - Generate multiple reasoning paths for same problem
 - Compare consistency across different approaches
 - Identify most reliable and robust solution
 - Highlight areas where approaches diverge and why
 
 **ReWOO (Reasoning Without Observation)**
+
 - Separate parametric reasoning from tool-based actions
 - Create reasoning plan without external dependencies
 - Identify what can be solved through pure reasoning
 - Optimize for efficiency and reduced token usage
 
 **Persona-Pattern Hybrid**
+
 - Combine specific role expertise with elicitation pattern
 - Architect + Risk Analysis: Deep technical risk assessment
 - UX Expert + User Journey: End-to-end experience critique
 - PM + Stakeholder Analysis: Multi-perspective impact review
 
 **Emergent Collaboration Discovery**
+
 - Allow multiple perspectives to naturally emerge
 - Identify unexpected insights from persona interactions
 - Explore novel combinations of viewpoints
@@ -1392,18 +1410,21 @@ Use the **expansion-creator** pack to build your own:
 ## Game-Based Elicitation Methods
 
 **Red Team vs Blue Team**
+
 - Red Team: Attack the proposal, find vulnerabilities
 - Blue Team: Defend and strengthen the approach
 - Competitive analysis reveals blind spots
 - Results in more robust, battle-tested solutions
 
 **Innovation Tournament**
+
 - Pit multiple alternative approaches against each other
 - Score each approach across different criteria
 - Crowd-source evaluation from different personas
 - Identify winning combination of features
 
 **Escape Room Challenge**
+
 - Present content as constraints to work within
 - Find creative solutions within tight limitations
 - Identify minimum viable approach
@@ -1412,6 +1433,7 @@ Use the **expansion-creator** pack to build your own:
 ## Process Control
 
 **Proceed / No Further Actions**
+
 - Acknowledge choice to finalize current work
 - Accept output as-is or move to next step
 - Prepare to continue without additional elicitation

package/dist/agents/dev.txt

@@ -69,9 +69,6 @@ core_principles:
   - Numbered Options - Always use numbered lists when presenting choices to the user
 commands:
   - help: Show numbered list of the following commands to allow selection
-  - run-tests: Execute linting and tests
-  - explain: teach me what and why you did whatever you just did in detail so I can learn. Explain to me as if you were training a junior engineer.
-  - exit: Say goodbye as the Developer, and then abandon inhabiting this persona
   - develop-story:
       - order-of-execution: Read (first or next) task→Implement Task and its subtasks→Write tests→Execute validations→Only if ALL pass, then update the task checkbox with [x]→Update story section File List to ensure it lists and new or modified or deleted source file→repeat order-of-execution until complete
       - story-file-updates-ONLY:
@@ -81,15 +78,171 @@ commands:
       - blocking: 'HALT for: Unapproved deps needed, confirm with user | Ambiguous after story check | 3 failures attempting to implement or fix something repeatedly | Missing config | Failing regression'
       - ready-for-review: Code matches requirements + All validations pass + Follows standards + File List complete
       - completion: 'All Tasks and Subtasks marked [x] and have tests→Validations and full regression passes (DON''T BE LAZY, EXECUTE ALL TESTS and CONFIRM)→Ensure File List is Complete→run the task execute-checklist for the checklist story-dod-checklist→set story status: ''Ready for Review''→HALT'
+  - explain: teach me what and why you did whatever you just did in detail so I can learn. Explain to me as if you were training a junior engineer.
+  - review-qa: run task `apply-qa-fixes.md'
+  - run-tests: Execute linting and tests
+  - exit: Say goodbye as the Developer, and then abandon inhabiting this persona
 dependencies:
+  checklists:
+    - story-dod-checklist.md
   tasks:
+    - apply-qa-fixes.md
     - execute-checklist.md
     - validate-next-story.md
-  checklists:
-    - story-dod-checklist.md
 ```
 ==================== END: .bmad-core/agents/dev.md ====================
 
+==================== START: .bmad-core/tasks/apply-qa-fixes.md ====================
+# apply-qa-fixes
+
+Implement fixes based on QA results (gate and assessments) for a specific story. This task is for the Dev agent to systematically consume QA outputs and apply code/test changes while only updating allowed sections in the story file.
+
+## Purpose
+
+- Read QA outputs for a story (gate YAML + assessment markdowns)
+- Create a prioritized, deterministic fix plan
+- Apply code and test changes to close gaps and address issues
+- Update only the allowed story sections for the Dev agent
+
+## Inputs
+
+```yaml
+required:
+  - story_id: '{epic}.{story}' # e.g., "2.2"
+  - qa_root: from `bmad-core/core-config.yaml` key `qa.qaLocation` (e.g., `docs/project/qa`)
+  - story_root: from `bmad-core/core-config.yaml` key `devStoryLocation` (e.g., `docs/project/stories`)
+
+optional:
+  - story_title: '{title}' # derive from story H1 if missing
+  - story_slug: '{slug}' # derive from title (lowercase, hyphenated) if missing
+```
+
+## QA Sources to Read
+
+- Gate (YAML): `{qa_root}/gates/{epic}.{story}-*.yml`
+  - If multiple, use the most recent by modified time
+- Assessments (Markdown):
+  - Test Design: `{qa_root}/assessments/{epic}.{story}-test-design-*.md`
+  - Traceability: `{qa_root}/assessments/{epic}.{story}-trace-*.md`
+  - Risk Profile: `{qa_root}/assessments/{epic}.{story}-risk-*.md`
+  - NFR Assessment: `{qa_root}/assessments/{epic}.{story}-nfr-*.md`
+
+## Prerequisites
+
+- Repository builds and tests run locally (Deno 2)
+- Lint and test commands available:
+  - `deno lint`
+  - `deno test -A`
+
+## Process (Do not skip steps)
+
+### 0) Load Core Config & Locate Story
+
+- Read `bmad-core/core-config.yaml` and resolve `qa_root` and `story_root`
+- Locate story file in `{story_root}/{epic}.{story}.*.md`
+  - HALT if missing and ask for correct story id/path
+
+### 1) Collect QA Findings
+
+- Parse the latest gate YAML:
+  - `gate` (PASS|CONCERNS|FAIL|WAIVED)
+  - `top_issues[]` with `id`, `severity`, `finding`, `suggested_action`
+  - `nfr_validation.*.status` and notes
+  - `trace` coverage summary/gaps
+  - `test_design.coverage_gaps[]`
+  - `risk_summary.recommendations.must_fix[]` (if present)
+- Read any present assessment markdowns and extract explicit gaps/recommendations
+
+### 2) Build Deterministic Fix Plan (Priority Order)
+
+Apply in order, highest priority first:
+
+1. High severity items in `top_issues` (security/perf/reliability/maintainability)
+2. NFR statuses: all FAIL must be fixed → then CONCERNS
+3. Test Design `coverage_gaps` (prioritize P0 scenarios if specified)
+4. Trace uncovered requirements (AC-level)
+5. Risk `must_fix` recommendations
+6. Medium severity issues, then low
+
+Guidance:
+
+- Prefer tests closing coverage gaps before/with code changes
+- Keep changes minimal and targeted; follow project architecture and TS/Deno rules
+
+### 3) Apply Changes
+
+- Implement code fixes per plan
+- Add missing tests to close coverage gaps (unit first; integration where required by AC)
+- Keep imports centralized via `deps.ts` (see `docs/project/typescript-rules.md`)
+- Follow DI boundaries in `src/core/di.ts` and existing patterns
+
+### 4) Validate
+
+- Run `deno lint` and fix issues
+- Run `deno test -A` until all tests pass
+- Iterate until clean
+
+### 5) Update Story (Allowed Sections ONLY)
+
+CRITICAL: Dev agent is ONLY authorized to update these sections of the story file. Do not modify any other sections (e.g., QA Results, Story, Acceptance Criteria, Dev Notes, Testing):
+
+- Tasks / Subtasks Checkboxes (mark any fix subtask you added as done)
+- Dev Agent Record →
+  - Agent Model Used (if changed)
+  - Debug Log References (commands/results, e.g., lint/tests)
+  - Completion Notes List (what changed, why, how)
+  - File List (all added/modified/deleted files)
+- Change Log (new dated entry describing applied fixes)
+- Status (see Rule below)
+
+Status Rule:
+
+- If gate was PASS and all identified gaps are closed → set `Status: Ready for Done`
+- Otherwise → set `Status: Ready for Review` and notify QA to re-run the review
+
+### 6) Do NOT Edit Gate Files
+
+- Dev does not modify gate YAML. If fixes address issues, request QA to re-run `review-story` to update the gate
+
+## Blocking Conditions
+
+- Missing `bmad-core/core-config.yaml`
+- Story file not found for `story_id`
+- No QA artifacts found (neither gate nor assessments)
+  - HALT and request QA to generate at least a gate file (or proceed only with clear developer-provided fix list)
+
+## Completion Checklist
+
+- deno lint: 0 problems
+- deno test -A: all tests pass
+- All high severity `top_issues` addressed
+- NFR FAIL → resolved; CONCERNS minimized or documented
+- Coverage gaps closed or explicitly documented with rationale
+- Story updated (allowed sections only) including File List and Change Log
+- Status set according to Status Rule
+
+## Example: Story 2.2
+
+Given gate `docs/project/qa/gates/2.2-*.yml` shows
+
+- `coverage_gaps`: Back action behavior untested (AC2)
+- `coverage_gaps`: Centralized dependencies enforcement untested (AC4)
+
+Fix plan:
+
+- Add a test ensuring the Toolkit Menu "Back" action returns to Main Menu
+- Add a static test verifying imports for service/view go through `deps.ts`
+- Re-run lint/tests and update Dev Agent Record + File List accordingly
+
+## Key Principles
+
+- Deterministic, risk-first prioritization
+- Minimal, maintainable changes
+- Tests validate behavior and close gaps
+- Strict adherence to allowed story update areas
+- Gate ownership remains with QA; Dev signals readiness via Status
+==================== END: .bmad-core/tasks/apply-qa-fixes.md ====================
+
 ==================== START: .bmad-core/tasks/execute-checklist.md ====================
 # Checklist Validation Task
 
@@ -102,7 +255,6 @@ If the user asks or does not specify a specific checklist, list the checklists a
 ## Instructions
 
 1. **Initial Assessment**
-
    - If user or the task being run provides a checklist name:
      - Try fuzzy matching (e.g. "architecture checklist" -> "architect-checklist")
      - If multiple matches found, ask user to clarify
@@ -115,14 +267,12 @@ If the user asks or does not specify a specific checklist, list the checklists a
      - All at once (YOLO mode - recommended for checklists, there will be a summary of sections at the end to discuss)
 
 2. **Document and Artifact Gathering**
-
    - Each checklist will specify its required documents/artifacts at the beginning
    - Follow the checklist's specific instructions for what to gather, generally a file can be resolved in the docs folder, if not or unsure, halt and ask or confirm with the user.
 
 3. **Checklist Processing**
 
    If in interactive mode:
-
    - Work through each section of the checklist one at a time
    - For each section:
      - Review all items in the section following instructions for that section embedded in the checklist
@@ -131,7 +281,6 @@ If the user asks or does not specify a specific checklist, list the checklists a
      - Get user confirmation before proceeding to next section or if any thing major do we need to halt and take corrective action
 
    If in YOLO mode:
-
    - Process all sections at once
    - Create a comprehensive report of all findings
    - Present the complete analysis to the user
@@ -139,7 +288,6 @@ If the user asks or does not specify a specific checklist, list the checklists a
 4. **Validation Approach**
 
    For each checklist item:
-
    - Read and understand the requirement
    - Look for evidence in the documentation that satisfies the requirement
    - Consider both explicit mentions and implicit coverage
@@ -153,7 +301,6 @@ If the user asks or does not specify a specific checklist, list the checklists a
 5. **Section Analysis**
 
    For each section:
-
    - think step by step to calculate pass rate
    - Identify common themes in failed items
    - Provide specific recommendations for improvement
@@ -163,7 +310,6 @@ If the user asks or does not specify a specific checklist, list the checklists a
 6. **Final Report**
 
    Prepare a summary that includes:
-
    - Overall checklist completion status
    - Pass rates by section
    - List of failed items with context
@@ -351,14 +497,12 @@ The goal is quality delivery, not just checking boxes.]]
 1. **Requirements Met:**
 
    [[LLM: Be specific - list each requirement and whether it's complete]]
-
    - [ ] All functional requirements specified in the story are implemented.
    - [ ] All acceptance criteria defined in the story are met.
 
 2. **Coding Standards & Project Structure:**
 
    [[LLM: Code quality matters for maintainability. Check each item carefully]]
-
    - [ ] All new/modified code strictly adheres to `Operational Guidelines`.
    - [ ] All new/modified code aligns with `Project Structure` (file locations, naming, etc.).
    - [ ] Adherence to `Tech Stack` for technologies/versions used (if story introduces or modifies tech usage).
@@ -370,7 +514,6 @@ The goal is quality delivery, not just checking boxes.]]
 3. **Testing:**
 
    [[LLM: Testing proves your code works. Be honest about test coverage]]
-
    - [ ] All required unit tests as per the story and `Operational Guidelines` Testing Strategy are implemented.
    - [ ] All required integration tests (if applicable) as per the story and `Operational Guidelines` Testing Strategy are implemented.
    - [ ] All tests (unit, integration, E2E if applicable) pass successfully.
@@ -379,14 +522,12 @@ The goal is quality delivery, not just checking boxes.]]
 4. **Functionality & Verification:**
 
    [[LLM: Did you actually run and test your code? Be specific about what you tested]]
-
    - [ ] Functionality has been manually verified by the developer (e.g., running the app locally, checking UI, testing API endpoints).
    - [ ] Edge cases and potential error conditions considered and handled gracefully.
 
 5. **Story Administration:**
 
    [[LLM: Documentation helps the next developer. What should they know?]]
-
    - [ ] All tasks within the story file are marked as complete.
    - [ ] Any clarifications or decisions made during development are documented in the story file or linked appropriately.
    - [ ] The story wrap up section has been completed with notes of changes or information relevant to the next story or overall project, the agent model that was primarily used during development, and the changelog of any changes is properly updated.
@@ -394,7 +535,6 @@ The goal is quality delivery, not just checking boxes.]]
 6. **Dependencies, Build & Configuration:**
 
    [[LLM: Build issues block everyone. Ensure everything compiles and runs cleanly]]
-
    - [ ] Project builds successfully without errors.
    - [ ] Project linting passes
    - [ ] Any new dependencies added were either pre-approved in the story requirements OR explicitly approved by the user during development (approval documented in story file).
@@ -405,7 +545,6 @@ The goal is quality delivery, not just checking boxes.]]
 7. **Documentation (If Applicable):**
 
    [[LLM: Good documentation prevents future confusion. What needs explaining?]]
-
    - [ ] Relevant inline code documentation (e.g., JSDoc, TSDoc, Python docstrings) for new public APIs or complex logic is complete.
    - [ ] User-facing documentation updated, if changes impact users.
    - [ ] Technical documentation (e.g., READMEs, system diagrams) updated if significant architectural changes were made.