This commit integrates the story-pipeline workflow (PR #1194) with autonomous-epic
and adds post-implementation validation to catch false positives.
MAJOR CHANGES:
1. Merged story-pipeline workflow from upstream PR #1194 (20 files, 4,564 additions)
2. Added post-validation step (step-05b) between implementation and code review
3. Integrated story-pipeline as the default workflow for autonomous-epic
4. Replaced super-dev-story with story-pipeline in batch mode
NEW FEATURES:
- Post-implementation validation (step-05b-post-validation.md)
* Verifies completed tasks against actual codebase
* Catches false positives (tasks marked done but not implemented)
* Re-runs implementation if gaps found
* Uses Glob/Grep/Read to verify file existence and completeness
BENEFITS:
- Token efficiency: 25-30K per story (vs 100-150K with super-dev-story)
- 65% token savings per story, 75% savings per epic
- All super-dev-story quality gates PLUS post-validation
- Checkpoint/resume capability for long stories
- Batch mode for fully unattended execution
ARCHITECTURE:
- autonomous-epic orchestrates epic-level processing
- story-pipeline handles single-story lifecycle (9 steps including 5b)
- Role-switching in same session (vs separate workflow calls)
- Single session per story = massive token savings
TIME ESTIMATES (updated):
- Small epic (3-5 stories): 2-4 hours (was 3-6 hours)
- Medium epic (6-10 stories): 4-8 hours (was 6-12 hours)
- Large epic (11+ stories): 8-16 hours (was 12-24 hours)
FILES MODIFIED:
- autonomous-epic/instructions.xml (integrated story-pipeline)
- autonomous-epic/workflow.yaml (updated settings, removed super-dev choice)
- story-pipeline/* (20 new files from PR #1194)
- story-pipeline/steps/step-05-implement.md (points to step-05b)
- story-pipeline/workflow.md (added step 5b to map and gates)
- story-pipeline/workflow.yaml (added step 5b definition)
- story-pipeline/templates/*.yaml → *.yaml.template (renamed to avoid linting)
FILES ADDED:
- story-pipeline/steps/step-05b-post-validation.md (NEW)
- INTEGRATION-NOTES.md (comprehensive documentation)
TESTING:
- PR #1194 validated with real User Invitation system story
- 17 files, 2,800+ lines generated successfully
- Context exhaustion recovery tested
See INTEGRATION-NOTES.md for full details.
Co-authored-by: tjetzinger (story-pipeline PR #1194)
- Add create-story-with-gap-analysis workflow for verified codebase scanning at planning time
- Fix autonomous-epic to support parallel execution (no auto-branch creation)
- Fix autonomous-epic and super-dev-story to auto-accept gap analysis in autonomous mode
- Fix push-all to support targeted file commits (safe for parallel agents)
- Update dev-story and super-dev-story to pass auto_accept_gap_analysis parameter
- Add explicit autonomous mode instructions to workflows
Breaking changes: None - all enhancements are backward compatible
- Each story now commits and pushes after completion
- Auto-generated commit messages per story
- Safety checks run before each push
- Continues on push failures (doesn't halt entire epic)
- All changes backed up to remote incrementally
Ensures epic progress is saved to remote as work completes
- New /push-all workflow for commit and push with safety
- Can be used anywhere (not just in super-dev-story)
- Comprehensive safety checks (secrets, API keys, large files)
- Smart commit message generation (conventional commits)
- Handles push failures (rebase, upstream, auth)
- Registered in Dev and SM agent menus
- Also integrated into super-dev-story Step 11
Applies to both BMM and BMGD modules
- New /autonomous-epic command processes entire epic
- Just-in-time planning: creates each story before developing
- Auto-develops using super-dev-story or dev-story
- Progress tracking with resume capability
- Git commits after each story completion
- Error handling with retry logic and continue-on-failure
- Epic completion report with statistics
- Estimated: 100K-150K tokens per story
Use cases:
- Overnight epic completion
- CI/CD integration
- Batch sprint processing
Applies to both BMM and BMGD modules
- New /super-dev-story command for comprehensive validation
- Includes all dev-story steps PLUS:
- Step 9.5: Post-dev gap analysis (verify completion)
- Step 9.6: Automated code review (catch issues)
- Auto-fixes issues and loops back if gaps/problems found
- Max iteration safety (default 3 cycles)
- Opt-in via separate command (not forced)
- ~30% more tokens but prevents review rework cycles
Applies to both BMM and BMGD modules
- Audit completed stories to verify claims match code
- Validate any story without starting development
- Detect false positives (marked done but not implemented)
- Batch mode to audit multiple stories
- Generate audit reports for team review
Applies to both BMM and BMGD modules
- Add Step 1.5 gap analysis before development starts
- Scan codebase to validate draft tasks against reality
- Propose task refinements (add/modify/remove)
- Six user options: approve, auto-accept, reject, edit, skip, review
- Update story file with Gap Analysis section
- Prevents duplicate implementations in batch planning
Applies to both BMM and BMGD modules
- Remove codebase scanning from planning phase
- Mark generated tasks as DRAFT
- Add notation that tasks will be validated at dev-time
- Focus on requirements analysis and architecture context
- Simplify workflow by deferring gap analysis to execution
Applies to both BMM and BMGD modules
- Fix XML syntax error in dev-story/instructions.xml:20 (goto element)
- Fix path typo in tech-writer.agent.yaml (_bmadbmm → _bmad/bmm)
- Fix wrong route in analyst.agent.yaml (edit-agent → party-mode)
- Comment out unimplemented validate-create-story in sm.agent.yaml
- Comment out unimplemented validate-design in ux-designer.agent.yaml
- Remove misleading validate-create-story reference in create-story output
Fixes#1075
Related to #1163🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* fix(bmm): sprint-status workflow improvements
- Remove dead by_epic template block and context_status variable (#1116, #1117)
- Define "first" story ordering as epic number then story number (#1119)
- Clarify retrospective check: "any retrospective status == optional" (#1120)
- Strengthen validate mode: check required metadata fields and valid statuses (#1121)
- Expand risk detection: stale file, orphaned stories, empty epics (#1122)
- Fix retrospective valid status: use "done" instead of "completed" for consistency
Fixes#1116, fixes#1117, fixes#1119, fixes#1120, fixes#1121, fixes#1122🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(bmm): address CodeRabbit review feedback
- Improve retrospective status descriptions for clarity
- Fix empty epic detection to only warn on in-progress epics
- Add 'generated' to required metadata field validation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* fix(bmm): improve sprint-status validation and epic status handling
- Add status validation with interactive correction for unknown values
- Update epic statuses to match state machine: backlog, in-progress, done
- Map legacy "contexted" status to "in-progress" explicitly
- Add retrospective status counting (optional, completed)
- Rewrite risk detection rules for LLM clarity
- Fix warnings vs risks naming inconsistency in data mode
Closes#1106Closes#1118🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* style: fix prettier formatting in sprint-status instructions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Updated status references to use canonical lowercase kebab-case format:
- dev-story/instructions.xml: Status field set to "review" (was "Ready for Review")
- dev-story/instructions.xml: Output messages reference actual "review" status
- dev-story/checklist.md: Status field instruction uses "review"
- daily-standup.xml: Status examples use "in-progress, review"
Story lifecycle: backlog → ready-for-dev → in-progress → review → done
Fixes#1105🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The `drafted` story state is no longer used since create-story now sets
status directly to `ready-for-dev`. This PR removes all references to
this legacy state from BMM documentation and workflow files.
Changes:
- Remove `drafted` from story status definitions and state machine docs
- Remove dead story-context file detection (story-context files no longer exist)
- Replace "draft" verb with "create" in story-related messaging
- Add legacy `drafted` → `ready-for-dev` migration in sprint-status
- Clarify that validate-create-story is optional and doesn't change status
- Document story handoff sequence: create-story → (optional) validate → dev-story
Story lifecycle is now: backlog → ready-for-dev → in-progress → review → done
Closes#1089🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Change "Story is ready for next work!" to "Code review complete!"
The original phrasing was misleading - when a code review finishes
with status "done", it means the review itself is complete and the
story is marked done in tracking. However, the user may choose to
do additional reviews or the story may genuinely be finished.
"Code review complete" more accurately describes what actually
happened without implying next steps.
Removes references to epic-tech-context, story-context, story-done,
and story-ready workflows that were deleted in the Phase 4 transformation.
Also renames mislabeled excalidraw element IDs from proc-story-done
to proc-code-review to match the actual displayed text.
Fixes#1088
- Fix checklist to only accept 'review' status (not 'ready-for-review')
- Include MEDIUM issues in done/in-progress status determination
- Initialize and track fixed_count/action_count variables for summary
- Add sprint-status.yaml sync when story status changes
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Replace 'looks good' with `looks good` to avoid nested single quote
issues when IDEs generate command files from workflow YAML.
Co-authored-by: Brian <bmadcode@gmail.com>
* feat: add sprint-status command
* minor changes to reduce the change radius
---------
Co-authored-by: mq-bot <mq-bot@local>
Co-authored-by: Brian <bmadcode@gmail.com>
MAJOR BREAKING CHANGES: Phase 4 completely reengineered for developer efficiency and quality
🚀 **Phase 4 Streamlined & Supercharged:**
- **Reduced from 11 to 5 essential workflows** (55% reduction in complexity)
- **Eliminated redundant steps** that created token waste and confusion
- **Created single source of truth** story files with comprehensive implementation context
- **Achieved more reliable results** with fewer steps and better developer guidance
💡 **Revolutionary Dev Agent Behavior Fixes:**
- **Story file is now LAW:** Tasks/subtasks sequence is absolutely binding
- **Red-green-refactor enforcement:** Tests written first, validated, then implementation
- **Zero tolerance for cheating:** Tests must ACTUALLY exist and pass before marking complete
- **Sequential execution only:** No more "doing whatever you want" - follow the story exactly
- **Continuous execution:** No premature pausing until all tasks complete
🎯 **Quality Competition System:**
- **Enhanced story context engine** prevents common LLM development mistakes
- **Quality competition between LLMs** ensures optimal story preparation
- **Comprehensive anti-pattern prevention** stops wheel reinvention and wrong approaches
- **Developer optimization focus** for maximum clarity with minimum verbosity
📋 **Enhanced Definition of Done:**
- **27-point validation checklist** covers all implementation aspects
- **Multiple validation gates** prevent claiming work that isn't actually done
- **Comprehensive test requirements** ensure no functionality goes untested
- **File tracking and documentation** for complete project visibility
🔧 **Technical Improvements:**
- **Variable consistency** throughout all workflow files
- **XML instruction format** for better workflow engine compatibility
- **Proper ask tag handling** for user interaction clarity
- **Project context integration** without blocking implementation
- **Fixed all agent schema compliance** for proper array formatting
**Result:** Phase 4 now delivers superior development outcomes with:
- ✅ **55% fewer workflows** to learn and maintain
- ✅ **Dramatically reduced token usage** and context switching
- ✅ **Eliminated dev agent behavioral issues** that caused quality problems
- ✅ **Faster time-to-completion** with more reliable, predictable results
- ✅ **Better developer experience** with clearer guidance and validation
This represents the most significant Phase 4 improvement since BMAD Method inception - fundamentally fixing developer workflow quality while drastically simplifying the implementation process.
## The Tale of the Frame Expert
Once upon a time, BMad Method had a specialized agent called Frame Expert.
This agent was the master of all visual artifacts - flowcharts, diagrams,
wireframes, data flows. Whenever anyone needed a diagram, they called upon
Frame Expert. The agent lived in its own isolated domain with four dedicated
workflows and a library of shared templates.
## The Awakening
But something felt wrong. Teams using BMad Method were meant to mirror real
agile teams - Product Managers, Architects, UX Designers, Tech Writers,
Developers. Each agent represented an authentic role you'd find in any
software team.
Except Frame Expert.
No real agile team has a "Frame Expert" or "Diagram Specialist" who creates
all visual artifacts. In real teams, Architects diagram system architecture.
PMs flowchart processes. UX Designers wireframe interfaces. Tech Writers
create documentation diagrams. The visuals emerge from the domain experts
who need them, not from a centralized diagram factory.
Frame Expert was an abstraction that made technical sense but violated the
very soul of BMad Method - authentic agile role modeling.
## The Transformation
And so Frame Expert was dissolved, its knowledge distributed to those who
truly needed it:
**The Architect** inherited system architecture diagrams and data flows -
the blueprints of technical systems they design.
**The Product Manager** received process flowcharts - the visual maps of
features and workflows they orchestrate.
**The UX Designer** claimed wireframes - the interface sketches that bring
their vision to life.
**The Tech Writer** gained all diagram types - the visual aids that clarify
their documentation.
Each agent now creates diagrams in their domain, using their expertise,
serving their purpose.
## The Shared Knowledge
But the wisdom of diagram creation itself - the Excalidraw templates, the
component libraries, the validation patterns - this knowledge was too
valuable to scatter. It was elevated to core resources, where both BMM
agents AND the new CIS presentation-master agent could draw upon it.
Shared infrastructure for common needs. Distributed execution for domain
expertise.
## The Ripple Effects
With diagrams now properly distributed, other misalignments became visible:
Epic creation was happening in Phase 2 (Planning), before Architecture
existed. But epics need architectural context - API contracts, data models,
technical decisions. So epic creation migrated to Phase 3 (Solutioning),
after Architecture provides that foundation.
Workflow paths were updated. Documentation gained visual flowcharts showing
the complete journey. Agent naming standards were clarified - filenames are
stable roles, persona names are user dreams.
## What Changed
**Removed:**
- frame-expert.agent.yaml (the centralized specialist)
- All frame-expert workflows and shared resources
- Phase 2 epic creation workflow (wrong timing)
- game-design workflow path (consolidated to method track)
- v6-open-items.md (planning doc, now complete)
**Distributed Diagram Capabilities:**
- Architect: create-excalidraw-diagram, create-excalidraw-dataflow
- PM: create-excalidraw-flowchart
- Tech Writer: create-excalidraw-{diagram,dataflow,flowchart}, generate-mermaid
- UX Designer: create-excalidraw-wireframe
**Created:**
- src/core/resources/ (shared diagram context for all modules)
- src/modules/cis/agents/presentation-master.agent.yaml (visual comms specialist)
- src/modules/bmm/workflows/3-solutioning/create-epics-and-stories/ (epic creation's new home)
- src/modules/bmm/workflows/diagrams/ (distributed diagram implementations)
- src/modules/bmm/docs/images/ (workflow visualization assets)
**Enhanced:**
- All agent definitions with domain-appropriate diagram workflows
- Documentation with embedded workflow diagrams and visual guides
- Agent compilation docs with critical naming convention rules
- All 4 workflow paths (enterprise/method × brownfield/greenfield)
**Fixed:**
- Epic creation now in Phase 3 after Architecture
- Story context path variables in BMGD module
- PRD workflow descriptions (epics moved to Phase 3)
## For Users
The Frame Expert commands are gone. In their place:
- Need architecture diagrams? Ask `/architect`
- Need process flows? Ask `/pm`
- Need wireframes? Ask `/ux-designer`
- Need documentation visuals? Ask `/tech-writer`
Each expert creates diagrams in their domain, with their context, using
their judgment.
This is how real teams work.
Jonah Schulte
Nick Pirocanac
Brian Madison
Jonah Schulte
Serhii
Alex Verkhovsky
Murat K Ozcan
Nguyen Quang Huy
Dicky Moore