* 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>
External agents find ALL possible issues, but not all are relevant.
This new step 4 evaluates findings against project context:
- Actually Important: AC violations, bugs, real security issues
- Context-Dependent: Performance, validation strictness (asks user)
- Theoretical/Nitpicking: Micro-optimizations, style preferences (skips)
This enables pragmatic code review that focuses on what matters.
- Rename misleading "CLAUDE CODE CLEANUP" comment to generic "SHELL CLEANUP"
- Remove unused external_prompt variable loading action
- Increase external agent timeout from 5 to 10 minutes for complex reviews
- Fix Review Method output to show actual method used instead of "OR"
- Restore web_bundle: false setting needed by web bundler
Rename 'develop-story' to 'dev-story' across agent triggers and documentation
to match the actual workflow folder and YAML configuration naming.
- Update dev.agent.yaml trigger from develop-story to dev-story
- Update game-dev.agent.yaml trigger from develop-story to dev-story
- Update 7 references in agents-guide.md documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
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.
Change cleanup logic from "check and maybe kill" to "kill unconditionally".
The previous approach allowed agents to read stale output from lingering
external agent processes, causing context pollution and reuse of old data.
New behavior:
- Kill ALL background shells as the FIRST action
- Do NOT read output from stale shells (BashOutput forbidden)
- Do NOT check what processes are doing - just terminate them
- Only proceed to Step 1 after all shells are dead
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
Adds support for delegating adversarial code reviews to external CLI agents
(Codex, Gemini, or Claude) when available. This provides independent, unbiased
code reviews from a different AI model.
Changes:
- Add invoke-bash and set-var tags to workflow.xml execution engine
- Add external_review_agents configuration to install-config.yaml
- Rewrite code-review workflow to detect and invoke external agents
- Cache agent detection in config.yaml to avoid repeated CLI checks
- Add fallback to built-in review if external agents unavailable/fail
- Update checklist to reflect new external agent workflow
External agent invocation:
- Codex: codex exec --full-auto "prompt"
- Gemini: gemini -p "prompt" --yolo
- Claude: claude -p "prompt" --dangerously-skip-permissions
- Add markdownlint-cli2 as dev dependency
- Add lint:md script to package.json
- Add markdownlint job to CI workflow
- Configure 5 rules: heading-increment, no-duplicate-heading,
no-trailing-punctuation, no-bare-urls, no-space-in-emphasis
- Fix existing violations across 19 markdown files
- No auto-fix to prevent destructive changes
Closes#1034🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
* update 2024 to 2025
* fix(workflows): remove hardcoded years from WebSearch queries
Years in search queries (2024/2025) do not improve results - search
engines already prioritize current documentation. Tested all patterns
and confirmed identical quality results with/without years.
Removes years from:
- step-03-starter.md (5 queries)
- step-04-decisions.md (2 queries)
- game-architecture/instructions.md (2 queries)
Leaves file-utils.md unchanged (test fixture data, not a search query).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(workflows): remove year placeholders from research WebSearch queries
Search engines return current results regardless of year - removes
{{current_year}} and hardcoded 2025 from step-05-technical-trends.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor(workflows): replace {{current_year}} with semantic alternatives
Replaces year placeholder with context-appropriate wording:
- 'current data' for up-to-date information
- 'web searches' without year qualifier
- Updated failure mode to focus on using web searches
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(workflows): clarify failure mode about stale training data
Rephrased to explicitly mention training data cutoff as the reason
to use web searches for current technology trends.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor(workflows): make web search references platform-agnostic
- Remove hardcoded year references from WebSearch queries
- Replace `WebSearch` tool name with natural language "search the web"
- Soften "training data is stale" to "verify and supplement your knowledge"
- Add web search prerequisite check to research workflow
- Add platform-agnostic design note to CLAUDE.md
This framework targets 15+ agentic platforms, not just Claude Code.
Tool-specific syntax like `WebSearch:` won't work across all platforms.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor(research): clean up prompts and routing
---------
Co-authored-by: Pomazan Bohdan <pomazan.bogdan@gmail.com>
Co-authored-by: Brian <bmadcode@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
- Remove validate-prd workflow references from all workflow path YAML files
- Update Excalidraw diagram: remove Validate PRD box and zombie JSON elements
- Re-export SVG at 1x scale
- Standardize implementation-readiness descriptions across all docs
- Add validation script (validate-svg-changes.sh) and README for SVG export process
- Correct Excalidraw timestamps
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Brian <bmadcode@gmail.com>
- 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>
sjennings
Alex Verkhovsky
Scott Jennings
Brian Madison
Murat K Ozcan
Brian
murat
Hang
Nguyen Quang Huy