- Added new fields to the exploration JSON schema: exploration_angle, exploration_index, and total_explorations for better tracking of exploration parameters.
- Created a comprehensive review-fix command documentation to automate code review findings fixing, detailing the workflow, execution flow, agent roles, and error handling.
- Introduced fix-plan-template.json for structured planning output, including execution strategy, group definitions, and risk assessments.
- Added fix-progress-template.json to track progress for each group during the execution phase, ensuring real-time updates and status management.
- Introduced a new command `/workflow:review-session-cycle` for session-based code reviews across 7 dimensions.
- Implemented hybrid parallel-iterative execution to enhance review efficiency and coverage.
- Added detailed documentation outlining command usage, execution flow, and agent roles.
- Configured specialized dimensions with priority-based allocation and defined severity assessment criteria.
- Established a robust aggregation logic for identifying cross-cutting concerns and critical findings.
- Enabled real-time progress tracking through an interactive HTML dashboard.
- Included mechanisms for deep-dive analysis and remediation planning for critical issues.
- Introduced `review-deep-dive-results-schema.json` to define the structure for deep-dive iteration analysis results, including root cause analysis, remediation plans, and impact assessments.
- Added `review-dimension-results-schema.json` to outline the schema for dimension analysis results, capturing findings across various dimensions such as security and architecture, along with cross-references to related findings.
Enhancement:
- Added "CRITICAL: Syntax Check Priority" section in @test-fix-agent template
- Positioned before Session Paths for maximum visibility
Requirements:
- Run syntax checker (TypeScript tsc --noEmit, ESLint, etc.) BEFORE any work
- Verify zero syntax errors before proceeding
- Fix syntax errors immediately if found
- Syntax validation is MANDATORY gate - no exceptions
Scope:
- Applies to all task types (test-gen, test-fix, test-fix-iteration)
- Agent-level enforcement (not in orchestrator flow)
Rationale:
- Syntax errors must be fixed before functional testing
- Prevents cascading failures from basic syntax issues
- Reduces iteration waste on trivial syntax problems
Changes:
- Removed model="haiku" from @test-fix-agent parallel invocation
- Use default model selection for flexibility
- Updated comment to remove model reference
Rationale:
- Let system auto-select appropriate model
- Avoid hardcoded configuration
- Maintain flexibility for future model changes
Based on Gemini architectural analysis (verdict: "File necessary but simplify"):
Removed Redundant Fields:
- session_id → Derive from file path or workflow-session.json
- current_iteration → Calculate as iterations.length + 1
- max_iterations → Read from task.meta.max_iterations (single source)
- stuck_tests → Calculate by analyzing iterations[].failed_tests history
- regression_detected → Calculate from consecutive pass_rate values
Retained Essential Fields:
- current_task: Active task pointer (Resume critical)
- selected_strategy: Current iteration strategy (runtime state)
- next_action: State machine next step (Resume critical)
- iterations[]: Historical log (source of truth, cannot rebuild)
Enhanced iterations[] Array:
- Added failed_tests[] to each entry (was stuck_tests at top-level)
- Removed redundant regression_detected (calculated from pass_rate)
Benefits:
- Single source of truth (no data duplication)
- Less state to maintain and synchronize
- Clearer data ownership and calculation points
- Adheres to data normalization principles
Documentation Updates:
- Added "Purpose" and "Field Descriptions" sections
- Added "Removed Redundant Fields" with derivation logic
- Updated orchestrator responsibilities (Runtime Calculations)
- Updated agent template (Orchestrator-Calculated metadata)
Impact: File remains essential for Resume capability, but now leaner and normalized.
Enhancement:
- Add dynamic prompt template for @test-fix-agent
- Supports 3 task types: test-gen, test-fix, test-fix-iteration
- Auto-adapts based on task.meta.type via configuration maps
Template Features:
- taskTypeObjective: Task-specific goals
- taskTypeSpecificReads: Required file reads per type
- taskTypeGuidance: Execution instructions per type
- taskTypeDeliverables: Expected outputs per type
- taskTypeSuccessCriteria: Completion validation per type
Benefits:
- Orchestrator uses single template for all task types
- Claude dynamically fills in type-specific details
- Reduces duplication, maintains consistency
- Clear guidance for criticality assessment (high/medium/low)
- Progressive testing integration (affected_only vs full_suite)
Lines: +86 (429 → 515, still -35% from original 791)
Structure Changes:
- Quick Start → What & Why → How It Works → Enhanced Features → Reference
- User-facing content first, technical details later
- 540 → 429 lines (-21%, total -46% from original 791)
Improvements:
- Usage examples at top (immediate access)
- Simplified "How It Works" section (tree diagram)
- Agent roles as table (quick reference)
- Technical details moved to Reference section
- All core features preserved
Benefits:
- New users find usage commands immediately
- Conceptual understanding before technical details
- Reference section for implementation details
- Maintains all functionality and enhancements
- Implemented the `docs-related-cli` command for context-aware documentation generation and update for changed modules using CLI execution with tool fallback.
- Introduced the `lite-fix` command for lightweight bug diagnosis and fix workflow, featuring intelligent severity assessment and optional hotfix mode for production incidents.
- Update action-planning-agent and task-generate-agent to load context
via file paths instead of embedded context packages
- Streamline test-cycle-execute workflow execution
- Remove redundant content from conflict-resolution and context-gather
- Update SKILL.md and tdd-plan documentation
Add explicit note in Phase 1 validation to prevent main Claude from
incorrectly looking for manifest.json in .workflow/active/WFS-xxx/.
manifest.json only exists in .workflow/archives/ (for archived sessions).
Active sessions only have workflow-session.json (metadata).
This prevents confusion during plan execution before agent invocation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add Phase 6 to both synthesis.md and design-sync.md to automatically
update context-package.json when artifacts are modified, preventing
stale cache issues when transitioning to /workflow:plan.
Changes:
- synthesis.md: Add Phase 6 to sync updated role analyses to context-package
- design-sync.md: Add Phase 5 to sync design system refs + role analyses
This ensures:
- synthesis → plan: context-package reflects synthesis enhancements
- ui-design → plan: context-package includes design system references
- No manual context-gather re-run needed after artifact updates
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create dedicated session folder (.workflow/.lite-plan/{task-slug}-{timestamp}/)
for each lite-plan execution to organize all planning artifacts
- Always export task.json (removed optional export question from Phase 4)
- Save exploration.json, plan.json, and task.json to session folder
- Add session artifact paths to executionContext for lite-execute delegation
- Update lite-execute to use artifact file paths for CLI/agent context
- Enable CLI tools (Gemini/Qwen/Codex) and agents to access detailed
planning context via file references
Benefits:
- Clean separation between different task executions
- All artifacts automatically saved for reusability
- Enhanced context available for execution phase
- Natural audit trail of planning sessions
- Condense Case A/B/C headers for clarity
- Merge bash if-else into single line using && ||
- Combine steps 1-4 in Case C into compact flow
- Remove redundant explanations while keeping key info
- Reduce from 64 lines to 39 lines (39% reduction)
- Add detailed session discovery logic with 3 cases (none, single, multiple)
- Implement AskUserQuestion for multiple active sessions
- Display rich session metadata (project name, task progress, completion %)
- Support flexible user input (session number, full ID, or partial ID)
- Maintain backward compatibility for single-session scenarios
- Improve user experience with clear confirmation messages
This minimal change addresses session conflict issues without complex
locking mechanisms, focusing on explicit user choice when ambiguity exists.
Removed all URL-related parameters and functionality from UI design commands
as they are no longer supported. All commands now only accept local files.
Changes:
- style-extract.md: Removed --urls parameter and all URL mode logic
- layout-extract.md: Removed --urls parameter and DOM extraction via URLs
- COMMAND_SPEC.md: Deleted capture and explore-layers commands, updated syntax
Affected commands:
- /workflow:ui-design:style-extract: Only accepts --images and --prompt
- /workflow:ui-design:layout-extract: Only accepts --images and --prompt
- Removed: /workflow:ui-design:capture (command deleted)
- Removed: /workflow:ui-design:explore-layers (command deleted)
All UI workflow commands now require manual input of local resources
(images, code files, HTML, CSS, JS) instead of fetching from URLs.
Add --dashboard parameter to /workflow:status command that generates
an interactive HTML task board displaying active and archived sessions.
Features:
- Responsive layout with modern CSS design
- Real-time statistics for sessions and tasks
- Task cards with status indicators (pending/in_progress/completed)
- Progress bars for each session
- Search and filter functionality
- Dark/light theme toggle
- Separate panels for active and archived sessions
Implementation:
- Added Dashboard Mode section to .claude/commands/workflow/status.md
- Created HTML template at .claude/templates/workflow-dashboard.html
- Template uses data injection pattern with {{WORKFLOW_DATA}} placeholder
- Generated dashboard saved to .workflow/dashboard.html
Usage:
/workflow:status --dashboard
The dashboard provides a visual overview of all workflow sessions
and their tasks, making it easier to track project progress.
