- Introduced a detailed guide for intelligent tools selection strategy, including quick reference, tool specifications, prompt templates, and best practices for CLI execution.
- Established a coding philosophy document outlining core beliefs, simplicity principles, and guidelines for effective coding practices.
- Created context requirements documentation emphasizing the importance of understanding existing patterns and dependencies before implementation.
- Developed a file modification workflow detailing the use of edit_file and write_file MCP tools, along with priority logic for file reading and editing.
- Implemented CodexLens auto hybrid mode, enhancing the CLI with automatic vector embedding generation and default hybrid search mode based on embedding availability.
- Introduced `help-i18n.js` for managing translations in Chinese and English for the help view.
- Created `help.js` to render the help view, including command categories, workflow diagrams, and CodexLens quick-start.
- Implemented search functionality with debounce for command filtering.
- Added workflow diagram rendering with Cytoscape.js integration.
- Developed tests for write-file verification, ensuring proper handling of small and large JSON files.
- Introduced `--id <id>` option in CLI for custom execution IDs.
- Enhanced CLI command handling to support multi-turn conversations.
- Updated execution and conversation detail retrieval to accommodate new structure.
- Implemented merging of multiple conversations with tracking of source IDs.
- Improved history management to save and load conversation records.
- Added styles for displaying multi-turn conversation details in the dashboard.
- Refactored existing execution detail functions for backward compatibility.
- Implemented a new HTML template for the workflow dashboard, featuring a responsive design with dark/light theme support, session statistics, and task management UI.
- Created a browser launcher utility to open HTML files in the default browser across platforms.
- Developed file utility functions for safe reading and writing of JSON and text files.
- Added path resolver utilities to validate and resolve file paths, ensuring security against path traversal attacks.
- Introduced UI utilities for displaying styled messages and banners in the console.
- 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 CLI mode example to implementation_approach showing optional command field
- Document two execution modes:
1. Default Mode (agent execution): No command field, agent interprets steps
2. CLI Mode (command execution): With command field, uses CLI tools (codex/gemini/qwen)
- Add Implementation Approach Execution Modes section with:
- Mode descriptions and use cases
- Required fields for each mode
- Command patterns for CLI mode (codex, gemini)
- Mode selection strategy
- Simplify implementation_approach examples to use generic placeholders
- Emphasize command field is optional, agent decides based on task complexity
Benefits:
- Clear documentation of both execution patterns
- Agents understand when to use CLI tools vs direct execution
- Pattern examples show structure without over-specifying content
- Supports both autonomous agent work and CLI tool delegation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove context_signature field from meta object
- Simplify meta object to focus on essential fields
- Keep execution_group for parallelization support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated output paths in various command files to reflect the new structure: `.workflow/sessions/{session_id}/` instead of `.workflow/{session_id}/`.
- Adjusted documentation and code comments to ensure consistency across all agents and commands.
- Ensured that all references to session-related files are correctly pointing to the new directory format.
- Updated references in various workflow commands to utilize role analysis documents instead of synthesis-specification.md.
- Modified CLI templates and command references to reflect the new architecture and document structure.
- Introduced conflict-resolution command to analyze and resolve conflicts between implementation plans and existing codebase.
- Deprecated synthesis role template and provided migration guidance for transitioning to the new role analysis approach.
- Updated implementation_approach in task-generate-tdd.md to use an array format with detailed steps for minimal code implementation and iterative testing.
- Enhanced task-generate.md to support CLI execution mode with Codex, including examples for task execution and session management.
- Modified test-task-generate.md to incorporate CLI execution mode, allowing Codex to autonomously generate tests and execute iterative test-fix cycles.
- Revised task-core.md and workflow-architecture.md to adopt a step-based implementation approach, improving clarity and dependency management in task execution.
- Improved documentation in workflow-architecture.md to clarify flow control structure and variable referencing.
Major role restructuring to improve workflow efficiency and clarity:
## New Roles Added (4)
- product-owner: Backlog management and user story definition
- scrum-master: Sprint planning and agile process facilitation
- ux-expert: User experience optimization and usability testing
- subject-matter-expert: Domain expertise and industry standards
## Roles Removed (5)
- business-analyst → functionality split to product-owner and scrum-master
- feature-planner → merged into product-owner responsibilities
- innovation-lead → integrated into subject-matter-expert
- security-expert → integrated into subject-matter-expert
- user-researcher → merged into ux-expert
## Files Updated
### Command Files (.claude/commands/workflow/brainstorm/)
- Created: product-owner.md, scrum-master.md, ux-expert.md, subject-matter-expert.md
- Deleted: business-analyst.md, feature-planner.md, innovation-lead.md, security-expert.md, user-researcher.md
- Updated: artifacts.md, auto-parallel.md, auto-squeeze.md, synthesis.md
### Planning Templates (.claude/workflows/cli-templates/planning-roles/)
- Created: product-owner.md, scrum-master.md, ux-expert.md, subject-matter-expert.md
- Archived: Moved 5 deprecated roles to _deprecated/ with migration guide
- Added: _deprecated/README.md with deprecation details and migration paths
### Agent Configurations
- Updated conceptual-planning-agent.md with new role mappings
- Updated action-planning-agent.md with new role references
### Documentation
- Updated README.md brainstorming role tables and descriptions
- Updated README_CN.md with Chinese translations for new roles
- Updated workflow documentation files with new role references
## Breaking Changes
Commands for removed roles are no longer available. Use replacement roles:
- /workflow:brainstorm:business-analyst → use product-owner or scrum-master
- /workflow:brainstorm:feature-planner → use product-owner
- /workflow:brainstorm:innovation-lead → use subject-matter-expert
- /workflow:brainstorm:security-expert → use subject-matter-expert
- /workflow:brainstorm:user-researcher → use ux-expert
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implemented task-generate-agent for autonomous task generation using action-planning-agent with discovery and output phases.
- Introduced task-generate command to generate task JSON files and IMPL_PLAN.md from analysis results with automatic artifact detection and integration.
- Enhanced documentation for both commands, detailing execution lifecycle, phases, and output structures.
- Established clear integration points and error handling for improved user experience.
## New Features
- **MCP Tools Integration**: Added support for Model Context Protocol tools
- Exa MCP Server: External API patterns and best practices
- Code Index MCP: Advanced internal codebase search and indexing
- **Enhanced Workflow Planning**: Updated pre_analysis to include MCP tool steps
- **Documentation Updates**: Added MCP tool setup guides and usage examples
## Changes
### Core Components
- Updated `plan.md` with MCP integration principles and implementation approach guidelines
- Added MCP tool steps in pre_analysis workflow: `mcp_codebase_exploration`, `mcp_external_context`
- Enhanced context accumulation with external best practices lookup
### Documentation
- Added comprehensive MCP tools section in both English and Chinese README
- Updated installation requirements and integration guidelines
- Added GitHub repository links for required MCP servers
### Agent Enhancements
- Updated multiple agents to support MCP tool integration
- Enhanced context gathering capabilities with external pattern analysis
## Technical Details
- MCP tools provide faster analysis through direct codebase indexing
- Automatic fallback to traditional bash/CLI tools when MCP unavailable
- Enhanced pattern recognition and similarity detection capabilities
🧪 **Experimental**: MCP integration is currently experimental and optional
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update action-planning-agent to use gemini-wrapper for improved CLI analysis
- Enhance task execution with simplified control structure and context requirements
- Improve plan-deep command with input validation and clarity requirements
- Add intelligent context acquisition rules to CLAUDE.md with required analysis patterns
- Strengthen agent workflow coordination with TodoWrite management and context rules
- Remove deprecated execution controls and streamline task execution flow
System now enforces proper context gathering before implementation and provides
better coordination between agents through structured TODO management.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Updated all CLI command examples across agent documentation and workflow
guides to use bash() wrapper for proper tool execution:
- Modified action-planning-agent.md CLI usage standards
- Updated code-developer.md analysis CLI commands
- Enhanced conceptual-planning-agent.md execution logic
- Revised code-review-test-agent.md CLI commands
- Wrapped all gemini-wrapper calls in gemini-unified.md
- Updated all codex commands in codex-unified.md
This ensures consistent tool execution patterns across all documentation
and provides clear guidance for proper CLI tool invocation.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
CONSISTENCY IMPROVEMENTS:
- Update gemini-unified.md examples to use full path ~/.claude/scripts/gemini-wrapper
- Add setup note indicating script auto-installs to ~/.claude/scripts/ location
- Clarify usage instructions to emphasize full path usage
AGENT DOCUMENTATION UPDATES:
- action-planning-agent.md: Use full path for gemini-wrapper
- code-developer.md: Use full path for gemini-wrapper
- code-review-test-agent.md: Use full path for gemini-wrapper
- conceptual-planning-agent.md: Use full path for gemini-wrapper
BENEFITS:
- Prevents "command not found" errors
- Ensures consistent invocation across all documentation
- Makes path explicit and unambiguous for users
- Supports direct copy-paste usage from documentation
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
ENHANCEMENTS:
- Create gemini-wrapper script with automatic token counting and smart flag management
- Auto-add --approval-mode based on task type (analysis=default, execution=yolo)
- Raise token threshold to 2M for better large project handling
- Add comprehensive parameter documentation for --approval-mode and --include-directories
WRAPPER FEATURES:
- Token-based --all-files management (small projects get --all-files automatically)
- Smart task detection for approval modes
- Error logging to ~/.claude/.logs/gemini-errors.log
- Complete parameter passthrough for full gemini compatibility
DOCUMENTATION UPDATES:
- Update gemini-unified.md with wrapper usage guidelines and examples
- Add intelligent wrapper as recommended approach
- Document all agent files to use gemini-wrapper instead of direct gemini calls
- Include new parameter reference and best practices
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add 'paths' field to task JSON schema with semicolon-separated concrete paths
- Create read-task-paths.sh script to convert paths to Gemini @ format
- Update all agents to use task-specific paths instead of --all-files
- Integrate get_modules_by_depth.sh for project structure discovery
- Update workflow planning to populate paths field automatically
- Enhance execute command to pass task-specific paths to agents
- Update documentation for new path management system
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## Major Changes
- Add --AM flag to /workflow:plan command for analysis method selection
- Support both Gemini CLI (pattern-based) and Codex CLI (autonomous) analysis
- Implement dual marker system: [GEMINI_CLI_REQUIRED] and [CODEX_CLI_REQUIRED]
- Update all 4 agents to handle both analysis markers
- Create analysis method templates for standardized CLI usage
## Files Modified
- workflow-architecture.md: Add Analysis Method Integration section
- plan.md: Add --AM flag and bilingual rule standardization
- execute.md: Update marker mapping logic and standardize to English
- 4 agent files: Add dual CLI support with usage guidelines
- New: analysis-methods/ templates for Gemini and Codex CLI
## Backward Compatibility
- Gemini CLI remains default analysis method
- Existing workflows continue to work unchanged
- Progressive enhancement for autonomous development scenarios
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update workflow:execute.md to inject session context paths into agent prompts
- Modify code-developer.md to require and use session context for TODO_LIST updates
- Update task:execute.md to include session_context structure in JSON template
- Enhance action-planning-agent.md to use provided session paths for plan generation
- Fix code-review-test-agent.md to reference session context for review summaries
Resolves issue where agents couldn't locate workflow directory for TODO_LIST.md updates
and summary creation. Agents now receive explicit paths instead of assuming defaults.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Introduced a comprehensive set of parallel execution command templates for various architectural and functional scenarios.
- Added prompts for analyzing system architecture, implementation patterns, performance, code quality, security, and project structure.
- Created templates for planning tasks, component implementation, migration strategies, and code reviews.
- Established a unified guideline for Gemini CLI usage, including command syntax, file patterns, and template best practices.
- Initialized VSCode settings file for project configuration.1
- Create /workflow:plan:deep command for deep technical planning
- Add GEMINI_ANALYSIS_REQUIRED support to conceptual-planning-agent
- Translate brainstorm commands to English (business-analyst, partial innovation-lead)
- Consolidate document format standards in file-structure-standards.md
- Update action-planning-agent to reference centralized format standards
Key changes:
- plan-deep.md: New command with mandatory Gemini CLI analysis via agent
- conceptual-planning-agent.md: Added Gemini Analysis Integration section
- file-structure-standards.md: Enhanced with detailed IMPL_PLAN.md formats
- Unified language to English for consistency
- Remove detailed progress views (Total Tasks: X, Completed: Y %) from all templates
- Simplify TODO_LIST.md structure by removing Progress Overview sections
- Remove stats tracking from session-management-principles.json schema
- Eliminate progress format and calculation logic from context command
- Remove percentage-based progress displays from action-planning-agent
- Simplify vibe command coordination by removing detailed task counts
- Focus on essential JSON state changes rather than UI progress metrics
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
