- Updated intelligent-tools-strategy.md to include -s parameter in all codex examples
- Added comprehensive sandbox modes documentation
- Updated tools-implementation-guide.md with -s workspace-write throughout
- Clarified that -s workspace-write is recommended for development tasks
- Added sandbox mode explanations: read-only, workspace-write, danger-full-access
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- plan.md: Compress from 307 to 183 lines while preserving all core functionality
- Add project structure analysis with get_modules_by_depth.sh integration
- Implement 5-field JSON schema compliance with workflow-architecture.md
- Add detailed context acquisition strategy with tool templates
- Include comprehensive file cohesion principles and variable system
- Maintain 10-task limit enforcement and pre-planning analysis requirements
- execute.md: Compress from 380 to 220 lines with enhanced agent context
- Preserve complete Task execution patterns with full flow control context
- Maintain comprehensive session context, implementation guidance, and error handling
- Streamline discovery process while keeping all critical execution details
- Keep complete agent assignment and status management functionality
- workflow-architecture.md: Minor structural updates for consistency
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Simplified argument hints and examples in plan.md
- Enhanced input detection logic for files, issues, and text
- Introduced analysis levels for improved context analysis
- Updated core rules for task limits and decomposition strategies
- Improved session management with active session marker system
- Expanded file structure reference and naming conventions
- Clarified task hierarchy and status rules
- Added detailed validation and error handling procedures
- Streamlined document templates for implementation plans and task summaries
- Add comprehensive /workflow:resume command with intelligent interruption detection
- Support multiple recovery strategies: automatic, targeted, retry, skip, force
- Implement context reconstruction and status synchronization
- Remove deprecated "gemini_required": true from task JSON examples
- Replace with pre_analysis multi-step approach for better workflow control
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Rename /context command to /workflow:status for better namespace organization
- Move command file from .claude/commands/context.md to .claude/commands/workflow/status.md
- Update all command references and usage examples in documentation
- Maintain all original functionality while improving command hierarchy
- Create workflow subdirectory for better command organization
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add critical warnings in codex-unified.md that no wrapper script exists
- Clarify in intelligent-tools.md that Gemini has wrapper, Codex uses direct commands
- Prevent confusion about non-existent ~/.claude/scripts/codex
- Emphasize correct usage: gemini-wrapper vs codex --full-auto exec
- Clean up CLAUDE.md tool references for consistency
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create intelligent-tools.md as strategic guide for tool selection
- Reference intelligent-tools.md from CLAUDE.md for global access
- Add three analysis levels to plan.md (quick/standard/deep)
- Separate tool selection strategy from plan command implementation
- Maintain clear separation of concerns between strategy and execution
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Translate Task Granularity Principles section to English
- Convert Task Decomposition Anti-patterns examples to English
- Update Task Saturation Assessment principles to English
- Translate all task examples and descriptions to English
- Maintain all technical functionality while improving readability
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix syntax error on lines 215 and 226 where @{pattern} caused parsing issues
- Wrap pattern strings in quotes to treat them as literal text labels
- Resolves "Parse error on line 21: Expecting 'SQE', 'DOUBLECIRCLEEND'..." error
- Ensures proper rendering of workflow diagrams in GitHub and other mermaid renderers
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add 6 new detailed mermaid diagrams showing complete development workflow from brainstorming to execution
- Document workflow vs task command relationships and dependencies
- Include planning method selection flow based on project complexity
- Add brainstorming to execution pipeline with multi-agent coordination
- Show task command hierarchy with execution modes and agent selection
- Integrate CLI tools (Gemini/Codex) within workflow context
- Update README files with workflow examples and planning method guides
- Provide clear visual guidance for choosing appropriate development paths
Enhanced documentation now covers complete workflow orchestration from
initial requirements through planning, execution, and final delivery.
🤖 Generated with [Claude Code](https://claude.ai/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>
- Add detailed mermaid workflow diagrams in WORKFLOW_DIAGRAMS.md
- Update README.md and README_CN.md with v1.2 features and architecture visualization
- Enhance system architecture diagrams with CLI routing and agent coordination flows
- Document major enhancements since v1.0: task saturation control, Gemini wrapper intelligence
- Add command execution flow diagrams and comprehensive workflow visualizations
- Update CLI guidelines in codex-unified.md and gemini-unified.md with bash() syntax
🤖 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>
- Update unified file structure to stress on-demand creation principle
- Add creation strategy section with explicit guidance:
- Initial setup creates only required files (session.json, IMPL_PLAN.md, TODO_LIST.md, .task/)
- Optional directories (.brainstorming/, .chat/, .summaries/) created when first needed
- Update core design principles to include on-demand file creation
- Add session initialization and directory creation examples in Data Operations
This ensures workflows start lean and expand only as functionality is used.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace separate Main Tasks/Subtasks sections with unified hierarchical list
- Use ▸ symbol for container tasks (with subtasks) instead of checkboxes
- Maintain standard - [ ]/- [x] for executable leaf tasks
- Add 2-space indentation to show task hierarchy clearly
- Include status legend for better user understanding
Benefits:
- Eliminates confusion about non-executable main tasks
- Provides clear visual hierarchy in single list
- Reduces TODO_LIST complexity and improves usability
- Aligns container task concept with execution model
🤖 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>
- Add /workflow:session:complete command to manually mark active sessions as complete
- Implements session status updates with completion timestamps
- Removes active flag marker while preserving all session data
- Provides detailed completion summary with statistics and artifacts
- Includes comprehensive error handling and validation checks
- Maintains integration with existing workflow system and TodoWrite
- Supports command variations (--detailed, --quiet, --force)
- Preserves completed sessions for future reference via /context
🤖 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>
- Increase Bash command timeout to 10 minutes for both gemini and codex workflows
- Better support for large codebase analysis and complex autonomous development tasks
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix all codex examples to use proper `--full-auto exec` syntax
- Replace all `codex exec` instances with `codex --full-auto exec`
- Update documentation to reflect that --full-auto exec is mandatory
- Correct directory analysis rules and template references
- Update shared template system references to use proper path format
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add 5-minute timeout for Bash commands in both gemini and codex workflows
- Mark --all-files as default behavior for gemini with fallback on content limits
- Update all examples to show explicit --all-files usage in gemini-unified.md
- Add execution settings section for both workflow guides
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add explicit directory analysis rule to gemini-unified.md for cd navigation
- Add directory analysis rule to codex-unified.md with --cd flag option
- Improve clarity for users when analyzing specific directories
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## Configuration Section Correction:
### Removed Unnecessary Configurations:
- **Gemini CLI**: Removed `outputFormat` and `templateDirectory` - these are not standard or required
- **Codex CLI**: Removed entire section - Codex CLI configuration is not part of CCW setup
- **Local Settings**: Removed `.claude/settings.local.json` section - not part of core configuration
### Retained Essential Setting:
- **Only `contextFileName: "CLAUDE.md"`**: This is the critical setting needed for CCW integration with Gemini CLI
- **Clear explanation**: Added description of why this setting is necessary
### Benefits:
- **Simplified setup**: Users only need to configure what's actually required
- **Reduced confusion**: No more unnecessary or potentially incorrect configuration examples
- **Focus on essentials**: Streamlined to core functionality requirements
- **Bilingual consistency**: Applied same fixes to both English and Chinese versions
The configuration section now accurately reflects only the settings that are necessary for CCW to function properly.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## Major Documentation Updates:
### README Transformation:
- **English README.md**: Rewritten as "The Neural Network for Software Development" with compelling storytelling, vivid metaphors, and emotional connection
- **Chinese README_CN.md**: Culturally adapted with engaging Chinese expressions while maintaining technical accuracy
- Added "AI Dream Team" concept, real-world scenarios, and developer transformation narratives
- Enhanced visual hierarchy with rich emojis and progressive disclosure of complex concepts
### Codex CLI Guidelines Enhancement:
- **Emphasized --full-auto as PRIMARY mode**: Added prominent golden rule section for autonomous development
- **Updated all examples**: Every code sample now leads with --full-auto approach, alternatives moved to secondary position
- **Critical guidance added**: Clear 90% usage recommendation for autonomous mode with explicit exception criteria
- **Comprehensive workflow updates**: Multi-phase development, quality assurance, and cross-project learning all prioritize autonomous execution
### Key Improvements:
- Transformed technical specifications into compelling developer stories
- Made complex architecture concepts accessible through analogies
- Added emotional resonance for both English and Chinese audiences
- Strengthened autonomous development workflow recommendations
- Enhanced developer experience focus with before/after scenarios
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Deleted unused command template files (context-analysis.md, folder-analysis.md, parallel-execution.md)
- Removed outdated WORKFLOW_SYSTEM_UPGRADE.md and codexcli.md files
- No references found in current workspace
- Streamlined template structure
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
