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>
- Create shared-template-system.md as unified template reference for both Gemini and Codex
- Extract duplicate template directory structures from gemini-unified.md and codex-unified.md
- Add comprehensive template categorization with tool compatibility matrix
- Include cross-tool usage patterns and selection guidelines
- Update both workflow files to reference shared template documentation
- Maintain tool-specific template selection guides with clear focus areas
- Add proper cross-references and usage examples for maintainability
This eliminates duplication while providing comprehensive template system documentation that can be maintained independently.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Based on Gemini analysis findings:
- Fix /update-memory command documentation to reflect actual separate commands
- Correct /codex:--full-auto to /codex:mode:auto matching actual implementation
- Remove --yolo flag from examples (behavior is default in execute commands)
- Update documentation management examples to use correct command syntax
- Standardize command reference tables in both English and Chinese READMEs
This ensures documentation accuracy matches the current codebase structure with 44 command files.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update README.md and README_CN.md to v1.1 with unified Gemini/Codex CLI integration
- Add comprehensive Codex command documentation with autonomous development capabilities
- Enhance CLI tool guidelines with shared template system architecture
- Consolidate documentation structure removing outdated CLAUDE.md files
- Reflect current project state with dual CLI workflow coordination
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Introduced new analysis templates for architecture, implementation patterns, performance, quality, and security.
- Created detailed development templates for component creation, debugging, feature implementation, refactoring, testing, and migration planning.
- Established structured documentation guidelines for root, domain, module, and sub-module levels to enhance clarity and organization.
- Implemented a hierarchy analysis template to optimize project structure and documentation depth.
- Updated codex-unified documentation to reflect new command structures, template usage, and best practices for autonomous development workflows.
- Fix execution order in update-memory-related: detect changes before staging
- Add safety checks to prevent unintended source code modifications
- Implement automatic staging recovery if non-CLAUDE.md files are modified
- Ensure both update commands have consistent safety mechanisms
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major Changes:
- Update README.md and README_CN.md to reflect v1.0 release instead of v2.0
- Add Gemini CLI integration highlights: dynamic template discovery, auto-selection
- Correct command references from /gemini:pre:* to /gemini:mode:*
- Add Smart Template Auto-Selection usage examples
- Reorganize Gemini commands from /pre/ to /mode/ directory structure
Documentation Improvements:
- Replace v2.0 architecture claims with actual v1.0 achievements
- Highlight 500+ lines of documentation streamlining
- Add practical examples for new auto-selection template system
- Maintain consistency between English and Chinese versions
Command Structure Updates:
- Move auto.md, bug-index.md, plan.md from /pre/ to /mode/ directory
- Update gemini-unified.md path references
- Ensure all command references are accurate and functional
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Simplify analyze.md, execute.md, bug-index.md, and plan.md command documentation
- Remove redundant content and focus on essential usage patterns
- Reduce total lines by 503 while maintaining core functionality
- Improve documentation clarity and reduce maintenance overhead
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix bash syntax in template discovery loop (remove complex pipe operations)
- Standardize paths to ~/.claude/prompt-templates/ throughout documentation
- Consolidate command into single line to prevent execution splitting
- Test command successfully discovers and reads template YAML frontmatter
🤖 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
- Add prerequisites section referencing official Gemini CLI repository
- Add essential configuration section showing proper settings.json setup
- Emphasize importance of "contextFileName": "CLAUDE.md" setting
- Update both English and Chinese README files
- Fix filename references from "Claude.md" to "CLAUDE.md" in install docs
- Improve user onboarding with proper configuration guidance
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Move bug-fix.md from gemini/chat/ to gemini/pre/bug-index.md
- Update command name from bug-fix to bug-index
- Update all command references to use /gemini:pre:bug-index path
- Delete obsolete chat/plan.md file
- Maintain template functionality while improving command organization
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Updates all command files to use consistent naming without parent field:
- Remove parent field from all command frontmatter
- Standardize name field to use simple names instead of prefixed names
- Fix usage patterns for brainstorm commands to use proper workflow namespace
- Add new medium-project-update.sh script for batch updates
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create brainstorming-framework.md to centralize common techniques and execution modes
- Simplify conceptual-planning-agent.md from 280 to 170 lines (39% reduction)
- Update all 9 brainstorm commands to reference framework instead of agent
- Eliminate circular dependencies and improve maintainability
Key improvements:
- Separated concerns: principles -> framework -> commands -> agent
- Role definitions now only exist in their respective command files
- Creative techniques centralized in framework file
- Agent focused solely on execution logic
- Clear hierarchical reference structure without duplication
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
- 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
- Rewrite brainstorm commands to professional English with improved structure
- Add synthesis command for cross-role integration and recommendations
- Improve template reference format in gemini chat commands (remove backticks)
- Enhance clarity and organization across all brainstorm role files
- Standardize quality assurance sections and implementation protocols
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Simplify /gemini:chat by removing complex template selection logic
- Create /gemini:chat:bug-fix for specialized bug analysis with diagnostic template
- Create /gemini:chat:plan for project planning with architecture template
- Remove dependencies on chat-template-load.sh script
- Organize template commands in gemini/chat/ folder structure
- Update README documentation for new command structure
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implemented the `brainstorm:synthesis` command to integrate insights from various roles into a cohesive analysis and recommendations report.
- Created `brainstorm:system-architect` command for technical architecture and scalability analysis, including detailed execution protocols and output structures.
- Developed `brainstorm:ui-designer` command focusing on user experience and interface design, with a structured approach to analysis and documentation.
- Introduced `brainstorm:user-researcher` command for user behavior analysis and research insights, emphasizing user needs and usability assessments.
