alirezarezvani/claude-code-skill-factory / generated-skills/codex-cli-bridge
codex-cli-bridge
UnverifiedBridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 5.5 KB |
| HOW_TO_USE.md | markdown | 10.1 KB |
| INSTALL.md | markdown | 10.2 KB |
| README.md | markdown | 9.5 KB |
| SKILL.md | skill md | 8.5 KB |
| agents_md_generator.py | script | 17.4 KB |
| bridge.pyexecutable | script | 7.5 KB |
| claude_parser.py | script | 14.9 KB |
| codex_executor.py | script | 13.0 KB |
| expected_output.json | config | 4.7 KB |
| package.shexecutable | script | 5.8 KB |
| project_analyzer.py | script | 11.0 KB |
| safety_mechanism.py | script | 12.0 KB |
| sample_input.json | config | 1.5 KB |
| skill_documenter.py | script | 9.5 KB |
CHANGELOG.md
View on GitHub# Changelog
All notable changes to the Codex CLI Bridge skill will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
---
## [1.0.0] - 2025-10-30
### π Initial Release
First production-ready release of the Codex CLI Bridge skill.
### Added
#### Core Components
- **bridge.py** - Main orchestrator for complete workflow execution
- **safety_mechanism.py** - Environment validation (Codex CLI + CLAUDE.md checks)
- **claude_parser.py** - CLAUDE.md and project structure parser
- **project_analyzer.py** - Project metadata and structure analysis
- **agents_md_generator.py** - Template-based AGENTS.md generation
- **skill_documenter.py** - Skill documentation for Codex CLI users
- **codex_executor.py** - Codex CLI execution helpers with Python wrappers
#### Safety Features
- Auto-check Codex CLI installation
- Auto-run `/init` if CLAUDE.md missing (with user notification)
- Comprehensive environment validation
- User-friendly error messages
- Status reporting
#### Documentation
- **README.md** - Complete skill overview with quick start guide
- **HOW_TO_USE.md** - Comprehensive usage guide with examples
- **SKILL.md** - Full skill reference documentation
- **sample_input.json** - Example input structure
- **expected_output.json** - Example output format
#### Slash Commands
- **`/sync-agents-md`** - Regenerate AGENTS.md from CLAUDE.md
- **`/codex-exec`** - Execute Codex CLI commands with proper syntax
#### Key Features
- β
CLAUDE.md β AGENTS.md automatic generation
- β
Reference-based architecture (no file duplication)
- β
Intelligent skill documentation (functional vs prompt-based)
- β
Codex execution helpers (always uses `codex exec`)
- β
Model selection logic (gpt-5 vs gpt-5-codex)
- β
Sandbox mode helpers (read-only, workspace-write)
- β
Session management (start, resume)
- β
Workflow pattern translation (Claude Code β Codex CLI)
- β
Command reference table
- β
MCP integration documentation
### Technical Details
- **Language**: Python 3.7+
- **Dependencies**: PyYAML
- **File Size**: 114KB (complete package)
- **Modules**: 7 Python files
- **Documentation**: 4 comprehensive guides
- **Tested On**: claude-code-skills-factory repository (13 skills, 59 agents)
### Statistics
- **Lines of Code**: ~2,500
- **Documentation**: ~3,000 lines
- **Test Coverage**: Manual testing on real project
- **Generated Output**: 19KB AGENTS.md (629 lines)
### Architecture Decisions
- **One-way sync**: CLAUDE.md β AGENTS.md (bidirectional deferred to v2.0)
- **Reference-based**: All file paths, no content duplication
- **Safety-first**: Auto-validation before any operation
- **Template-driven**: Consistent output format
### Known Limitations
- Bidirectional sync (AGENTS.md β CLAUDE.md) not implemented (planned for v2.0)
- Watch mode for auto-regeneration not included
- MCP server detection requires manual configuration
- Templates folder created but no custom templates yet
---
## [Unreleased] - Future Versions
### Planned for v2.0
#### Major Features
- π **Bidirectional Sync**: AGENTS.md β CLAUDE.md updates
- Conflict resolution
- Merge strategies
- Change detection
- π **Watch Mode**: Auto-regenerate on file changes
- File system monitoring
- Debounced updates
- Background process
- π **Enhanced Templates**: Customizable AGENTS.md output
- Multiple template formats
- User-defined sections
- Style customization
#### Improvements
- **Performance**: Caching for faster re-generation
- **Validation**: Enhanced YAML and Markdown validation
- **Testing**: Automated test suite
- **Logging**: Structured logging system
- **CLI**: Enhanced command-line interface
#### New Features
- **Plugin System**: Extend functionality with plugins
- **Multiple Formats**: Generate docs in different formats (HTML, PDF)
- **Diff View**: Show changes between versions
- **Analytics**: Track skill usage and popularity
### Planned for v1.1 (Minor Updates)
- **Bug Fixes**: Address any issues reported by users
- **Documentation**: Add more examples and use cases
- **Error Handling**: More granular error messages
- **Performance**: Optimize parsing for large projects
---
## Version History
| Version | Date | Description |
|---------|------|-------------|
| 1.0.0 | 2025-10-30 | Initial production release |
---
## Migration Guide
### From Nothing to v1.0.0
**New Installation**:
```bash
# 1. Clone or copy the skill
cp -r codex-cli-bridge ~/.claude/skills/
# 2. Install dependencies
pip3 install PyYAML
# 3. Validate installation
python3 ~/.claude/skills/codex-cli-bridge/bridge.py --validate
# 4. Generate AGENTS.md
python3 ~/.claude/skills/codex-cli-bridge/bridge.py
```
---
## Breaking Changes
### None (Initial Release)
Future versions will document breaking changes here.
---
## Deprecations
### None (Initial Release)
Future versions will document deprecations here.
---
## Security Updates
### None (Initial Release)
Security updates will be documented here in future versions.
---
## Contributors
- **Claude Code Skills Factory Team**
- Built with β€οΈ for cross-tool collaboration
---
## Links
- [GitHub Repository](https://github.com/your-repo/codex-cli-bridge)
- [Documentation](./HOW_TO_USE.md)
- [Bug Reports](https://github.com/your-repo/issues)
- [Feature Requests](https://github.com/your-repo/issues)
---
**Legend**:
- β
Implemented
- π Planned
- π Bug Fix
- π Major Feature
- π Documentation
- β‘ Performance
- π Security
---
*Last Updated: 2025-10-30*
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |