codex-cli-bridge

这段内容是审核时保存的快照。外部来源才是完整且最新的版本。

---
name: codex-cli-bridge
description: Bridge 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
---

# Codex CLI Bridge Skill

## Purpose

This skill creates a comprehensive bridge between **Claude Code** and **OpenAI's Codex CLI**, enabling seamless interoperability through:

1. **Documentation Translation**: Converts CLAUDE.md → AGENTS.md (reference-based, no file duplication)
2. **Execution Helpers**: Python wrappers for Codex CLI commands (always uses `codex exec`)
3. **Skill Documentation**: Makes Claude Skills accessible to Codex CLI users

## Key Capabilities

### 1. CLAUDE.md → AGENTS.md Generation
- Parses CLAUDE.md and project structure
- Scans `.claude/skills/`, `.claude/agents/`, `documentation/` folders
- Generates comprehensive AGENTS.md with file path references
- **Reference-based**: No file duplication, only links to existing files
- Documents Skills with most relevant usage method (bash scripts vs prompt references)

### 2. Safety Mechanism
- **Auto-checks Codex CLI installation** (`codex --version`)
- **Auto-runs `/init`** if CLAUDE.md missing (with user notification)
- Validates authentication and environment
- User-friendly error messages

### 3. Codex CLI Execution Helpers
- `exec_analysis()` - Read-only analysis tasks (gpt-5, read-only sandbox)
- `exec_edit()` - Code editing tasks (gpt-5-codex, workspace-write)
- `exec_with_search()` - Web search-enabled tasks
- `resume_session()` - Continue last Codex session
- **Always uses `codex exec`** (never plain `codex` - critical for Claude Code)

### 4. Skill Documentation for Codex CLI
- **Prompt-only skills**: Show how to reference in Codex prompts
- **Functional skills**: Show how to execute Python scripts directly
- **Complex skills**: Show both methods
- Includes proper `codex exec` command syntax
- Model selection guidance (gpt-5 vs gpt-5-codex)

## Input Requirements

### For AGENTS.md Generation
```json
{
  "action": "generate-agents-md",
  "project_root": "/path/to/project",
  "options": {
    "validate_codex": true,
    "auto_init": true,
    "include_mcp": true,
    "skill_detail_level": "relevant"
  }
}
```

### For Codex Execution
```json
{
  "action": "codex-exec",
  "task_type": "analysis|edit|search",
  "prompt": "Your task description",
  "model": "gpt-5|gpt-5-codex",
  "sandbox": "read-only|workspace-write|danger-full-access"
}
```

## Output Formats

### AGENTS.md Structure
```markdown
# AGENTS.md

## Project Overview
[From CLAUDE.md]

## Available Skills
### Skill Name
**Location**: `path/to/skill/`
**Using from Codex CLI**: [Most relevant method]

## Workflow Patterns
[Slash commands → Codex equivalents]

## MCP Integration
[MCP server references]

## Command Reference
| Claude Code | Codex CLI |
|-------------|-----------|
[Mappings]
```

### Execution Helper Output
```python
{
  "status": "success|error",
  "output": "Command output",
  "session_id": "uuid",
  "model_used": "gpt-5|gpt-5-codex",
  "command": "codex exec ..."
}
```

## Python Scripts

### safety_mechanism.py
- Check Codex CLI installation
- Validate CLAUDE.md exists (auto-run /init if missing)
- Environment validation
- User notifications

### claude_parser.py
- Parse CLAUDE.md sections
- Scan skills, agents, commands
- Extract quality gates and MCP configuration
- Return file paths only (no content duplication)

### project_analyzer.py
- Auto-detect project structure
- Discover all Claude Code assets
- Generate project metadata
- Build reference map

### agents_md_generator.py
- Template-based AGENTS.md generation
- File path references (no duplication)
- Skill documentation (most relevant method)
- Workflow translation (Claude → Codex)

### skill_documenter.py
- Document skills for Codex CLI users
- Determine most relevant usage method per skill type
- Generate bash examples for Python scripts
- Create Codex prompt templates

### codex_executor.py
-