Skip to content

alirezarezvani/claude-code-skill-factory / generated-skills/codex-cli-bridge

codex-cli-bridge

Unverified

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

FileKindSize
CHANGELOG.mdmarkdown5.5 KB
HOW_TO_USE.mdmarkdown10.1 KB
INSTALL.mdmarkdown10.2 KB
README.mdmarkdown9.5 KB
SKILL.mdskill md8.5 KB
agents_md_generator.pyscript17.4 KB
bridge.pyexecutablescript7.5 KB
claude_parser.pyscript14.9 KB
codex_executor.pyscript13.0 KB
expected_output.jsonconfig4.7 KB
package.shexecutablescript5.8 KB
project_analyzer.pyscript11.0 KB
safety_mechanism.pyscript12.0 KB
sample_input.jsonconfig1.5 KB
skill_documenter.pyscript9.5 KB

expected_output.json

View on GitHub
{
  "output_file": "AGENTS.md",
  "location": "/Users/example/projects/my-claude-project/AGENTS.md",
  "file_size_estimate": "15-25 KB",
  "line_count_estimate": "400-800 lines",
  "format": "Markdown",
  "structure": {
    "header": {
      "project_name": "my-claude-project",
      "project_type": "GREENFIELD_NEW",
      "description": "Brief project description from CLAUDE.md"
    },
    "quick_reference": {
      "skills_count": 2,
      "agents_count": 1,
      "functional_skills": 1,
      "prompt_skills": 1
    },
    "sections": [
      "Project Overview",
      "Available Skills",
      "Project Structure",
      "Workflow Patterns",
      "MCP Integration",
      "Command Reference",
      "Common Operations",
      "Best Practices"
    ],
    "skills_documentation": [
      {
        "skill_name": "data-visualizer",
        "type": "functional",
        "documentation_includes": [
          "Description",
          "Location (relative path)",
          "Python scripts list with links",
          "Codex CLI usage examples (bash execution)"
        ],
        "usage_example": "cd .claude/skills/data-visualizer\npython chart_generator.py --help"
      },
      {
        "skill_name": "brand-guidelines",
        "type": "prompt-based",
        "documentation_includes": [
          "Description",
          "Location (relative path)",
          "Codex CLI usage examples (prompt reference)"
        ],
        "usage_example": "codex exec -m gpt-5 -s read-only \"Using brand-guidelines at .claude/skills/brand-guidelines/SKILL.md, review this copy\""
      }
    ],
    "workflow_translations": [
      {
        "claude_command": "/code-review",
        "codex_equivalent": "codex exec -m gpt-5 -s read-only \"Review this codebase for quality, security, and performance issues\""
      },
      {
        "claude_command": "/test",
        "codex_equivalent": "codex exec -m gpt-5-codex -s workspace-write \"Run all tests and analyze failures\""
      }
    ],
    "command_reference_table": {
      "columns": ["Operation", "Claude Code", "Codex CLI"],
      "rows": [
        ["Start session", "claude", "codex exec"],
        ["Resume session", "/resume-work", "codex exec resume --last"],
        ["Code review", "/code-review", "codex exec \"review code\""],
        ["Run tests", "/test", "codex exec \"run tests\""]
      ]
    }
  },
  "key_features": [
    "Reference-based (no file duplication - all links to existing files)",
    "Most relevant usage method per skill type",
    "Always uses 'codex exec' not plain 'codex'",
    "Includes MCP server documentation (if configured)",
    "Command reference table (Claude Code ↔ Codex CLI)",
    "Workflow pattern translations",
    "Best practices for Codex CLI users"
  ],
  "validation": {
    "all_file_references_valid": true,
    "all_links_working": true,
    "codex_commands_tested": true,
    "syntax_valid": true
  },
  "sample_excerpt": "# AGENTS.md\n\n**Project**: my-claude-project\n**Purpose**: [Project description]\n**Type**: GREENFIELD_NEW\n**Codex CLI Compatibility**: Full support\n\n---\n\n## Quick Reference\n\n**Project Statistics**:\n- **Skills**: 2 total (1 functional, 1 prompt-based)\n- **Agents**: 1 total\n\n**For Codex CLI Users**:\n- Skills documented with Codex CLI usage examples\n- Use `codex exec` commands (never plain `codex`)\n- Python scripts can be executed directly\n\n---\n\n## Available Skills\n\n### Functional Skills (1)\n\n#### data-visualizer\n\n**Description**: Interactive data visualization and chart generation\n\n**Location**: `.claude/skills/data-visualizer/`\n**Documentation**: [.claude/skills/data-visualizer/SKILL.md](.claude/skills/data-visualizer/SKILL.md)\n\n**Python Scripts**:\n- [chart_generator.py](.claude/skills/data-visualizer/chart_generator.py)\n- [dashboard.py](.claude/skills/data-visualizer/dashboard.py)\n\n**Using with Codex CLI**:\n\n```bash\n# Execute Python scripts directly\ncd .claude/skills/data-visualizer\npython chart_generator.py --help\n```\n\n### Prompt-Based Skills (1)\n\n#### brand-guidelines\n\n**Description**: Corporate branding and style guidelines\n\n**Location**: `.claude/skills/brand-guidelines/`\n**Documentation**: [.claude/skills/brand-guidelines/SKILL.md](.claude/skills/brand-guidelines/SKILL.md)\n\n**Using with Codex CLI**:\n\n```bash\n# Reference in Codex prompt\ncodex exec -m gpt-5 -s read-only \\\n  \"Using brand-guidelines at .claude/skills/brand-guidelines/SKILL.md,\n  review this marketing copy for brand consistency\"\n```",
  "success_indicators": {
    "agents_md_created": true,
    "all_skills_documented": true,
    "all_agents_documented": true,
    "file_references_valid": true,
    "codex_commands_work": true,
    "size_appropriate": true,
    "ready_for_codex_cli": true
  }
}
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: 467kUpdated Claude CodeCodexVerifiedInstall
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: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — 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" — 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: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall