{
  "markdown": "<div align=\"center\">\n\n# codex-review\n\n**Let Claude and Codex review each other's work.**\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![Claude Code Plugin](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet)](https://code.claude.com/docs/en/plugins)\n[![OpenAI Codex](https://img.shields.io/badge/OpenAI-Codex_CLI-412991)](https://github.com/openai/codex)\n[![Blog Post](https://img.shields.io/badge/Blog-Read_the_story-orange)](https://aseemshrey.in/blog/claude-codex-iterative-plan-review/)\n\n---\n\nA Claude Code plugin that sends your plans and code to OpenAI Codex CLI for **iterative, multi-round review**. Claude and Codex go back-and-forth — fixing, refining, and improving — until Codex approves.\n\n[Installation](#installation) · [Usage](#usage) · [How It Works](#how-it-works) · [Configuration](#configuration)\n\n</div>\n\n## Skills\n\n| Skill | What it does |\n|:--|:--|\n| `/codex-review:plan` | Review an implementation plan. Claude revises based on Codex feedback until approved. |\n| `/codex-review:code` | Review code changes from the current session. Claude fixes issues until approved. |\n\n## How It Works\n\n<p align=\"center\">\n<img src=\"https://aseemshrey.in/static/a82ed27bb0a18671cbf0f78bb4a0826b/3ed24/codex-review-loop.png\" alt=\"Codex Review Loop\" width=\"600\" />\n</p>\n\n## Prerequisites\n\n- [**Claude Code**](https://docs.anthropic.com/en/docs/claude-code) — installed and authenticated\n- [**OpenAI Codex CLI**](https://github.com/openai/codex) — `npm install -g @openai/codex`\n- **OpenAI API key** — configured for Codex\n\n## Installation\n\n**Quick install** (run inside Claude Code):\n\n```\n/plugin marketplace add LuD1161/codex-review-skill\n/plugin install codex-review@codex-review-marketplace\n```\n\n**Local / development**\n\n```bash\nclaude --plugin-dir /path/to/codex-review-skill\n```\n\n## Usage\n\n### Review a plan\n\n```\n/codex-review:plan\n```\n\nSend your implementation plan to Codex. Claude automatically revises the plan based on feedback until Codex approves.\n\n### Review code changes\n\n```\n/codex-review:code\n```\n\nGather the git diff from your session and send it to Codex. Claude automatically fixes issues Codex finds.\n\n### Override the model\n\nBoth skills accept a model argument:\n\n```\n/codex-review:plan o4-mini\n/codex-review:code o4-mini\n```\n\n## Configuration\n\n| Option | Default | Description |\n|:--|:--|:--|\n| Model | `gpt-5.3-codex` | Override per-invocation via arguments |\n| Max rounds | `5` | Prevents infinite review loops |\n| Sandbox | `read-only` | Codex can read your codebase but never writes |\n\n## Project Structure\n\n```\ncodex-review-skill/\n├── .claude-plugin/\n│   └── plugin.json          # Plugin manifest\n├── skills/\n│   ├── plan/\n│   │   └── SKILL.md         # Plan review skill\n│   └── code/\n│       └── SKILL.md         # Code review skill\n├── LICENSE\n└── README.md\n```\n\n## Contributing\n\nPRs welcome! If you have ideas for new review skills or improvements to the review prompts, open an issue or submit a pull request.\n\n## License\n\n[MIT](LICENSE)\n\n---\n\n<div align=\"center\">\n<sub>Built with Claude Code + OpenAI Codex — because two heads are better than one.</sub>\n</div>\n",
  "bytes": 3142,
  "sha": "abaceeaa74b0ac2e35ed6d997eba5f01cb6f4333fbf3dc3bc2db33d89e44adfa",
  "repo_slug": "lud1161/codex-review-skill",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_lud1161_codex_review_skill_codex_review_b94e5d08/readme"
}