#365 · Primary category： AI Coding Assistants
skill-codex
A claude code skill to delegate prompts to codex
Project last updated：07/19/26
GitHub Stars
1.4K
Forks
109
Contributors
12
License
MIT
Why we included this project
Claude Code users who want to offload heavier analysis or refactoring to OpenAI's Codex CLI can use this skill to connect the two. It installs as a Claude Code plugin or a standalone skill, and teaches Claude to call `codex exec` and resume sessions with sensible defaults for model choice, reasoning effort, and sandbox mode. So you can ask for a repository review or a refactor in plain language and get back a Codex run summarized by Claude, instead of juggling two terminals and two context windows. The skill also suppresses Codex's thinking tokens by default to keep your Claude context lean, but you can surface them when you want to inspect the reasoning. Teams that mix Anthropic and OpenAI coding agents will find it a practical bridge for keeping one workflow.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.