Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/openai/codex-plugin-cc/llms.txt

Use this file to discover all available pages before exploring further.

If you are already signed into Codex on this machine, that account works immediately. The plugin uses your local Codex CLI authentication — no separate login is needed.If you only use Claude Code today and have not used Codex yet, you need to sign in to Codex with either a ChatGPT account or an API key. Codex is available with a ChatGPT subscription, including the Free tier. Run /codex:setup to check whether Codex is ready, then run !codex login if it is not authenticated.
No. The plugin delegates through your local Codex CLI and Codex app server on the same machine. That means:
  • it uses the same Codex install you would use directly
  • it uses the same local authentication state
  • it uses the same repository checkout and machine-local environment
Yes. The plugin picks up your existing ~/.codex/config.toml (user-level) and .codex/config.toml (project-level) config files, the same as running Codex directly.
Yes. Because the plugin uses your local Codex CLI, your existing sign-in method and openai_base_url config still apply. No additional configuration is needed.
Run /codex:setup. It checks Node.js, npm, Codex CLI installation, and authentication status, and shows recommended next steps for anything that is missing or not configured. If Codex is missing and npm is available, it can offer to install Codex for you.
Passing --background spawns a detached worker process that runs the Codex task independently of your Claude Code session. You can continue working in Claude Code while Codex runs.Use /codex:status to check the job’s progress and /codex:result to retrieve its output once it completes.
Yes. Pass --model <model-name> to /codex:rescue to use a specific model for that run. Use spark as a shorthand for gpt-5.3-codex-spark. For reasoning effort, pass --effort <level> (accepted values: none, minimal, low, medium, high, xhigh).
/codex:rescue --model spark fix the issue quickly
/codex:rescue --model gpt-5.4-mini --effort medium investigate the flaky integration test
If you omit --model and --effort, Codex uses its own defaults, or whatever you have set in your config.toml.

Build docs developers (and LLMs) love