Skip to content
Back to search

openai-codex

MarketplaceWorks with Claude CodeOfficial: OpenAIGitHub

Use Codex from Claude Code to review code or delegate tasks.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/openai-codex-plugin-cc/badge.svg)](/listings/openai-codex-plugin-cc)

HTML

<a href="/listings/openai-codex-plugin-cc"><img src="/api/listings/openai-codex-plugin-cc/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Add the marketplace in Claude Code:

/plugin marketplace add openai/codex-plugin-cc

Install the plugin:

/plugin install codex@openai-codex

Reload plugins:

/reload-plugins

Then run:

/codex:setup

`/codex:setup` will tell you whether Codex is ready. If Codex is missing and npm is available, it can offer to install Codex for you.

If you prefer to install Codex yourself, use:

npm install -g @openai/codex

If Codex is installed but not logged in yet, run:

!codex login

After install, you should see:

- the slash commands listed below - the `codex:codex-rescue` subagent in `/agents`

One simple first run is:

/codex:review --background
/codex:status
/codex:result

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 21 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "openai-codex",
  3. "owner": {
  4. "name": "OpenAI"
  5. },
  6. "metadata": {
  7. "description": "Codex plugins to use in Claude Code for delegation and code review.",
  8. "version": "1.0.6"
  9. },
  10. "plugins": [
  11. {
  12. "name": "codex",
  13. "description": "Use Codex from Claude Code to review code or delegate tasks.",
  14. "version": "1.0.6",
  15. "author": {
  16. "name": "OpenAI"
  17. },
  18. "source": "./plugins/codex"
  19. }
  20. ]
  21. }
README.md · README · 320 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Codex plugin for Claude Code
  2. Use Codex from inside Claude Code for code reviews or to delegate tasks to Codex.
  3. This plugin is for Claude Code users who want an easy way to start using Codex from the workflow
  4. they already have.
  5. <video src="./docs/plugin-demo.webm" controls muted playsinline autoplay></video>
  6. ## What You Get
  7. - `/codex:review` for a normal read-only Codex review
  8. - `/codex:adversarial-review` for a steerable challenge review
  9. - `/codex:rescue`, `/codex:transfer`, `/codex:status`, `/codex:result`, and `/codex:cancel` to delegate work, hand off sessions, and manage background jobs
  10. ## Requirements
  11. - **ChatGPT subscription (incl. Free) or OpenAI API key.**
  12. - Usage will contribute to your Codex usage limits. [Learn more](https://developers.openai.com/codex/pricing).
  13. - **Node.js 18.18 or later**
  14. ## Install
  15. Add the marketplace in Claude Code:
  16. ```bash
  17. /plugin marketplace add openai/codex-plugin-cc
  18. ```
  19. Install the plugin:
  20. ```bash
  21. /plugin install codex@openai-codex
  22. ```
  23. Reload plugins:
  24. ```bash
  25. /reload-plugins
  26. ```
  27. Then run:
  28. ```bash
  29. /codex:setup
  30. ```
  31. `/codex:setup` will tell you whether Codex is ready. If Codex is missing and npm is available, it can offer to install Codex for you.
  32. If you prefer to install Codex yourself, use:
  33. ```bash
  34. npm install -g @openai/codex
  35. ```
  36. If Codex is installed but not logged in yet, run:
  37. ```bash
  38. !codex login
  39. ```
  40. After install, you should see:
  41. - the slash commands listed below
  42. - the `codex:codex-rescue` subagent in `/agents`
  43. One simple first run is:
  44. ```bash
  45. /codex:review --background
  46. /codex:status
  47. /codex:result
  48. ```
  49. ## Usage
  50. ### `/codex:review`
  51. Runs a normal Codex review on your current work. It gives you the same quality of code review as running `/review` inside Codex directly.
  52. > [!NOTE]
  53. > Code review especially for multi-file changes might take a while. It's generally recommended to run it in the background.
  54. Use it when you want:
  55. - a review of your current uncommitted changes
  56. - a review of your branch compared to a base branch like `main`
  57. Use `--base <ref>` for branch review. It also supports `--wait` and `--background`. It is not steerable and does not take custom focus text. Use [`/codex:adversarial-review`](#codexadversarial-review) when you want to challenge a specific decision or risk area.
  58. Examples:
  59. ```bash
  60. /codex:review
  61. /codex:review --base main
  62. /codex:review --background
  63. ```
  64. This command is read-only and will not perform any changes. When run in the background you can use [`/codex:status`](#codexstatus) to check on the progress and [`/codex:cancel`](#codexcancel) to cancel the ongoing task.
  65. ### `/codex:adversarial-review`
  66. Runs a **steerable** review that questions the chosen implementation and design.
  67. It can be used to pressure-test assumptions, tradeoffs, failure modes, and whether a different approach would have been safer or simpler.
  68. It uses the same review target selection as `/codex:review`, including `--base <ref>` for branch review.
  69. It also supports `--wait` and `--background`. Unlike `/codex:review`, it can take extra focus text after the flags.
  70. Use it when you want:
  71. - a review before shipping that challenges the direction, not just the code details
  72. - review focused on design choices, tradeoffs, hidden assumptions, and alternative approaches
  73. - pressure-testing around specific risk areas like auth, data loss, rollback, race conditions, or reliability
  74. Examples:
  75. ```bash
  76. /codex:adversarial-review
  77. /codex:adversarial-review --base main challenge whether this was the right caching and retry design
  78. /codex:adversarial-review --background look for race conditions and question the chosen approach
  79. ```
  80. This command is read-only. It does not fix code.
  81. ### `/codex:rescue`
  82. Hands a task to Codex through the `codex:codex-rescue` subagent.
  83. Use it when you want Codex to:
  84. - investigate a bug
  85. - try a fix
  86. - continue a previous Codex task
  87. - take a faster or cheaper pass with a smaller model
  88. > [!NOTE]
  89. > Depending on the task and the model you choose these tasks might take a long time and it's generally recommended to force the task to be in the background or move the agent to the background.
  90. It supports `--background`, `--wait`, `--resume`, and `--fresh`. If you omit `--resume` and `--fresh`, the plugin can offer to continue the latest rescue thread for this repo.
  91. Examples:
  92. ```bash
  93. /codex:rescue investigate why the tests started failing
  94. /codex:rescue fix the failing test with the smallest safe patch
  95. /codex:rescue --resume apply the top fix from the last run
  96. /codex:rescue --model gpt-5.4-mini --effort medium investigate the flaky integration test
  97. /codex:rescue --model spark fix the issue quickly
  98. /codex:rescue --background investigate the regression
  99. ```
  100. You can also just ask for a task to be delegated to Codex:
  101. ```text
  102. Ask Codex to redesign the database connection to be more resilient.
  103. ```
  104. **Notes:**
  105. - if you do not pass `--model` or `--effort`, Codex chooses its own defaults.
  106. - if you say `spark`, the plugin maps that to `gpt-5.3-codex-spark`
  107. - follow-up rescue requests can continue the latest Codex task in the repo
  108. ### `/codex:transfer`
  109. Creates a persistent Codex thread from the current Claude Code session and prints a `codex resume <session-id>` command.
  110. Use it when you started a debugging or implementation conversation in Claude Code and want to continue that same context directly in Codex.
  111. Examples:
  112. ```bash
  113. /codex:transfer
  114. /codex:transfer --source ~/.claude/projects/-Users-me-repo/<session-id>.jsonl
  115. ```
  116. The plugin's existing `SessionStart` hook supplies the current transcript path automatically; `--source` is available as a manual override. The transfer uses Codex's external-agent session importer, so it follows the same conversion rules as importing Claude history in the Codex App and creates visible turns that can be continued in the App or TUI. The source must be under `~/.claude/projects`, and older Codex versions that do not expose session import must be upgraded before using this command.
  117. ### `/codex:status`
  118. Shows running and recent Codex jobs for the current repository.
  119. Examples:
  120. ```bash
  121. /codex:status
  122. /codex:status task-abc123
  123. ```
  124. Use it to:
  125. - check progress on background work
  126. - see the latest completed job
  127. - confirm whether a task is still running
  128. ### `/codex:result`
  129. Shows the final stored Codex output for a finished job.
  130. When available, it also includes the Codex session ID so you can reopen that run directly in Codex with `codex resume <session-id>`.
  131. Examples:
  132. ```bash
  133. /codex:result
  134. /codex:result task-abc123
  135. ```
  136. ### `/codex:cancel`
  137. Cancels an active background Codex job.
  138. Examples:
  139. ```bash
  140. /codex:cancel
  141. /codex:cancel task-abc123
  142. ```
  143. ### `/codex:setup`
  144. Checks whether Codex is installed and authenticated.
  145. If Codex is missing and npm is available, it can offer to install Codex for you.
  146. You can also use `/codex:setup` to manage the optional review gate.
  147. #### Enabling review gate
  148. ```bash
  149. /codex:setup --enable-review-gate
  150. /codex:setup --disable-review-gate
  151. ```
  152. When the review gate is enabled, the plugin uses a `Stop` hook to run a targeted Codex review based on Claude's response. If that review finds issues, the stop is blocked so Claude can address them first.
  153. > [!WARNING]
  154. > The review gate can create a long-running Claude/Codex loop and may drain usage limits quickly. Only enable it when you plan to actively monitor the session.
  155. ## Typical Flows
  156. ### Review Before Shipping
  157. ```bash
  158. /codex:review
  159. ```
  160. ### Hand A Problem To Codex
  161. ```bash
  162. /codex:rescue investigate why the build is failing in CI
  163. ```
  164. ### Start Something Long-Running
  165. ```bash
  166. /codex:adversarial-review --background
  167. /codex:rescue --background investigate the flaky test
  168. ```
  169. Then check in with:
  170. ```bash
  171. /codex:status
  172. /codex:result
  173. ```
  174. ## Codex Integration
  175. The Codex plugin wraps the [Codex app server](https://developers.openai.com/codex/app-server). It uses the global `codex` binary installed in your environment and [applies the same configuration](https://developers.openai.com/codex/config-basic).
  176. ### Common Configurations
  177. If you want to change the default reasoning effort or the default model that gets used by the plugin, you can define that inside your user-level or project-level `config.toml`. For example to always use `gpt-5.4-mini` on `high` for a specific project you can add the following to a `.codex/config.toml` file at the root of the directory you started Claude in:
  178. ```toml
  179. model = "gpt-5.4-mini"
  180. model_reasoning_effort = "high"
  181. ```
  182. Your configuration will be picked up based on:
  183. - user-level config in `~/.codex/config.toml`
  184. - project-level overrides in `.codex/config.toml`
  185. - project-level overrides only load when the [project is trusted](https://developers.openai.com/codex/config-advanced#project-config-files-codexconfigtoml)
  186. Check out the Codex docs for more [configuration options](https://developers.openai.com/codex/config-reference).
  187. ### Moving The Work Over To Codex
  188. Delegated tasks and any [stop gate](#what-does-the-review-gate-do) run can also be directly resumed inside Codex by running `codex resume` either with the specific session ID you received from running `/codex:result` or `/codex:status` or by selecting it from the list.
  189. This way you can review the Codex work or continue the work there.
  190. ## FAQ
  191. ### Do I need a separate Codex account for this plugin?
  192. If you are already signed into Codex on this machine, that account should work immediately here too. This plugin uses your local Codex CLI authentication.
  193. If you only use Claude Code today and have not used Codex yet, you will also need to sign in to Codex with either a ChatGPT account or an API key. [Codex is available with your ChatGPT subscription](https://developers.openai.com/codex/pricing/), and [`codex login`](https://developers.openai.com/codex/cli/reference/#codex-login) supports both ChatGPT and API key sign-in. Run `/codex:setup` to check whether Codex is ready, and use `!codex login` if it is not.
  194. ### Does the plugin use a separate Codex runtime?
  195. No. This plugin delegates through your local [Codex CLI](https://developers.openai.com/codex/cli/) and [Codex app server](https://developers.openai.com/codex/app-server/) on the same machine.
  196. That means:
  197. - it uses the same Codex install you would use directly
  198. - it uses the same local authentication state
  199. - it uses the same repository checkout and machine-local environment
  200. ### Will it use the same Codex config I already have?
  201. Yes. If you already use Codex, the plugin picks up the same [configuration](#common-configurations).
  202. ### Can I keep using my current API key or base URL setup?
  203. Yes. Because the plugin uses your local Codex CLI, your existing sign-in method and config still apply.
  204. If you need to point the built-in OpenAI provider at a different endpoint, set `openai_base_url` in your [Codex config](https://developers.openai.com/codex/config-advanced/#config-and-state-locations).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.