CC Plugin Codex

Use Claude from inside Codex for code reviews or to delegate tasks to Claude Code.

This repository is the source for the Codex-native Claude Companion plugin bundle. It is meant to be a reverse port of openai/codex-plugin-cc: the original brings Codex into Claude Code, while this project brings Claude-backed review and delegation workflows into Codex.

The installable plugin bundle lives under claude/README.md.

What You Get

$claude-review for a normal read-only Claude review from Codex
$claude-adversarial-review for a steerable challenge review
$claude-delegate, $claude-status, $claude-result, and $claude-cancel to delegate and manage longer-running Claude tasks
$claude-rescue as a backwards-compatible alias for $claude-delegate
$claude-setup to verify Claude Code readiness and report the current review-gate limitation honestly

Requirements

Codex with plugin support and the codex CLI available on PATH
Claude Code installed and available as claude
Node.js 18.18 or later available as node

Install

codex plugin marketplace add pejmanjohn/cc-plugin-codex
codex plugin add claude-companion@cc-plugin-codex-marketplace

This uses Codex's normal plugin marketplace flow directly from GitHub. No repo-local installer or machine-specific paths are required.

Verify

Open Codex:

codex

If you normally use the Codex Mac app and it is already open, restart it instead.

Then start a new thread and run:

$claude-setup

After install, you should see the bundled Claude Companion skills in Codex. The full bundle-level usage guide lives in claude/README.md.

Update

codex plugin marketplace upgrade cc-plugin-codex-marketplace
codex plugin add claude-companion@cc-plugin-codex-marketplace

Start a new Codex thread after reinstalling so the updated skills are loaded.

Uninstall

codex plugin remove claude-companion@cc-plugin-codex-marketplace
codex plugin marketplace remove cc-plugin-codex-marketplace

The first command removes the installed plugin. The second removes the GitHub marketplace source from Codex.

Usage

`$claude-review`

Runs a normal read-only Claude review on your current work or against a base ref.

`$claude-adversarial-review`

Runs a more skeptical review that questions implementation choices, tradeoffs, and failure modes.

`$claude-delegate`

Delegates a foreground or background task to Claude and stores durable job state for follow-up.

By default, delegation uses Claude Code model opus with effort high.

$claude-delegate investigate the flaky checkout test

Override the model or effort level per task:

$claude-delegate --model sonnet --effort medium investigate the flaky checkout test
$claude-delegate --background --model opus --effort xhigh implement the retry fix

Persist new defaults with setup:

$claude-setup --model opus --effort high

Claude Code currently accepts effort levels such as low, medium, high, xhigh, and max. Model values can be aliases such as sonnet or opus, or full Claude model names supported by your Claude Code installation.

$claude-rescue remains available as a backwards-compatible alias.

`$claude-status`, `$claude-result`, `$claude-cancel`

Shows running and recent jobs, returns the stored final output, or cancels an active background task.

`$claude-setup`

Checks whether Claude Code is installed and usable, and reports the current stop-time review-gate limitation.

Current Limitation

The plugin is usable today, but it is not fully functionally equivalent to openai/codex-plugin-cc.

The missing piece is the automatic stop-time review gate. Codex supports repo-level and user-level hooks, but validated installed-plugin runs still did not execute bundled plugin hooks after official install, so this plugin reports that limitation honestly instead of pretending the gate works.

Troubleshooting

Codex blocks `$claude-delegate` as data exfiltration

Codex may refuse to launch the delegate command with a message like "this delegates repository context to an external service". Two things to know:

What data goes where. Delegation runs your locally installed Claude Code CLI under your own Anthropic account. Workspace context is sent to Anthropic's API exactly as if you ran claude in your own terminal. There is no third-party or plugin-operated service involved (see PRIVACY.md).
Who decides. The approval layer belongs to Codex, not to this plugin. The plugin cannot and will not bypass it. If Codex denies the command after you approve it, that is a Codex-side policy decision to raise with OpenAI.

One known aggravator: Codex sometimes invents Claude Code CLI flags — most commonly --dangerously-skip-permissions — when composing the command, which makes an ordinary delegation look like a safety bypass to the approval layer. This plugin never uses that flag; the skill instructions now list the supported flags explicitly, and claude-companion.mjs rejects unknown flags with an error instead of passing them along. If you see a rejection quoting a flag not documented above, retry the skill — the corrected command usually passes review.

Releases

This repo uses simple tag-based releases.

Keep package.json and claude/.codex-plugin/plugin.json on the same semantic version.
Create a tag like v0.1.0.
Push the tag to GitHub.

The release workflow will verify the tag matches both version files, run the Claude plugin test suite, and publish a GitHub release with generated notes.

Development

npm ci
npm run test:claude

Helpful files:

For local development, add this checkout as a local marketplace instead of using the GitHub source:

codex plugin marketplace add /path/to/cc-plugin-codex
codex plugin add claude-companion@cc-plugin-codex-marketplace