Menu
Configure or explain the optional Codex Stop hook that can run a read-only Claude review when a turn ends.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Compatibility alias for stricter Claude review; prefer claude-review with --adversarial for new use.
Diagnose whether Claude Code is installed and authenticated for this local Codex plugin without making a billable Claude call.
Run a structured, read-only Claude Code review over the current git diff or a branch diff.
Delegate a foreground read-only or write-capable task to Claude Code from Codex using the local companion script.
Cancel a running Claude Code companion job by sending process signals through the plugin job index.
Analyze plugin-owned Claude Code job logs for permission prompts and export reviewed allowedTools arguments.
| name | claude-stop-review-hook |
| description | Configure or explain the optional Codex Stop hook that can run a read-only Claude review when a turn ends. |
Use this skill when the user wants Claude Code to review changes automatically when a Codex turn stops.
The plugin bundles hooks/hooks.json with a Stop hook, but the hook helper is inert until explicitly configured with the plugin root and then enabled for review. Codex also requires non-managed hooks to be reviewed and trusted with /hooks before they run.
First point the bundled hook config at this plugin using an absolute path before launching Codex:
export CLAUDE_COMPANION_PLUGIN_ROOT=/absolute/path/to/cc-plugin-codex
Then enable review in the shell before launching Codex:
export CLAUDE_COMPANION_STOP_REVIEW=1
Or enable it per repository:
mkdir -p .codex
touch .codex/claude-stop-review.enabled
The per-repository marker enables review after the hook helper is located; it does not replace CLAUDE_COMPANION_PLUGIN_ROOT.
By default, the hook reports review findings without blocking Codex. To block on high or critical findings:
export CLAUDE_COMPANION_STOP_REVIEW_BLOCKING=1
Useful options:
CLAUDE_COMPANION_STOP_REVIEW_MODEL=opus to choose the model for serious review gates.CLAUDE_COMPANION_STOP_REVIEW_EFFORT=low to choose Claude Code effort.CLAUDE_COMPANION_STOP_REVIEW_BASE=main to review main...HEAD.CLAUDE_COMPANION_STOP_REVIEW_ADVERSARIAL=1 to use the adversarial review prompt.Model guidance:
CLAUDE_COMPANION_STOP_REVIEW_MODEL=opus for serious blocking gates or important merge-readiness checks.CLAUDE_COMPANION_STOP_REVIEW_EFFORT=low only for smoke tests, cheap sanity checks, or explicitly low-effort requests.Manual smoke test:
Use the companion script from the installed plugin root. If the current working
directory is not this plugin checkout, resolve the script relative to this skill
file, for example ../../scripts/claude-companion.mjs.
node scripts/claude-companion.mjs hook-stop-review --json
The hook always uses Claude Code --permission-mode plan and should not edit files.