codex-reviewlisted
Install: claude install-skill tonydzi/second-brain-starter-kit
# codex-review — "Claude checks Codex"
A thin broker for the review pair. Codex writes the code; Claude reviews its diff independently. (The old note "`codex exec` headless hangs on Windows" is obsolete: on codex-cli 0.141+ headless works natively — verified 2026-07-07 on the laptop and 2026-07-14 on the hub.) File handoff, no shared credentials, subscription (not a paid API).
## When to run it
The owner made a change through Codex (or there is simply a diff/edit in a repository) and wants an independent "second pair of eyes" check. Triggers: see `description`.
## What I do
1. **Identify the target.** Ask for / take the path to the repository where Codex made the change (or the path to a patch file). Default — the working repository the owner named.
2. **Run the engine** (deterministic, 0 of my tokens for the run itself — the review is done by headless `claude -p`):
```
python "%USERPROFILE%\.claude\scripts\cc-review\cc_review.py" --repo "<path to repo>" --model sonnet
```
- model: **Sonnet by default** (the free subscription bucket; in the test it caught both bugs in 25s); **Opus** for hard/safety-critical changes (`--model opus`) — the quality gate.
- other modes: `--range "HEAD~1 HEAD"` (a specific commit), `--diff "<patch.diff>"` (a ready patch), `--task "<task.md>"` (what Codex was asked to do — gives the reviewer context).
3. **Report to the owner:** the verdict (`APPROVE` / `REQUEST_CHANGES`), the list of findings (file:line · severity · what is wrong