Review code
Pick the reviewer
- Codex (default when
codex-bridgeis on PATH): an unanchored second read. Read~/agent-skills/shared/codex-bridge.mdonce per session first. - Out of quota (
"quotaExhausted": true): rerun with--agent antigravity, then--agent opencode(order in~/agent-skills/shared/agent-routing.md). If none is available, review it yourself in the same output format. In Claude Code, the built-in/code-reviewis an alternative the user can run.
Steps
Target: uncommitted changes (default), a branch against its base (
--base main) or one commit (--commit SHA). For a non-git folder usecodex-bridge run --kind reviewwith a read-only prompt naming the files.Focus note (short): what the change is for, the risky parts, out of scope. Don't pass your own conclusions.
Run (read-only is enforced by the bridge; run in the background for big diffs):
codex-bridge review --cd "<repo>" [--base main | --commit SHA] --timeout 900 \ --prompt "Focus: <intent and risks>. Report findings as: severity (high/medium/low), file:line, the problem, a concrete failure scenario, and the suggested fix. Separate real bugs from style. Say 'no findings' if there are none."Verify every finding against the code: confirmed, plausible or rejected (with the reason). Don't relay unverified claims. A runtime claim (browser API behavior, layout, timing, an observer missing an element) is checked in the real runtime, with a browser probe or a test that fails, not by reading code. A reviewer once said a ChapterRail IntersectionObserver
rootMarginwould miss short chapters, and a Chromium probe showed it did not.Report: run id, confirmed findings by severity, rejected ones in one line each. Change code only if asked; then fix each confirmed bug with a regression test (
fix-bug).