Code Audit
Two-pass audit on recent changes or specified files: an adversarial Opus deep review followed by an independent Codex second opinion.
Runs on the latest Opus with
effort: xhigh. Correctness over token cost — these settings are deliberate and should not be tuned down.
How this works
Pass 1 — Opus deep audit. Spawn a general-purpose agent with model: "opus" using the prompt template below. The agent reads code, runs verification commands, and returns a structured
[Description truncada. Veja o README completo no GitHub.]