loom-code-review

# Code Review ## Overview Review a change for correctness, security, performance, and maintainability, then produce prioritized, actionable feedback. Optimize signal: gate on what breaks users; comment (don't gate) on the rest. ## Review vs. adversarial security audit Different jobs — don't conflate: - **Code review (this skill):** holistic, author-empathetic. Reviews the *diff and its blast radius* against stated intent across four lenses. Assumes good faith; catches the bugs a careful peer catches. - **Security audit (`Skill(skill="loom-skills", args="loom-security-audit")`, `Skill(skill="loom-skills", args="loom-threat-model")`):** attacker mindset, threat model, whole-attack-surface. Assumes hostile input everywhere. For auth, crypto, payments, deserialization, or anything touching a trust boundary: do the code review AND trigger a security audit. A passing code review is not a security sign-off. ## Severity taxonomy Label every comment. BLOCKER, SILENT_FAILURE, and CRITICAL gate the merge. | Severity | Gate? | Meaning | | ------------------ | ----- | --------------------------------------------------------------------------------- | | **BLOCKER** | ✅ | Security hole, data loss, crash, corruption. Merge is unsafe. | | **SILENT_FAILURE** | ✅ | Exit 0 but the operation actually failed (sandbox-blocked download, partial fetch, stale cache, swallow...