Inizia
Code Review Board — 4-Lens AI Code Review

Code Review Board — 4-Lens AI Code Review

Four independent AI reviewers — Security Skeptic, Reliability Realist, Maintainability Pragmatist, and Performance Pessimist — each review your diff blind to the others' verdicts, so real bugs don't get averaged away into one polite summary.
#Ingegneria
Valutazione
Servono altre valutazioni
Venduti
0
Come si usa
Scarica

How it works

Code Review Board runs your diff through a three-phase adversarial review process instead of a single pass:

Phase 1 — Four independent reviewers, blind. Security Skeptic, Reliability Realist, Maintainability Pragmatist, and Performance Pessimist each review the same code without seeing each other's notes.

Phase 2 — Cross-examination. Every finding gets challenged or corroborated by the other three lenses — false positives get contested with a concrete reason, and issues that multiple lenses independently flag get marked as a stronger signal.

Phase 3 — Board verdict. Every finding is tagged CONFIRMED / CORROBORATED / DISPUTED, followed by one merge recommendation line you can actually act on.

Sample output

## Phase 3 — Board verdict
1. **[CORROBORATED]** Unparameterized SQL in refund handler (payments.js:42) — Security + Reliability both flagged this independently. Fix: use parameterized queries.
2. **[DISPUTED]** Possible stored XSS in note field — Security raised it, Maintainability countered: no render path exists in this diff. Human call needed.

**Merge recommendation:** Block merge — 1 CORROBORATED security finding.

Use cases

  • Get a rigorous second opinion on a PR before merging, without setting up a CI pipeline
  • Catch the specific class of bug a single-pass AI review tends to average away or soften into "looks good overall"
  • Use inside Claude Code, Codex, or OpenClaw sessions directly — paste a diff and go

FAQ

Does this replace static analysis tools (linters, SAST)? No — it's a reasoning-based review layer, not a substitute for running your existing linter/type-checker/test suite.

What if my diff contains secrets or real customer data? Redact them before pasting. The Skill treats any secret it spots as a Security finding, but it does not fetch or store your code anywhere on its own.

Is this the same as the free "Code Review Board" GitHub Action? Related but separate — the GitHub Action runs 3 free lenses automatically on every PR via CI. This Skill runs all 4 lenses plus the cross-examination and verdict phases on demand, inside your agent session.


Informativa sulla privacy

https://glowhalo.github.io/privacy/