Claude Code review design: REVIEW.md, base-branch rules, 3-mode gating
FinanceYF5 · x · 2026-11-18
Part 6 of the Claude Code engineering series on code review: a REVIEW.md tells the review agent what to focus on instead of stacking more review models; review rules are read from the base branch so the code under review can't modify its own standards; tests, build and linters run before the PR; and unverified commits pass through off/observe/enforce gating modes for gradual rollout. The quoted part 5 covers the 3-failed-round escalation rule and running only 3–10 relevant checks out of 39.
Related event: Claude Code Team Shares Engineering Practices for AI Coding at Scale(3 posts)→
More from coding & agent
- GPT-6.2 Astra Tops Bug-Hunt Coding Benchmark at 62.7/105, One-Fifth Sonnet's Cost — PawelHuryn · 2026-11-18
- Dev wants a routing model to dispatch intents between Codex and Claude MCPs — TheZachMueller · 2026-11-18
- One dev ships full zombie survival game built by a team of Hermes AI agents — Teknium · 2026-11-18
- 10 ChatGPT + Codex prompts to diagnose and fix a slow laptop yourself — anthara_ai · 2026-11-18
- Agent auto-iterates Triton kernels in background, beats all OSS implementations on Strix Halo — qtnx_ · 2026-11-18
- SimplePost Gives ChatGPT and Claude a Publishing Button for 10 Social Networks — haltakov · 2026-11-18