Codex now uses AGENTS.md rules to automate repo-specific code review
reach_vb · x · 2026-07-22
Codex now applies custom code-review rules from AGENTS.md
Codex can now read review rules from AGENTS.md, letting teams encode the context that usually lives in a few reviewers’ heads and apply it consistently across pull requests.
OpenAI recommends starting with a repository-specific mistake, then testing one change that should trigger the rule, one safe counterexample, and one unrelated change. The point is to make the review signal useful without creating noise.
Related event: Codex Code Review Now Supports Custom Rules via AGENTS.md(3 posts)→
More from coding & agent
- A GitHub roundup lists 100+ free open-source AI agents and skills — Saboo_Shubham_ · 2026-07-22
- Excalidraw-for-agents idea surfaces alongside 100+ open-source AI agents — Saboo_Shubham_ · 2026-07-22
- Built a `brew doctor`-style checker for Skills and MCP conflicts — dbreunig · 2026-07-22
- BasicallyMythos logs Claude Code reroutes and can swap the fallback model to Kimi K3 — JoshuaJBouw · 2026-07-22
- TypeScript SDK unifies OpenAI, Anthropic, Google and other providers — j4ys0nj · 2026-07-22
- A Codex meme turns a flat “great” into the whole joke — Aizkmusic · 2026-07-22