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
- AIE Code Summit 2026 opens applications: 800 seats, keynotes streamed free — trq212 · 2026-10-27
- TRL adds Score Centering, a simple fix for RLHF training instability — lvwerra · 2026-10-27
- Precompute golden answers and match at runtime for exact wording control — colinmcnamara · 2026-10-27
- Dev argues there's still alpha in working with your coding agent interactively — alex_frantic · 2026-10-27
- Researchers launch AMA on patterns for safer AI agents used by citizen developers — Loose_Rip359 · 2026-10-27
- Gradio Adds In-Chat Human-in-the-Loop So ML Intern Pauses Before Training — Gradio · 2026-10-27