ProTip: lock down code sections in agents.md to stop agents from breaking them
cyrus_zei · x · 2026-09-13
Replying to a complaint that AI coding agents keep re-breaking just-fixed code, cyruszei shares a tip: create an agents.md file that explicitly locks down sections/features you don't want touched. The agent will leave them alone and ask before changing them, giving you more control over LLM mistakes.
More from coding & agent
- Dev builds an AI assistant inside ComfyUI that can inspect and edit your workflow — HungryDonat · 2026-09-13
- App Store Connect CLI 5.3.0 adds native PKG publishing path for macOS — rudrank · 2026-09-13
- Agent swarm leaderboard 'turkish-delight' dethroned; anyone can submit an agent in 2 minutes — mervenoyann · 2026-09-13
- Dev open-sources MnemoBrain, an agent memory system that works without prompt-based recall — AxelFooley · 2026-09-13
- Dev seeks validation for a control gateway managing agent credentials, permissions and auditing — Decent_Progress7631 · 2026-09-13
- Dev builds 'recursive self-improvement': scheduled automations with MCP access that fix codebases — DanielLockyer · 2026-09-13