Don't Write Markdown Files for Your Coding Agent. Write Scripts
Rules in AGENTS.md are suggestions. A script with a pass or fail result is a constraint.
About Don't Write Markdown Files for Your Coding Agent. Write Scripts
Daniel Nwaneri argues that files like CONTRIBUTING.md, AGENTS.md and CLAUDE.md are recommendations, not constraints. The agent reads them, then has to judge what "use small functions" or "run the tests" means, and the judgment is where it strays.
Why it is worth reading: the fix is to turn preferences into deterministic actions. "Follow the coding style" becomes ./scripts/lint.sh with a pass or fail result, a refactor becomes an ast-grep or jscodeshift run, and make setup, make lint and make test replace a page of instructions. If your agent keeps drifting from your rules, this is the cheapest change to try first.
The facts
- Type
- Guides
- Tags
- AIDeveloper Tools
- Listed
- November 9, 2026
More Guides
See all →- An Agent Said It Deployed. The Containers Were a Day OldFour claims an agent makes about a deploy, and the command that proves each one.
- Jev + Opus: Frontier-Accuracy LLM Judging at 4x Lower CostHightouch's test: a Jev plus Opus hybrid judge matched frontier accuracy at over 4x lower cost.
- Agent Skills Drift: A Feedback Loop for Keeping One TrueAgent skills go stale in six ways while their checks stay green. A step-by-step loop to catch it.
- Four Ways a Test Can Lie to YouWhat 530 agent-written tests taught one developer: checks can be green, or red, and mean nothing.
- Headless Content Marketing: A New (Old) Strategy for SearchAhrefs on pages written mainly for AI answers, why big brands are making them, and what it means.