My agent.md to improve LLM-assisted code quality
- ID
- 17395
- Status
- summarized
- Published
- 24 Aug 2026, 1:59 AM
- Fetched
- 26 Aug 2026, 2:57 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://fabiensanglard.net/agent.md/index.html
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.5
- Created
- 26 Aug 2026, 2:57 AM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Fabien Sanglard shares his agent.md file—a set of coding style rules injected into LLM coding sessions via agentic IDEs like Antigravity and VS Code's Claude Code plugin. After finding AI-generated code unusable (spaghetti, no comments, no structure), he iterated by repeatedly giving the same feedback, then codified those rules into agent.md: no magic numbers, function names under 30 characters, enums over booleans for parameters, early returns to reduce indentation, minimal but pointed comments, and no superlatives or praise from the LLM.
Why it matters
If you use agentic IDEs (Claude Code, Antigravity, Gemini), dropping an agent.md at your project root with explicit style rules eliminates the repetitive 'reviewing a junior dev' loop. Sanglard's specific rules—especially 'use enums not booleans for parameters' and 'no superlatives, give me the cold hard truth'—are concrete starting points you can copy and adapt today. The symlink trick (gemini.md/claude.md → agent.md) lets one file work across multiple tools.
Discussion angle
Compare agent.md rules against your own team's real pain points with AI-generated code—which rules from Sanglard's list would you add, remove, or change for your stack?