GitHub analyzes 2,500+ repos to summarize top 5 patterns for writing agents.md
bibryam · x · 2026-08-30
GitHub's official blog analyzed over 2,500 agents.md files across public repositories to identify the key patterns for effectively configuring AI agents:
- Put commands early: Place specific instructions at the top.
- Show code, not prose: Use code snippets instead of descriptions to define style.
- Name the exact stack: Specify frameworks and libraries precisely.
- Set clear boundaries: Explicitly define what the agent should not do.
- Cover tests, structure, style, and Git: Include the full workflow context.
The post emphasizes that agents need an operating manual, not a personality. Vague personas like "helpful assistant" often fail, while specific roles (e.g., React test engineer) with clear constraints yield better results.
More from coding & agent
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Vibe-coded iPhone Duo sniping bot built with Codex in 17 minutes, 41 tests passing — xiaohu · 2026-10-16