I labeled 558 AGENTS.md files. Here’s what they say — and what almost nobody writes down

说明与用途

该项目收集了558个AGENTS.md文件，使用9个类别的规则分类，并在英文和中文文件上验证了分类器的精度（92%/70%和88%/73%）。生成的数据集和agent‑charters工具帮助开发者将自己的AGENTS.md文件与可复现的基线进行对比。

问题

Developers lack a systematic view of AGENTS.md content, making it hard to ensure completeness and consistency across repos.

结果

The project produced a reproducible baseline of AGENTS.md content, revealing that prohibitions and build/test commands dominate, while gotchas are rare. The tool enables developers to audit their own files against this baseline.

工作流

• Collect AGENTS.md files from public repos
• Apply rule‑based classifier to assign 9 categories
• Validate classifier against blind‑labeled held‑out samples
• Publish dataset and tooling (agent‑charters)
• Invite external users to run compare and provide feedback

证据

92% precision / 70% recall on 55 English files, 88% / 73% on 50 Chinese files

来源

49% point to some other file; 15% route to a knowledge or rules directory

来源