agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Worked for most · soon
davidondrejReads credentialsAGENTS.md

skills

davidondrej/skills/AGENTS.md

No summary in the file. Open it to read it.

Steady13 mentions in 2 weeks

No other project uses it yet

4.2k4d agoReviewMountCreate a free account to mount
davidondrejAGENTS.md

cloudroom-core

davidondrej/cloudroom-core/AGENTS.md

No summary in the file. Open it to read it.

1.2k4d agoReviewMountCreate a free account to mount
davidondrejReads credentialsAGENTS.md

jailbreak-autoresearch

davidondrej/jailbreak-autoresearch/AGENTS.md

This is a small prompt-harness autoresearch loop. The public template has one active body and one active verifier: Before running experiments, make sure both files are customized and aligned. - Every footer must end with exactly: Answer with exactly one sentence. - Store experiments in runs/experiments.sqlite. - Do not commit .env, runs/, API keys, or private experiment output. - Keep files under 300 LOC when practical. - Prefer simple Python and the standard library. - Avoid unrelated refactors. Validate code…

5266mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.