# AGENTS.md generator: run it free, or from your agent

An AGENTS.md and a CLAUDE.md for your repo from a short form: stack, commands, style, no-go paths, PR rules.

## Prompt

Use looot to write an AGENTS.md for this repo. 1. Set up https://looot.ai/skill.md. 2. Read package.json, the CI config and the README for the install, build, test and lint commands. 3. Write sections for stack, commands, code style, paths not to touch and pull request rules. 4. Add a CLAUDE.md with one line, @AGENTS.md.

## What it needs

Stack, commands, code style rules, paths to leave alone and PR rules

## What comes back

- AGENTS.md text
- CLAUDE.md that imports it
- download for each file

## Endpoints and providers

None. The tool on the web page runs in the browser and calls no endpoint.

## What it costs

Nothing. The tool on the web page runs in the visitor's browser: no account, no API call and no limit per hour. The prompt above runs the same job from your own looot account with current data, billed per call.

## Onboard an agent

Tell a coding agent how to build and test the repo before it edits anything.

## Protect paths

List migrations, secrets and legal files the agent must leave alone.

## One file, many agents

Keep one AGENTS.md and import it from CLAUDE.md so every tool follows the same rules.

## Fewer bad PRs

Put your PR rules where the agent reads them, so its pull requests match.

## What is AGENTS.md?

A markdown file at the root of a repo that tells coding agents how to work in it: commands, style, rules. The format is described at agents.md and is plain markdown with no required fields.

## What is the difference between AGENTS.md and CLAUDE.md?

Claude Code reads CLAUDE.md. Many other agents read AGENTS.md. A CLAUDE.md with the line @AGENTS.md imports the other file, so you keep one set of rules.

## Where do I put the files?

At the root of the repo. Large repos can add more AGENTS.md files in sub-folders for rules that apply only there.

## What should go in an AGENTS.md?

The exact install, build, test and lint commands, code style rules, paths not to touch and pull request rules. Short lines an agent can follow beat long prose.

## Is my input sent anywhere?

No. The files are built in your browser. There is no account and no limit.

## How does my agent use this?

Copy the prompt above. Your agent reads the repo's own config for the commands and writes the same two files, with looot set up from skill.md.

## Related tools

- /free-tools/mcp-config-generator
- /free-tools/llms-txt-generator
- /free-tools/ai-prompt-generator

## Last reviewed

2026-10-14.