AGENTS.md and CLAUDE.md Generator

AGENTS.md and CLAUDE.md Generator

Create an AGENTS.md or CLAUDE.md for your repo from a short form: commands, structure, code style, testing and boundaries. Copy or download it. Free, runs in your browser.

Describe your project

Your file

How to use the AGENTS.md and CLAUDE.md Generator

  1. Enter your project name, a short description and the tech stack.
  2. Fill in the install, dev, test, lint and build commands.
  3. List the folder structure, code style rules and what the agent should always, ask first, or never do.
  4. Pick AGENTS.md, CLAUDE.md, or a CLAUDE.md that imports AGENTS.md.
  5. Copy or download the file and put it in the root of your repository.

Frequently asked questions

What is AGENTS.md?

AGENTS.md is a plain Markdown file in your repo root that tells AI coding agents how your project works: setup commands, structure, code style and boundaries. It is often described as a README for agents.

What is CLAUDE.md?

CLAUDE.md is the memory file Claude Code reads at the start of each session. It holds project instructions in the same way AGENTS.md does for other agents.

Can Claude Code use AGENTS.md?

Claude Code reads CLAUDE.md. Its documentation says a CLAUDE.md can import other files with the @path syntax, so a CLAUDE.md containing @AGENTS.md pulls the AGENTS.md content in. The third file option above creates exactly that.

How long should these files be?

The Claude Code docs recommend under 200 lines per CLAUDE.md, because longer files use more context and reduce adherence. Move rarely needed detail into separate files.

What should I put in Always, Ask first and Never?

Always: checks to run, such as tests. Ask first: risky steps like adding dependencies or changing schemas. Never: hard limits like committing secrets or editing generated files.

Is my project information uploaded?

No. Everything is generated in your browser.

Everything runs in your browser. Nothing you enter is uploaded or stored by Nexatoolbox.