AGENTS.md generator
Write the AGENTS.md, CLAUDE.md, .cursorrules or Copilot instructions file for your repository from its package.json or a short description.
Your key stays in your browser.It goes straight to the provider, never to our servers, and we neither log nor keep it. Use a dedicated key with a spending cap, and delete it in the provider's dashboard when you are done.
Input
Result
The result will appear here.Coding agents — Codex, Claude Code, Cursor, Copilot, Gemini CLI — read one file before they touch a repository, and the quality of that file decides whether they run your tests or invent their own, respect your lint rules or fight them. Writing it from scratch is tedious; most teams copy a template that says nothing specific. Paste your package.json, pyproject.toml, README or a description of the project and this generator writes the file for the target you pick, following the conventions documented at agents.md: the stack and layout, the exact install, test, lint and type-check commands read from your manifest, the conventions that matter, and the things agents get wrong unless told.
How it works
- A pasted manifest is read for scripts and dependencies, so the commands in the file are yours rather than the generic ones for the stack; anything not visible is marked (verify).
- Each target has its own shape: AGENTS.md as cross-tool Markdown, CLAUDE.md kept short because it is loaded into every session, .cursorrules in Cursor's traditional layout, copilot-instructions.md with the limits Copilot imposes.
- The output is the file content only, ready to save at the repository root — no preamble to strip.
Where your data goes
With your own key, what you type and the key go from your browser straight to the provider you choose; neither passes through Hysen Labs. In hosted mode, your text goes through our server to our provider (DeepSeek) and is billed in credits; we keep the token counts and cost of each run for billing, never the text itself or the answer. How the provider handles the text is governed by its own privacy policy.
This tool handles keys and credentials, so nothing about a run is saved, not even to your own history.
About your API key
We do not collect, store or leak your key: it lives only in this page's memory (unless you tick “remember in this tab”) and is gone when you close it. Still, treat any key you have pasted into a web page with care — create a dedicated key with a spending cap for use here, and delete or rotate it in your provider's dashboard when you are done.
What it costs
This tool is free, with no sign-in and no points.
Common questions
- Which file should I create if I use several agents?
- AGENTS.md: Codex, Cursor, Gemini CLI, Jules, Zed, Amp and others read it directly. Claude Code reads CLAUDE.md, so the common pattern is an AGENTS.md with the content and a one-line CLAUDE.md that says @AGENTS.md to include it. Copilot needs its own file under .github.
- How long should the file be?
- Shorter than you think — it is loaded into every conversation, so each line costs context on every turn. The generator aims for under about 150 lines, puts commands and hard rules first, and links to deeper docs rather than inlining them. If a section is generic advice the model already knows, cut it.
- Can I generate rules for a monorepo?
- Paste the root manifest plus a short directory tree and say which packages matter. Agents read the nearest AGENTS.md to the file they are editing, so for a monorepo you often want a short root file and one per package; run the tool once per package with that package's manifest.
The open-source behind it
This tool's prompt is adapted from agentsmd/agents.md (MIT) and runs on the model you choose. To use the same capability from the command line or inside your own program, start with that project.
agentsmd/agents.mdAlso known as
- agents.md generator
- claude.md generator
- cursorrules generator
- copilot-instructions.md
- ai coding agent rules file
- repository instructions for codex