- Home
- AI support
- AGENTS.md Generator
AGENTS.md Generator for AI Coding Agents
Choose how you work, fill what you already know, download the files. Put them at the repo root. The coding agent asks once about anything still empty, writes the answer into docs/, and does not ask again.
What it is for?Project
AI tools you use
Cursor, Codex, Windsurf, Zed and most others read AGENTS.md directly. The extra files only point to it.
Technology
Ask later leaves that row empty. The agent asks it once, writes the answer, and does not ask again. None means do not add that layer.
Commands
Empty commands are guessed from the framework and marked as not verified.
Rules
Files are English. Drop them at the repository root. Token counts are rough (about 4 characters per token); agents read these files on every chat, so shorter is cheaper.
What it is for?
This is not an application. It is a starter pack for a coding agent (Cursor, Codex, Claude, Copilot): AGENTS.md at the root, and a docs/ folder the agent is told to keep up to date. If you would not write those files yourself, this still gives you a usable base.
What you get
- AGENTS.md: standing rules (smallest change, no extra caution that hurts speed, related tests only, docs/ in English) plus how the agent should talk to you.
- docs/project.md and docs/stack.md: language, database, cache, Docker, queue, Graphify. Empty rows are asked once, then written, then not asked again.
- docs/TODO.md: checkboxes for later work, plain bullets for notes ("remember this").
- docs/testing.md, docs/adr/ with one example decision record (ADR) and a template. If Graphify is on, docs/graphify.md as well.
- Safety rules for secrets, the database, security and verification, plus the git rule you picked. With IDs on, the agent starts a warning with the rule, for example [DB-001].
- Optional CLAUDE.md, GEMINI.md and .github/copilot-instructions.md that point to AGENTS.md, so every tool reads the same rules.
Do not want a docs folder? Pick Only AGENTS.md: the stack, commands, todos and notes go into that one file.
How the agent is supposed to use it
First chat: if a fact is still empty, one message of questions, then the agent updates the markdown. Later chats read the files. "We are adding Redis now" updates stack.md and an ADR; it does not restart the questionnaire. Using Docker is not the same as creating Compose files; scaffolding needs a separate yes.
It stays in the browser
Nothing is uploaded. The zip is built in this tab. Put the files in git so every agent session sees the same base.