# Agents Md Generator

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-knuckles-team-universal-skills-agents-md-generator`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Knuckles-Team](https://agentstack.voostack.com/s/knuckles-team)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Knuckles-Team](https://github.com/Knuckles-Team)
- **Source:** https://github.com/Knuckles-Team/universal-skills/tree/main/universal_skills/agent-tools/agents-md-generator

## Install

```sh
agentstack add skill-knuckles-team-universal-skills-agents-md-generator
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AGENTS.md Generator

Generates a robust `AGENTS.md` file designed specifically for AI coding agents. This file acts as a "README for machines," providing them with the exact project context, rules, and instructions they need to work effectively.

## Features
- **Project Metadata Extraction**: Automatically parses `pyproject.toml` for project name, description, and scripts.
- **Dynamic File Tree**: Generates a text-based tree view of the project structure, ignoring common noise directories (`.git`, `__pycache__`, etc.).
- **Mermaid Diagrams**: Includes standardized Architecture and Workflow diagrams to help agents understand the system's design.
- **Battle-Tested Template**: Uses a structure optimized for high agent performance, including "Always/Ask first/Never" boundaries.

## Usage

Run the generator script with the path to your project root:

```bash
python scripts/generate_agents_md.py 
```

### Options
- ``: (Required) Path to the root directory of the project to document.

## AGENTS.md Standard

The generated `AGENTS.md` follows the emerging open standard for AI agent documentation:
1. **Tech Stack & Architecture**: High-level overview of technologies and component interactions.
2. **Commands**: Exact, file-scoped commands for building, testing, and linting.
3. **Project Structure**: Quick reference to key files and the dynamic tree view.
4. **Code Style & Conventions**: Specific "Always" rules with concrete Good/Bad code examples.
5. **Dos and Don'ts**: Specific behavioral guidelines.
6. **Safety & Boundaries**: Explicit "Always do", "Ask first", and "Never do" constraints.
7. **When Stuck**: Instructions on how to handle ambiguity (e.g., "propose a plan first").

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Knuckles-Team](https://github.com/Knuckles-Team)
- **Source:** [Knuckles-Team/universal-skills](https://github.com/Knuckles-Team/universal-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-knuckles-team-universal-skills-agents-md-generator
- Seller: https://agentstack.voostack.com/s/knuckles-team
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.