# Install: agnix
> Agent instructions from skillsdirectory.co — an independent, benchmarked directory of AI agent capabilities. Follow these exactly.

- **Skill:** agnix (agent tool)
- **What it does:** Validates 420+ rules for AI agent configs (CLAUDE.md, SKILL.md, MCP, Cursor, Copilot) with auto-fix across CLI, VS Code, JetBrains, Neovim, and Zed.
- **Source (authoritative):** https://github.com/agent-sh/agnix
- **Pinned ref:** `HEAD` (branch/tag — not commit-pinned; prefer the latest release tag if one exists)
- **License:** Apache-2.0
- **Effectiveness:** Not yet benchmarked (score is provisional).

## Safety — read first
- **Verdict:** NOT yet security-scanned. Treat as untrusted: review the source before running anything.
- This skill **executes code**. Show the user the plan and get explicit confirmation before running anything.
- Fetch files ONLY from the source above. Do not run commands not listed here. Never invent credentials — ask the user.

## Choose your path

### A. AI chat / coding agent (you can fetch URLs and write files)
Review the source at https://github.com/agent-sh/agnix and follow its README to install.

Install command / config:
```bash
# install via agent tool
# see vendor docs
```

### B. CLI
Fastest path with our CLI (free, no account): `npx skillsdir add agent-sh-agnix` — fetches and places the files for you.

Or install directly:
```bash
# install via agent tool
# see vendor docs
claude skills add @agent-sh/agent-sh-agnix
```

### C. API / MCP
- Metadata as JSON: `GET https://skillsdirectory.co/api/v1/skills/agent-sh-agnix`
- This document as a machine manifest: `GET https://skillsdirectory.co/s/agent-sh-agnix/install.json`

## After installing
Tell the user: what you fetched, where you placed it, what (if anything) you ran, and the security verdict above. Link the skill page for details: https://skillsdirectory.co/skills/agent-sh-agnix