# homelab-guardian

> homelab-guardian — spezzuti-homelab-guardian. Use this tool when you need to protect your homelab from unintended AI actions, ensuring verified health checks and secure, approval-gated repairs without shell access. It solves problems of AI safety and security by providing a safeguard layer between AI agents and root access. The homelab-guardian tool accepts homelab health data as input and outputs audited, allowlisted repair actions via MCP.

Canonical page: https://skillsregistry.net/skills/spezzuti-homelab-guardian  
JSON: https://api.skillsregistry.net/v1/skills/spezzuti-homelab-guardian

## Description

The safety layer between an AI agent and root. Verified homelab health over MCP, plus approval-gated, allowlisted, audited repairs - never a shell.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/spezzuti/homelab-guardian)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "spezzuti-homelab-guardian"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/spezzuti-homelab-guardian` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/spezzuti-homelab-guardian/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt