# ratchet

> ratchet — suhui-organization-ratchet. Use this tool when you need to generate and verify least-privilege access policies for AI agents, ensuring secure and trustworthy interactions. It compiles policies based on actual reachability and provides verifiable evidence to recipients without requiring trust. Ideal for use cases involving secure data sharing, access control, and compliance, with integration capabilities via git.

Canonical page: https://skillsregistry.net/skills/suhui-organization-ratchet  
JSON: https://api.skillsregistry.net/v1/skills/suhui-organization-ratchet

## Description

Compile a least-privilege policy from what your AI agents can actually reach - then hand over evidence the recipient verifies without trusting you.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/suhui-organization/ratchet)

## 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": "suhui-organization-ratchet"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/suhui-organization-ratchet` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/suhui-organization-ratchet/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