# lockkeeper

> lockkeeper — hannay001-lockkeeper. Use this tool when you need to optimize AI coding agent performance and security by routing skills and injecting prompts. It solves the problem of excessive skill and server exposure by limiting access to only the necessary tools and servers for each task. The lockkeeper tool takes in task-specific requirements and outputs a tailored set of skills, MCP servers, and tools, such as git, to ensure efficient and secure coding operations.

Canonical page: https://skillsregistry.net/skills/hannay001-lockkeeper  
JSON: https://api.skillsregistry.net/v1/skills/hannay001-lockkeeper

## Description

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools each task needs.

## 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/Hannay001/lockkeeper)

## 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": "hannay001-lockkeeper"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hannay001-lockkeeper` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hannay001-lockkeeper/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