# Astrolabe

> Astrolabe — chrisroyse-astrolabe. Use this tool when you need to verify and validate the integrity of AI-generated code, ensuring that every claim has provenance and the code is measured, grounded, and guarded. The Astrolabe tool takes a repository as input and outputs self-improving intelligence with predictive capabilities. It is particularly useful in contexts where code reliability and trustworthiness are crucial, such as in high-stakes AI development projects.

Canonical page: https://skillsregistry.net/skills/chrisroyse-astrolabe  
JSON: https://api.skillsregistry.net/v1/skills/chrisroyse-astrolabe

## Description

The full-state-verification layer for AI coding agents: one native MCP server (Rust host, C engine) that turns a repository into measured, grounded, guarded, predictive, self-improving intelligence with provenance for every claim.

## 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:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/ChrisRoyse/Astrolabe)

## 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": "chrisroyse-astrolabe"
    }
  }
}
```

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