# ctrlrun

> ctrlrun — ctrlrun-ctrlrun. Use this tool when you need to ensure safe execution of AI agents, preventing potential errors or security breaches. Ctrlrun provides a safety layer for AI agents, solving problems related to unreliable or untested code execution. It integrates with git, accepting code repositories as input and outputting verified and secure executable code.

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

## Description

The execution safety layer for AI agents.

## 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:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/CTRLRun/ctrlrun)

## 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": "ctrlrun-ctrlrun"
    }
  }
}
```

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