# sandbox

> sandbox — cocoonstack-sandbox. Use this tool when you need to create isolated and secure environments for testing and training AI agents, solving problems related to dependency management and reproducibility. The sandbox tool takes in git repositories as input and outputs fast and lightweight MicroVMs, allowing for efficient cold-booting and minimal overhead. Ideal for use cases where isolation and speed are crucial, such as AI model development and deployment on the cocoon platform.

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

## Description

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

## Trust

- **Trust score (0–1):** 0.59
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/cocoonstack/sandbox)

## 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": "cocoonstack-sandbox"
    }
  }
}
```

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