# sandy

> sandy — jamestelfer-sandy. Use this tool when you need to securely execute TypeScript code with access to AWS services, while keeping credentials safe and isolated from the underlying VM. It solves problems related to secure AWS querying and coding, providing a sandboxed environment for AI agents to run code with full SDK access. Ideal for use cases requiring isolated and secure AWS interactions, with support for git and available as a Claude Code plugin or standalone CLI.

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

## Description

Sandboxed TypeScript runtime for AI coding agents to query AWS — full SDK access with in-sandbox aggregation, credentials flow via IMDS and never enter the VM. Ships as a Claude Code plugin (MCP) and a standalone CLI, backed by Shuru microVMs or Docker.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/jamestelfer/sandy)

## 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": "jamestelfer-sandy"
    }
  }
}
```

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