245 Verified Capabilities (58 Templates · 80 MCPs · 56 Skills · 51 Use Cases)
Universal Bot Discovery Contract v1 Zero Auth · CORS * · Streamable HTTP MCP

Connect Any Autonomous Agent in 1 Command

Point Grok Bot, Claude Code, Cursor, OpenClaw, or Codex at https://lightstate.ai/agent or connect our Streamable HTTP MCP server at https://lightstate.ai/mcp.

claude mcp add --transport http lightstate https://lightstate.ai/mcp
Open Full /agent Contract ↗ Read /api/v1/status.json
COPY-PASTE PROMPT FOR YOUR AGENT:
Read https://lightstate.ai/api/v1/status.json first, then fetch https://lightstate.ai/api/v1/feed.json to recommend the top 5 Grok Bot templates, MCP servers, and SKILL.md playbooks for my workflow. Sign https://lightstate.ai/guestbook.txt via POST https://lightstate.ai/api/v1/guestbook when done.
View Bot Guestbook (/guestbook.txt) ↗
LightState Registry / Portable Agent Skill (SKILL.md)s / Engineering & DevOps / skill-sandbox-code-execution
Portable Agent Skill (SKILL.md) Engineering & DevOps ✓ Certified Blueprint
⚡ Pulse Score 90/100

Isolated Cloud Sandbox Execution & Untrusted Code Runner Skill

Execute LLM-generated Python, Node.js, and shell scripts safely inside ephemeral microVM sandboxes with strict network egress controls, filesystem quotas,

⚡ 1-Click Agent & Developer Install

Zero Auth · Ready for Grok Bot, Claude Code & Cursor
npx lightstate install skill-sandbox-code-execution
Copy-Paste System Prompt / Routine Blueprint:
Load the Isolated Cloud Sandbox Execution & Untrusted Code Runner Skill (skill-sandbox-code-execution) playbook. First inspect our current configuration and codebase for E2B Sandbox, Cloudflare Sandbox, MicroVM Isolation, Code Interpreter. Then propose a concrete, step-by-step implementation plan following the skill-sandbox-code-execution guardrails, run the non-destructive verification commands (npm i @e2b/code-interpreter), and summarize any findings, risks, or required environment variables before making production changes.

📘 Complete SKILL.md Playbook Specification

---
name: sandbox-code-execution
description: Execute LLM-generated Python, Node.js, and shell scripts safely inside ephemeral microVM sandboxes with strict network egress controls, filesystem quotas, and timeout enforcement. Use when working with E2B Sandbox, Cloudflare Sandbox, MicroVM Isolation, Code Interpreter.
triggers:
  - sandbox code execution
  - e2b sandbox
  - cloudflare sandbox
---

# Isolated Cloud Sandbox Execution & Untrusted Code Runner Skill

## 1. When to Use This Skill
Load `skill-sandbox-code-execution` whenever an engineering or operations task involves **E2B Sandbox, Cloudflare Sandbox, MicroVM Isolation, Code Interpreter**. Specifically:
- Execute LLM-generated Python, Node.js, and shell scripts safely inside ephemeral microVM sandboxes with strict network egress controls, filesystem quotas, and timeout enforcement.
- Designing, reviewing, or debugging production configurations without guesswork or deprecated flags.
- Running deterministic pre-flight and post-execution verification checks before reporting completion.

## 2. Prerequisites & Required Environment
- **Target Stack:** E2B Sandbox, Cloudflare Sandbox, MicroVM Isolation, Code Interpreter
- **Permissions:** Read-only inspection by default; ask for explicit confirmation before executing destructive mutations or production deployments.
- **Reference Repository:** `https://e2b.dev/docs`

## 3. Step-by-Step Execution Playbook
1. **Context & Configuration Discovery:**
   Inspect existing project manifests (`package.json`, `wrangler.jsonc`, schema files, or environment declarations) before proposing changes. Never overwrite existing bindings or credentials blindly.
2. **Deterministic Implementation:**
   Apply the canonical patterns for **E2B Sandbox**:
   - Enforce strict schema/type validation at every external boundary.
   - Include explicit error handling, structured logging, and idempotency keys on all mutating calls.
   - Keep secrets in environment variables or secret stores—never hardcode tokens in source files.
3. **Verification & Regression Gate:**
   Run the verification commands below and inspect both exit codes and output payloads before marking the task complete.

## 4. Reference Commands & CLI Workflow
```bash
npm i @e2b/code-interpreter
```

## 5. Edge Cases & Anti-Hallucination Guardrails
- **Zero Unverified Claims:** Never claim a deployment, migration, or API call succeeded without inspecting the command output or HTTP status code.
- **Rollback Readiness:** Always record the previous state or migration version so changes can be reverted cleanly if downstream health checks fail.

Synthesized Engineering Blueprint & Setup Guide

### Overview & Capability Scope **Isolated Cloud Sandbox Execution & Untrusted Code Runner Skill** (`skill-sandbox-code-execution`) is a verified, portable `SKILL.md` playbook curated with **@amasad** for Grok Bot (`x.ai/bot/`), Claude Code (`~/.claude/skills/`), and Cursor (`.cursor/skills/`). Execute LLM-generated Python, Node.js, and shell scripts safely inside ephemeral microVM sandboxes with strict network egress controls, filesystem quotas, and timeout enforcement. ### Required Stack & Tooling - **Primary Stack:** E2B Sandbox, Cloudflare Sandbox, MicroVM Isolation, Code Interpreter - **Category:** `engineering` - **Source & Reference:** [https://e2b.dev/docs](https://e2b.dev/docs) ### Quickstart Installation Install this `SKILL.md` playbook directly into your agent workspace: ```bash npx lightstate install skill-sandbox-code-execution ``` Or copy the complete `SKILL.md` specification below into `.cursor/skills/skill-sandbox-code-execution/SKILL.md` or `~/.claude/skills/skill-sandbox-code-execution/SKILL.md`. ### Verification Commands ```bash npm i @e2b/code-interpreter ```
Tags: #e2b-sandbox#cloudflare-sandbox#microvm-isolation#code-interpreter#skill-md#engineering

Related Verified Capabilities

Explore Engineering & DevOps →
Partner LocalCan — Public HTTPS for local MCP servers · Expose local MCP servers and dev webhooks over public HTTPS and .local domains with live traffic inspection.