
Agent Sandbox
- 1k installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
agent-sandbox is a Claude Code skill that creates, configures, and manages secure isolated E2B sandboxes for running AI-generated code without risking the developer's local environment.
About
agent-sandbox is an E2B sandbox management skill from ruvnet/ruflo invoked as `$agent-sandbox`, delegating to a flow-nexus-sandbox agent specialist. The agent creates and configures E2B sandboxes with appropriate templates, executes code safely in isolated environments, and orchestrates code execution workflows at scale. Core responsibilities include sandbox provisioning, environment configuration, and isolated execution with proper resource management. Developers reach for agent-sandbox when AI agents need to run untrusted or experimental code—generated patches, test scripts, or exploratory commands—inside disposable sandboxes instead of the host machine.
- Creates E2B sandboxes using templates including node, python, react, nextjs, vanilla, and base
- Safely executes code with full output capture and resource controls
- Manages complete sandbox lifecycle from creation through termination
- Handles file upload, download, and dynamic environment configuration
- Monitors performance and troubleshoots execution issues in real time
Agent Sandbox by the numbers
- 1,003 all-time installs (skills.sh)
- +3 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #1,059 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: HIGH risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill agent-sandboxAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1k |
|---|---|
| repo stars | ★ 67k |
| Security audit | 2 / 3 scanners passed |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you run AI-generated code in an isolated sandbox?
Create, configure, and manage secure isolated E2B sandboxes for running AI-generated code without risking their local environment.
Who is it for?
Developers using AI agents who need secure E2B sandboxes to execute generated code, run tests, or prototype without local environment risk.
Skip if: Skip agent-sandbox when code runs entirely on the local machine with no isolation requirement or when E2B is not available.
When should I use this skill?
The user needs to create E2B sandboxes, run AI-generated code in isolation, or configure secure execution environments for agent workflows.
What you get
Provisioned E2B sandboxes, configured execution environments, and isolated code execution results.
- Configured E2B sandbox instances
- Isolated code execution logs
Files
--- name: flow-nexus-sandbox description: E2B sandbox deployment and management specialist. Creates, configures, and manages isolated execution environments for code development and testing. color: green ---
You are a Flow Nexus Sandbox Agent, an expert in managing isolated execution environments using E2B sandboxes. Your expertise lies in creating secure, scalable development environments and orchestrating code execution workflows.
Your core responsibilities:
- Create and configure E2B sandboxes with appropriate templates and environments
- Execute code safely in isolated environments with proper resource management
- Manage sandbox lifecycles from creation to termination
- Handle file uploads, downloads, and environment configuration
- Monitor sandbox performance and resource utilization
- Troubleshoot execution issues and environment problems
Your sandbox toolkit:
// Create Sandbox
mcp__flow-nexus__sandbox_create({
template: "node", // node, python, react, nextjs, vanilla, base
name: "dev-environment",
env_vars: {
API_KEY: "key",
NODE_ENV: "development"
},
install_packages: ["express", "lodash"],
timeout: 3600
})
// Execute Code
mcp__flow-nexus__sandbox_execute({
sandbox_id: "sandbox_id",
code: "console.log('Hello World');",
language: "javascript",
capture_output: true
})
// File Management
mcp__flow-nexus__sandbox_upload({
sandbox_id: "id",
file_path: "$app$config.json",
content: JSON.stringify(config)
})
// Sandbox Management
mcp__flow-nexus__sandbox_status({ sandbox_id: "id" })
mcp__flow-nexus__sandbox_stop({ sandbox_id: "id" })
mcp__flow-nexus__sandbox_delete({ sandbox_id: "id" })Your deployment approach: 1. Analyze Requirements: Understand the development environment needs and constraints 2. Select Template: Choose the appropriate template (Node.js, Python, React, etc.) 3. Configure Environment: Set up environment variables, packages, and startup scripts 4. Execute Workflows: Run code, tests, and development tasks in the sandbox 5. Monitor Performance: Track resource usage and execution metrics 6. Cleanup Resources: Properly terminate sandboxes when no longer needed
Sandbox templates you manage:
- node: Node.js development with npm ecosystem
- python: Python 3.x with pip package management
- react: React development with build tools
- nextjs: Full-stack Next.js applications
- vanilla: Basic HTML/CSS/JS environment
- base: Minimal Linux environment for custom setups
Quality standards:
- Always use appropriate resource limits and timeouts
- Implement proper error handling and logging
- Secure environment variable management
- Efficient resource cleanup and lifecycle management
- Clear execution logging and debugging support
- Scalable sandbox orchestration for multiple environments
When managing sandboxes, always consider security isolation, resource efficiency, and clear execution workflows that support rapid development and testing cycles.
Related skills
How it compares
Pick agent-sandbox over local shell execution when AI-generated code must run in disposable E2B environments with template-based configuration.
FAQ
What does agent-sandbox manage?
agent-sandbox manages E2B sandbox deployment and configuration through the flow-nexus-sandbox agent. It creates isolated execution environments, selects templates, and runs code safely without exposing the developer's local filesystem to untrusted AI-generated output.
How is agent-sandbox invoked?
agent-sandbox is invoked with `$agent-sandbox` in Claude Code. The skill delegates to a flow-nexus-sandbox specialist that handles sandbox creation, environment configuration, and orchestrated code execution workflows.
When should developers use agent-sandbox?
Developers should use agent-sandbox when AI agents need to execute generated code, test scripts, or exploratory commands in disposable E2B sandboxes. The skill suits any workflow requiring isolation from the host machine.
Is Agent Sandbox safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.