Home Tutorials Categories Skills About
ZH EN JA KO
💻

Code Runner

Development Developer Tools

Install Command

npx clawhub@latest install coderunner

Installation Guide

1
Check Environment

Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.

2
Run Installation

Run the install command above in your terminal. ClawHub will automatically download and install Code Runner to the ~/.openclaw/skills/ directory.

3
Verify Installation

Run openclaw skills list to check your installed skills and confirm Code Runner appears in the list.

4
Configure (Optional)

Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.

Manual Installation: Copy the Skill folder to ~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Multi-Language Sandbox Execution Data Analysis

Detailed Description

Code Runner gives OpenClaw the ability to execute code, allowing the AI to not only write code but actually run it and return results.

Core Features

  • Multi-Language Support: Python, JavaScript/TypeScript, Go, Rust, Ruby, Shell, and more
  • Secure Sandbox: Code runs in an isolated environment without affecting the host system
  • Package Management: The Python environment comes with commonly used packages pre-installed (numpy, pandas, requests, etc.), with on-demand installation available
  • File I/O: Supports reading and writing files within the sandbox for data processing
  • Timeout Protection: Automatically terminates code that runs too long

Configuration

{
  skills: {
    coderunner: {
      timeout: 30,           // Execution timeout (seconds)
      languages: ["python", "javascript", "shell"],
      sandboxType: "docker", // docker or process
      maxMemory: "512m"
    }
  }
}

Use Cases

  • Data analysis: Have the AI write a Python script to process CSV data and generate statistics
  • Quick validation: Verify whether an algorithm idea is correct
  • Automation scripts: Have the AI write and execute system management scripts
  • Math computation: Handle complex mathematical calculations

Notes

The sandbox environment has resource limits and is not suitable for running large applications or long-duration tasks. Docker sandbox mode is recommended for the best isolation.

← Back to Skills List