claude-code-runner
Execute programming tasks via Claude Code using PTY-based invocation. Handles non-TTY environments, auto-responds to prompts, and manages file synchronization.
Why use this skill?
Integrate Claude Code into your CI/CD pipelines and background tasks with the claude-code-runner skill. Automate refactoring, security audits, and more.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/lhl09120/claude-code-runnerWhat This Skill Does
The claude-code-runner skill is a powerful automation bridge designed for developers who need to integrate Claude Code into non-interactive environments like CI/CD pipelines, Docker containers, or automated background services. At its core, it leverages PTY (pseudo-terminal) technology to trick tools that demand a real terminal into thinking they are running in an interactive session. This allows for seamless programmatic execution of complex coding tasks without manual intervention.
Beyond just running commands, the skill manages the entire lifecycle of a coding task. It copies your source project into an isolated temporary workspace, executes the specified Claude Code operations while auto-responding to security and confirmation prompts, and carefully synchronizes all file changes back to your original repository. This wrapper ensures that your automated tasks have the same capability as a human developer sitting in front of a terminal, but with the scalability of an AI agent.
Installation
To install this skill, use the ClawHub CLI tool integrated within your OpenClaw environment:
clawhub install openclaw/skills/skills/lhl09120/claude-code-runner
Once installed, ensure that your environment has the necessary permissions to execute scripts as a non-root user, as the skill is designed to transition ownership for security purposes. You can verify the installation by checking your script path and ensuring the run_claude.py file has the required execution bits set via chmod +x.
Use Cases
- Continuous Integration Hardening: Automatically run security linting and code refactoring as part of your PR process.
- Legacy Code Migration: Automate the tedious process of updating database drivers or library versions across multiple microservices.
- Auto-Documentation: Trigger documentation generation tasks whenever a significant codebase update is pushed to a remote branch.
- Background Feature Prototyping: Allow the agent to draft new endpoint logic or boilerplate code while the developer works on higher-level architectural decisions.
Example Prompts
- "Use claude-code-runner to refactor the authentication module in /app/auth to use JWT tokens instead of session cookies."
- "Perform a security audit on the /api-service directory and fix any identified vulnerabilities found in the dependency tree."
- "Add a comprehensive unit test suite for the payment-processor folder using the latest framework standards."
Tips & Limitations
- Resource Management: Always define a realistic timeout value. Because the skill runs in a PTY, complex tasks may take longer than expected; set your timeout based on the scale of the codebase.
- Security: The skill performs file writes as the specified user. Ensure that the 'user' parameter provided to the skill has the appropriate least-privilege permissions required to perform the requested edits.
- Environment: If running in a restricted container, ensure that the container has the necessary tools like git and python installed, as these are prerequisites for the execution engine.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-lhl09120-claude-code-runner": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution