Skip to content
Agentmart
Submit a tool

claude-code-runner

Execute programming tasks via Claude Code using PTY-based invocation.

Skill by aAAaqwq

IndexedMIT★ 111
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/aaaaqwq-claude-code-runner

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Execute programming tasks via Claude Code using PTY-based invocation. Handles non-TTY environments, auto-responds to prompts, and manages file synchronization.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/claude-code-runner

What's inside

Skill name
claude-code-runner
Description
Execute programming tasks via Claude Code using PTY-based invocation. Handles non-TTY environments, auto-responds to prompts, and manages file synchronization.
License
MIT
Instructions
219 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (6)

  • origin.json · .clawdhub/
  • README.md
  • SKILL.md
  • _meta.json
  • clawhub.json
  • run_claude.py · scripts/

SKILL.md (first lines)

# Claude Code Runner

## Overview

A wrapper skill for running Claude Code programmatically in non-interactive environments. Uses PTY (pseudo-terminal) to handle TTY-required operations and automatically responds to confirmation prompts.

## Features

- **PTY-based execution**: Works in non-TTY environments (containers, CI/CD, background processes)
- **Auto-respond to prompts**: Automatically answers "Do you want to..." confirmations
- **User switching**: Runs as specified non-root user
- **File synchronization**: Copies project to temp directory, executes, syncs changes back
- **Timeout handling**: Configurable timeout with proper cleanup
- **Output capture**: Captures and returns full stdout/stderr

## Installation

```bash
# Clone the skill
git clone https://github.com/lhl09120/claude-code-runner-en.git

# Make script executable
chmod +x claude-code-runner-en/scripts/run_claude.py
```

## Usage

### Basic Usage

```python
from claude_code_runner import run_claude_code

result = run_claude_code(
    workdir='/path/to/project',
    prompt='Refactor the authentication module to use JWT tokens',
    user='lighthouse',
    timeout=300
)

print(result)
```

### Via Command Line

```bash
python3 scripts/run_claude.py /path/to/project "Your task description here"
```

### Advanced Options

```python
result = run_claude_code(
    workdir='/root/repo/my-project',
    prompt='''
    1. Review the codebase
    2. Identify security vulnerabilities
    3. Fix any issues found
    4. Add appropriate tests
    ''',
    user='developer',
    timeout=600  # 10 minutes
)
```

## API Reference

### `run_claude_code(workdir, prompt, user='lighthouse', timeout=300)`

Execute a Claude Code task in a PTY environment.

**Parameters:**
- `workdir` (str): Working directory containing the project
- `prompt` (str): Natural language task description
- `user` (str): User to run as (default: 'lighthouse')
- `timeout` (int): Timeout in seconds (default: 300)

**Returns:**
- `str`: Combined stdout and stderr output

**Behavior:**
1. Copies project to temporary directory
2. Changes ownership to specified user
3. Executes Claude Code via PTY
4. Auto-responds to confirmation prompts
5. Syncs changes back to original directory
6. Cleans up temporary files

## Use Cases

### 1. Automated Code Review

```python
result = run_claude_code(
    workdir='/root/repo/project',
    prompt='Review this codebase and identify potential bugs or improvements'
)
```

### 2. Refactoring Tasks

```python
result = run_claude_code(
    workdir='/root/repo/legacy-app',
    prompt='Refactor the database layer to use SQLAlchemy ORM instead of raw SQL'
)
```

### 3. Adding Features

```python
result = run_claude_code(
    workdir='/root/repo/api-service',
    prompt='''
    Add a new REST endpoint for user profile management:
    - GET /api/users/{id}/profile
    - PUT /api/users/{id}/profile
    - Include validation and error handling
    - Add unit tests
    '''

From aAAaqwq/AGI-Super-Team, MIT.

More from aAAaqwq/AGI-Super-Team

Signals

Stars
111
Forks
25
Open issues
1
Last commit (this folder)
Apr 15, 2026 (6 months ago)
Last release
Sep 20, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from aAAaqwq

Cite this page

claude-code-runner skill. Agent Mart. https://agentmart.dev/skills/aaaaqwq-claude-code-runner (last updated 2026-10-24)