coding-agent

Control AI coding agents via bash commands with PTY support.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/xxrenzhe/autobb --skill coding-agent-xxrenzhe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/xxrenzhe/autobb/tree/main/openclaw-prebuilt/skills/coding-agent
Command: npx skills add https://github.com/xxrenzhe/autobb --skill coding-agent-xxrenzhe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a unified interface to run various AI coding agents (Codex, Claude Code, OpenCode, Pi) for programmatic code generation, review, and modification, ensuring safe execution through PTY and sandboxing.

Core Features & Use Cases

  • Unified Agent Interface: Interact with multiple coding agents through a single bash-first interface.
  • Safe Execution: Enforces PTY mode for interactive agents and offers sandboxing or --yolo modes for different risk tolerances.
  • Background Processing: Run long-running tasks like code generation or refactoring in the background with session monitoring.
  • Use Case: Automatically generate boilerplate code for a new API endpoint, review a pull request, or refactor a module using your preferred AI coding assistant.

Quick Start

Use the coding-agent skill to run codex exec 'Add error handling to the API calls' in the ~/Projects/myproject directory with PTY enabled.

Frequently Asked Questions about coding-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code generation and review tasks using AI coding agents?

You can automate code generation and review by running AI coding agents like Codex or Claude Code via background processes. This Skill uses bash commands with PTY support to interactively control agents for code modification tasks.

Can I run multiple AI coding agents in the background and monitor their sessions?

Yes, you can run multiple AI coding agents in the background. This Skill supports session management, allowing you to list, poll, log, and kill background processes for tasks like code generation or refactoring.

Is it possible to execute code modifications with Claude Code or Codex programmatically?

Programmatic code modification with Claude Code or Codex is supported through a unified bash-first interface. It enforces safe execution using PTY mode for interactive CLIs and offers sandboxing or yolo modes for different risk tolerances.

How does PTY support affect the execution of interactive AI coding assistants?

PTY support ensures safe execution of interactive AI coding assistants by properly managing their interactive CLI environments. This allows background processes to run long tasks like code generation without breaking the interactive session.

What is the best way to safely execute automated code refactoring using an AI agent?

The best way to safely execute automated code refactoring is by using sandboxing features alongside PTY mode. This Skill provides a unified interface to control agents like OpenCode and Pi, ensuring safe execution for various risk tolerances.

How do I manage and terminate background processes for long-running code generation tasks?

You can manage and terminate background processes for code generation tasks using built-in session management features. This includes listing active sessions, polling their status, viewing logs, and killing processes when tasks complete.