coding-agent

Execute AI coding agents in background processes with workdir and git worktrees.

Updated Jan 26, 2026
One-click install
npx skills add https://github.com/caiazzop/clawdbot-personal-assistant --skill coding-agent-caiazzop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/caiazzop/clawdbot-personal-assistant/tree/main/skills/coding-agent
Command: npx skills add https://github.com/caiazzop/clawdbot-personal-assistant --skill coding-agent-caiazzop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables programmatic control over various AI coding agents, allowing for background execution of coding tasks without direct user interaction.

Core Features & Use Cases

  • Background Execution: Run coding agents like Codex, Claude Code, OpenCode, and Pi Coding Agent in the background for non-interactive tasks.
  • Focused Workspaces: Utilize workdir to confine agents to specific project directories, enhancing security and relevance.
  • Parallel Processing: Efficiently handle multiple coding tasks, such as batch PR reviews or issue fixing, using techniques like git worktrees and tmux.

Quick Start

Use the coding-agent skill to build a snake game with a dark theme in the background within your project folder.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I run AI coding agents in the background for non-interactive tasks?

You can run AI coding agents in the background by executing tools like Codex, Claude Code, OpenCode, and Pi Coding Agent via background processes for programmatic control without direct user interaction. This enables automated code generation and debugging.

How can I execute parallel coding tasks across multiple project directories?

You can execute parallel coding tasks efficiently by utilizing techniques like git worktrees and tmux. This approach allows you to handle multiple batch processes, such as PR reviews or issue fixing, simultaneously across isolated project workspaces.

How do I confine an AI coding agent to a specific project directory?

You can confine an AI coding agent to a specific project directory by utilizing the workdir parameter. This focused workspace approach enhances security and ensures the agent only operates within the relevant codebase boundaries.

What AI coding agents are supported for programmatic execution?

Supported AI coding agents for programmatic execution include Codex, Claude Code, OpenCode, and Pi Coding Agent. These agents can be launched via background processes to handle automated development and debugging tasks.

Can I use this to automate batch code reviews and issue fixing?

Yes, you can automate batch code reviews and issue fixing by running multiple AI coding agents in parallel. Using git worktrees and tmux allows efficient handling of these simultaneous coding tasks without requiring direct user interaction.