skills.rest
SafeAI-Lab-X
SafeAI-Lab-XCOMMUNITY
Explore all skills by this author →
GitHub

coding-agent

Coordinate Codex, Claude Code, or Pi agents in background coding sessions.

1.0k|59|Updated Mar 20, 2026
Search Tags:#automation#codex#coding#terminal#openai#claude-code#ai-agents
One-click install
npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill coding-agent-safeai-lab-x
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/coding-agent
Command: npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill coding-agent-safeai-lab-x

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates complex coding workflows by delegating tasks to AI coding agents, enabling faster feature development and safer PR reviews through managed background sessions.

Core Features & Use Cases

  • Background coding sessions: run Codex, Claude Code, OpenCode, or Pi in the context of a defined project directory without disrupting your local workspace.
  • Multi-agent collaboration: coordinate across different AI providers for drafting, reviewing, and refactoring code.
  • Safe, controlled execution: sandboxed tasks with PTY-enabled CLIs and clear process management for progress monitoring.

Quick Start

Ask me to start a background coding session with Codex, Claude Code, or Pi to work on a feature in a dedicated project directory.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I automate coding tasks with Claude Code or Codex in the background?▼

Automating coding tasks with Claude Code or Codex involves delegating feature development or refactoring to AI agents through managed background sessions. This skill coordinates these CLIs in isolated project directories without disrupting your local workspace.

What is safe sandboxed execution for AI coding agents?▼

Safe sandboxed execution for AI coding agents isolates delegated tasks in controlled environments using PTY-enabled tools. It enforces clear process management and defined APIs, ensuring background sessions run securely without risking your local system.

Can I run multiple AI coding agents like Codex and Pi simultaneously for one project?▼

Running multiple AI coding agents simultaneously is supported through multi-agent collaboration. You can coordinate Codex, Claude Code, OpenCode, or Pi across different providers for drafting, reviewing, and refactoring code within your defined project directory.

Do I need PTY-enabled tools to run background coding sessions?▼

PTY-enabled tools are required to run background coding sessions. This skill depends on PTY-enabled CLIs to enforce safe sandboxed execution, manage background processes, and monitor progress for delegated coding tasks.

What's the best way to automate PR reviews using AI agents?▼

Automating PR reviews using AI agents is best handled by delegating the review task to a background coding session. This skill manages sandboxed execution with Codex or Claude Code, enabling safer PR reviews through isolated workspaces and clear process monitoring.

Related Skills

Explore More Software Engineering Skills→
jonnytacos8jonnytacos8

coding-agent

Orchestrate interactive coding agents in PTY-enabled background terminal sessions.

Community
Intermediate
CityBear3CityBear3

execute-plan

Execute approved implementation plans in isolated workspaces with verification gates.

Community
Advanced
greencmgreencm
1

land-and-deploy

Merge pull requests, run CI tests, and deploy to production with canary checks.

Community
Advanced
nshaikhsnshaikhs

hosted-agents

Coordinate remote sandboxed agents with per-session state isolation and GitHub authentication.

Community
Advanced