skills.rest
liutao96
liutao96COMMUNITY
Explore all skills by this author →
GitHub

coding-agent

Delegate coding tasks to Codex, Claude Code, OpenCode, or Pi agents in background processes.

Updated Feb 14, 2026
Search Tags:#coding#code-review#ai-agents#feature-development#background-execution
One-click install
npx skills add https://github.com/liutao96/skill --skill coding-agent-liutao96
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/liutao96/skill/tree/main/coding-agent
Command: npx skills add https://github.com/liutao96/skill --skill coding-agent-liutao96

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates coding workflows by delegating tasks to Codex, Claude Code, OpenCode, or Pi agents in a background process, freeing developers from manual instruction chasing.

Core Features & Use Cases

  • Background execution: spawn agents in a separate session to work on coding tasks without blocking your workflow.
  • Multi-agent orchestration: route tasks to Codex, Claude Code, OpenCode, or Pi based on task type and availability.
  • PR review & refactoring: run tasks in a temporary directory for safe code reviews and iterative improvements.

Quick Start

Start a session in your project directory, spawn a coding agent, and prompt it to implement the requested feature.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I automate feature development with AI agents in the background?▼

Run PR reviews by delegating coding agents to operate in a temporary directory, allowing safe code analysis and iterative improvements without modifying your primary project workspace.

Does Claude Code require interactive permissions for background coding tasks?▼

No, Claude Code uses --print --permission-mode bypassPermissions for non-interactive execution, allowing it to run autonomously in background coding workflows without prompting for permissions.

Do I need PTY to run Codex or OpenCode agents for code refactoring?▼

Yes, you need PTY for executing Codex, Pi, and OpenCode agents in background sessions, while Claude Code uses a separate non-interactive execution mode for iterative refactoring tasks.

What are the guardrails when delegating coding to background AI agents?▼

The workflow includes built-in guardrails to prevent unsafe actions during background execution, ensuring that agents performing feature development or refactoring operate within a controlled and safe process.

How do I orchestrate multiple AI agents for code review tasks?▼

You orchestrate multi-agent code reviews by routing tasks to Codex, Claude Code, OpenCode, or Pi based on task type and availability, executing the workflow through a defined agent framework.

Related Skills

Explore More Software Engineering Skills→
dakshrawat298-gifdakshrawat298-gif

coding-agent

Manage coding agents in terminal sessions across git worktrees.

Community
Advanced
praveenpererapraveenperera
4

review-fix-loop

Automate iterative GitHub pull request review cycles until no issues remain.

Community
Advanced
kk20300113-pngkk20300113-png

land-and-deploy

Merge pull requests and verify production health via canary checks.

Community
Advanced
cogpycogpy

coding-agent

Execute AI coding assistants like Codex and Claude Code in background processes.

Official
Advanced