skills.rest
Jnuso
JnusoCOMMUNITY
Explore all skills by this author →
GitHub

coding-agent

Delegate coding tasks to AI agents in background sessions.

Updated Apr 8, 2026
Search Tags:#coding#background#ai-agents#pr-review#code-refactor#workspace-safety
One-click install
npx skills add https://github.com/Jnuso/OpenClaw --skill coding-agent-jnuso
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/Jnuso/OpenClaw/tree/main/skills/coding-agent
Command: npx skills add https://github.com/Jnuso/OpenClaw --skill coding-agent-jnuso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delegates coding tasks to AI agents (Codex, Claude Code, Pi, or OpenCode) and runs them in background sessions to accelerate feature development, code reviews, and refactors without blocking your workstation.

Core Features & Use Cases

  • Background multi-agent coding: spawn Codex, Claude Code, Pi, or OpenCode in isolated sessions to work on features, PR reviews (in a temp dir), and large refactors.
  • Safe, bounded execution: enforces workspace boundaries, PTY rules, and avoids OpenClaw state and live project folders.
  • Interactive workflow tooling: supports long-running tasks with process controls (list, log, poll, write, submit, kill) for monitoring and control.

Quick Start

Launch a background coding session in a temp project and tell the agent to implement the requested feature using Codex or Claude Code as appropriate.

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 large refactors?▼

You can delegate large refactors to background AI coding agents by spawning sessions with Codex, Claude Code, Pi, or OpenCode. This isolates long-running tasks to accelerate codebase refactoring without blocking your workstation.

Can I review pull requests in a temporary directory using AI agents?▼

Yes, you can review PRs in a temporary directory by spawning an AI agent like Claude Code or Codex in a background session. This safely isolates the review process from your live project folders.

What safety boundaries apply when delegating tasks to background coding agents?▼

Background coding agents enforce safety boundaries by preventing execution within the OpenClaw state directory and live project folders. They also enforce specific PTY rules for Codex, Pi, and OpenCode to maintain workspace safety.

How do I monitor long-running background sessions for iterative coding?▼

You can monitor long-running background coding sessions using interactive workflow tooling. Process controls let you list active agents, poll logs, write input, submit tasks, and kill sessions to manage iterative coding.

Do I need to install CLI tools to use background AI agents for feature development?▼

Yes, you must install the required CLI tools for Codex, Claude Code, Pi, or OpenCode to delegate feature development. The skill provides install instructions and enforces specific PTY usage for these tools.

What is the best way to build new features with AI agents without blocking my terminal?▼

The best way to build features without terminal blockage is delegating tasks to isolated background AI agents. This spawns Codex or Claude Code in separate sessions to implement features while you continue working.

Related Skills

Explore More Software Engineering Skills→
AnandaAnugrahHandyantoAnandaAnugrahHandyanto

blackbox

Delegate coding tasks to the Blackbox AI CLI agent.

Community
Advanced
blakesimsblakesims

review-merge

Validate feature branch merge readiness with integration checks and summaries.

Community
Advanced
VanLVanL
1

landing-report

Display live version claims, open PRs, and deployment priorities from repository data.

Community
Basic
NeKon69NeKon69
1

windsurf.nvim

Integrate Codeium AI code completion, generation, and chat into Neovim.

Community
Basic