coding-agent

Orchestrate PTY-enabled background sessions for AI coding agents.

9|2|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/hongmaple0820/agent-academy --skill coding-agent-hongmaple0820
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/hongmaple0820/agent-academy/tree/main/skills/development/coding-agent
Command: npx skills add https://github.com/hongmaple0820/agent-academy --skill coding-agent-hongmaple0820

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Coding Agent helps you delegate complex coding tasks to AI agents (Codex, Claude Code, Pi) running in a controlled PTY-enabled background session, enabling automated development workflows and rapid iteration without losing context.

Core Features & Use Cases

  • PTY-enabled interactive agents for coding tasks in a focused workspace
  • Background session orchestration with start/list/log/kill controls
  • Safe, context-aware execution for feature development, code review, and refactoring
  • Multi-agent collaboration across repositories and languages

Quick Start

Ask your AI agent to start a PTY-enabled coding session in your project directory and run Codex or Claude Code to implement the feature.

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 background sessions for automated development?

To run AI coding agents in background sessions, use a PTY-enabled bash interface to orchestrate interactive agents with start, list, log, and kill controls for automated iterative development.

What is PTY-enabled session management for AI coding tasks?

PTY-enabled session management orchestrates AI coding agents in pseudo-terminal interfaces, allowing safe background execution of feature development, code reviews, and refactors across large codebases.

Can I coordinate multiple AI agent backends across different repositories?

Yes, you can coordinate multiple AI agent backends like Codex and Claude Code across repositories, orchestrating multi-agent collaboration for exploratory work and complex refactoring tasks.

Does this coding agent approach work for large codebase refactoring?

Yes, this coding agent approach works for large codebase refactoring by delegating complex coding tasks to AI agents in controlled PTY-enabled background sessions, enabling rapid iteration across diverse languages.

How do I start a PTY-enabled coding session in my project directory?

To start a PTY-enabled coding session, ask your AI agent to initialize the session in your project directory and run Codex or Claude Code to implement the desired feature with background session controls.

What are the limitations of using PTY terminals for AI code review?

PTY terminals for AI code review require careful session orchestration to avoid context loss, and you must manually poll logs and submit or kill sessions to manage iterative development workflows safely.