coding-agent

Run interactive coding agents with PTY allocation and background session control.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/RobbyMo81/assistantrobby --skill coding-agent-robbymo81
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/RobbyMo81/assistantrobby/tree/main/skills/coding-agent
Command: npx skills add https://github.com/RobbyMo81/assistantrobby --skill coding-agent-robbymo81

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a reliable way to run and manage interactive coding agents (Codex, Claude Code, OpenCode, Pi) from the shell while ensuring correct pseudo-terminal allocation, workspace isolation, and background session control so agents do not hang or read unrelated files.

Core Features & Use Cases

  • PTY-required execution: Ensures interactive CLIs receive a pseudo-terminal to avoid broken output, missing colors, or hangs.
  • Background sessions & monitoring: Start agents in background, receive session IDs, stream logs, poll status, send input, paste text, and terminate sessions as needed.
  • Tool-specific guidance and safety: Covers Codex git-repo requirements and flags, Claude Code/OpenCode/Pi usage, safe PR review patterns with temporary clones or worktrees, and auto-notify on completion for long tasks.
  • Use Case: Launch parallel Codex reviewers across many PRs in isolated worktrees, monitor each session, and post aggregated results to GitHub.

Quick Start

Start an interactive coding agent in your project directory as a background PTY session and monitor progress with process action:log.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
Why do my interactive coding agents hang or lose color output when run in the background?

Interactive coding agents hang because they lack proper PTY allocation. This Skill ensures correct pseudo-terminal assignment for background sessions, preventing broken output, missing colors, and unexpected hangs.

How do I run Claude Code or Codex as a background session and monitor the logs?

You can start coding agents as background PTY sessions and receive unique session IDs. Use process action:log to stream output, poll status, send input, and terminate sessions as needed.

Can I launch parallel Codex reviewers across multiple PRs with workspace isolation?

Yes, you can launch parallel Codex reviewers across many PRs using isolated worktrees or temporary clones. This prevents agents from reading unrelated files and ensures safe PR review patterns.

Does this coding agent runner support OpenCode and Pi alongside Codex and Claude Code?

Yes, the runner supports tool choice among Codex, Claude Code, OpenCode, and Pi. It provides tool-specific guidance including Codex git-repo requirements and safe usage patterns.

What is the best way to manage long-running code generation workflows without blocking the shell?

Run long-running code generation workflows as background PTY sessions. The runner provides session IDs for monitoring, supports auto-notify on completion, and allows you to continue shell work without blocking.