coding-agent

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

Updated Feb 8, 2026

Search Tags:#claude code #codex #git worktrees #pty #coding agent #background sessions #interactive cli

Ready to run

npx skills add https://github.com/nomad3/openclaw-k8s --skill coding-agent-nomad3

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/nomad3/openclaw-k8s/tree/main/package/skills/coding-agent
Command: npx skills add https://github.com/nomad3/openclaw-k8s --skill coding-agent-nomad3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of broken, hanging, or garbled output when running interactive coding agents (like Codex, Claude Code, OpenCode, or Pi) in a programmatic/batch environment.

Core Features & Use Cases

PTY-safe execution: Ensures interactive terminal applications run correctly by always allocating a pseudo-terminal.
Background session control: Starts agents in the background and manages them with session lifecycle actions like list, poll, log, write, submit, paste, send-keys, and kill.
Workspace-focused context: Uses a specified workdir so the agent operates in the intended project/repo scope (including safe scratch repos for Codex).

Quick Start

Start a Codex coding agent in your target repository with a PTY and background monitoring.

Frequently Asked Questions about coding-agent

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

FAQPage Schema

Why does my interactive coding agent output garbled text or hang in a batch environment?▼

Interactive coding agents output garbled text or hang because they expect a terminal. Allocating a pseudo-terminal (PTY) before execution ensures interactive CLI applications run correctly without broken or hanging output.

How do I run a coding agent in the background and monitor its session?▼

You can run a coding agent in the background by starting it with a PTY and using session lifecycle actions like list, poll, log, write, submit, paste, send-keys, and kill to monitor and manage the background process reliably.

Can I scope an interactive coding agent to a specific git worktree or repository directory?▼

Yes, you can scope an interactive coding agent to a specific git worktree or repository directory by specifying a focused work directory. This ensures the agent operates safely within the intended project context.

Does running Claude Code or Codex require PTY allocation for automated workflows?▼

Yes, running Claude Code or Codex in automated workflows requires PTY allocation. These interactive terminal applications need a pseudo-terminal to function correctly and avoid broken, hanging, or garbled output during programmatic execution.

What is the best way to manage long-running coding agent sessions for refactoring tasks?▼

The best way to manage long-running coding agent sessions for refactoring is to start them in the background with a specified work directory and PTY allocation, then use session tracking actions like poll, log, and send-keys for reliable monitoring and input.

How do I send input or keystrokes to a background coding agent session?▼

You can send input or keystrokes to a background coding agent session by using the write, submit, paste, and send-keys actions. These lifecycle commands allow you to interact with and control the agent during execution.