coding-agent

Execute AI coding assistants via background processes with pseudo-terminal support.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/hummbl-dev/hummbl-agent --skill coding-agent-hummbl-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/hummbl-dev/hummbl-agent/tree/main/skills/coding-agent
Command: npx skills add https://github.com/hummbl-dev/hummbl-agent --skill coding-agent-hummbl-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables programmatic control over various AI coding assistants like Codex, Claude Code, and OpenCode, allowing for automated code generation, refactoring, and review tasks.

Core Features & Use Cases

  • Interactive Terminal Execution: Run coding agents within a pseudo-terminal (PTY) for proper interactive behavior.
  • Background Task Management: Execute long-running coding tasks in the background and monitor their progress.
  • Use Case: Automate the process of fixing multiple bugs by launching a separate coding agent for each issue using git worktrees, then monitoring their progress and creating pull requests upon completion.

Quick Start

Use the coding-agent skill to run codex exec 'Add error handling to the API calls' in the ~/Projects/myproject directory with a pseudo-terminal.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I automate code generation with AI coding assistants in the background?

Run interactive AI coding assistants like Codex and Claude Code using background processes to achieve programmatic control over automated code generation, refactoring, and review tasks.

How does pseudo-terminal execution work for interactive coding agents?

Pseudo-terminal (PTY) execution provides the proper interactive terminal behavior required for coding agents to operate correctly, supporting parameters for command execution, working directory, timeouts, and elevated privileges.

Can I run multiple coding agents simultaneously to fix different bugs?

Yes, you can launch a separate coding agent for each issue using git worktrees, monitor their progress through background task management, and create pull requests upon completion using process actions like list and poll.

What process actions are available for managing background coding sessions?

You can manage background coding sessions using process actions including list, poll, log, write, submit, send-keys, paste, and kill to control long-running automated coding tasks programmatically.

Do I need a pseudo-terminal to run Claude Code or Codex programmatically?

Yes, a pseudo-terminal (PTY) is required for correct operation when running interactive terminal applications like Claude Code or Codex, ensuring proper behavior during programmatic background execution.

What parameters are supported when executing coding agents via background processes?

Supported parameters include command execution, working directory, background execution mode, timeouts, and elevated privileges, enabling precise control over automated coding tasks and background sessions.