coding-agent

Delegate coding tasks to AI agents via background PTY sessions.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Delegate coding tasks to AI agents via background processes, enabling faster feature development, PR reviews, and iterative refactoring while keeping work isolated and transparent.

Core Features & Use Cases

  • Background, PTY-enabled sessions for long-running coding tasks
  • Supports multiple agents (Codex, Claude Code, Pi, OpenCode) with per-task backends
  • Isolates work in target directories, enabling safe PR reviews and feature exploration
  • Session management via CLI with commands like start, log, poll, write, submit, and kill

Quick Start

Launch a background coding session in your project directory and issue prompts to Codex, Claude Code, Pi, or OpenCode as needed.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I delegate coding tasks to AI agents in the background?

You can delegate coding tasks to AI agents by launching background, PTY-enabled sessions that isolate work in target directories. Use session-management commands like start, log, poll, write, submit, and kill to control the execution flow.

What is the best way to review PRs using multiple AI coding agents?

Reviewing PRs with multiple AI agents involves isolating work in temporary directories and selecting specific backends like Codex, Claude Code, Pi, or OpenCode. This approach keeps feature exploration safe and transparent while running long tasks.

Do I need a PTY-enabled terminal to run background coding sessions?

Yes, a PTY-enabled terminal is required to run background coding sessions. This terminal type supports the interactive CLIs necessary for the agents to function properly during long-running feature development and refactoring tasks.

Can I use Claude Code and Codex simultaneously for codebase exploration?

Yes, you can explore large codebases using multiple agents simultaneously by explicitly selecting different backends like Claude Code and Codex. Each task runs in an isolated background session to maintain transparency and prevent conflicts.

How do I monitor and manage active AI agent coding sessions?

You monitor active AI agent coding sessions via CLI commands such as log, poll, and kill. These session-management commands allow you to track progress, issue prompts, and terminate long-running background tasks as needed.