coding-agent

Delegate large-scale coding tasks to background AI agents in isolated workspaces.

1|Updated May 3, 2026
One-click install
npx skills add https://github.com/brikkoAI/brikko-studio --skill coding-agent-brikkoai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/brikkoAI/brikko-studio/tree/main/packages/core/skills/coding-agent
Command: npx skills add https://github.com/brikkoAI/brikko-studio --skill coding-agent-brikkoai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual effort of handling large, iterative coding tasks such as building new features, refactoring entire codebases, and reviewing pull requests, freeing you to focus on higher-level work instead of waiting for long-running jobs to complete.

Core Features & Use Cases

  • Multi-Agent Support: Works with Codex, Claude Code, OpenCode, and Pi coding agents, letting you use your preferred tool for the job.
  • Background Execution: All coding tasks run in the background immediately, so you never have to block your workflow waiting for results.
  • Isolated Workspaces: PR reviews and feature work run in temporary git clones or worktrees to avoid modifying your live project files.
  • Parallel Task Handling: Run multiple coding agents at once for batch work like fixing multiple GitHub issues simultaneously.
  • Use Case: If you need to refactor a 10,000-line legacy codebase, delegate the task to a background coding agent and get a direct notification when it finishes, no constant progress checking required.

Quick Start

Use the coding-agent skill to refactor the authentication module in your ~/my-project directory and notify me when the work is complete.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I run large codebase refactoring tasks in the background without blocking my workflow?

Large codebase refactoring can run in the background immediately by delegating the iterative coding tasks to AI coding agents, freeing your workflow and routing completion notifications directly to you.

Can I use Claude Code and Codex agents for parallel batch issue fixing?

Yes, parallel batch issue fixing is supported by running multiple AI coding agents like Claude Code and Codex simultaneously, handling multiple GitHub issues at once without blocking your environment.

Do I need specific PTY configuration to run OpenCode and Pi coding agents?

Yes, proper PTY configuration is required for Codex, Pi, and OpenCode agents to execute background coding tasks and route direct completion notifications via the message send tool.

What is the best way to handle feature development without waiting for long-running coding jobs?

Feature development is handled by offloading the iterative coding process to background AI agents, which execute the work immediately and send a direct notification upon completion.

Are there limitations when running multiple AI coding agents in isolated workspaces?

Limitations include requiring proper PTY configuration for certain agents like Codex and Pi, and tasks must be properly delegated to temporary git workspaces to prevent live file modifications.