bucho

Orchestrate Claude Code and Codex agents via tmux for software development tasks.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows you to manage AI agents for complex development tasks, overseeing the entire lifecycle from task inception to user approval without writing code yourself.

Core Features & Use Cases

  • AI Agent Orchestration: Directs two specialized AI agents (Claude Code for implementation, Codex for advice) through tmux.
  • Full Task Lifecycle Management: Manages tasks from initial investigation and planning through implementation, testing, verification, and final approval.
  • Use Case: Delegate a feature request to "bucho" mode. It will coordinate the AI agents to research, plan, code, test, and prepare a reviewable report, ensuring the feature is fully implemented and validated according to your instructions.

Quick Start

Instruct the bucho skill to implement the user's request by managing the AI agents.

Frequently Asked Questions about bucho

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

FAQPage Schema
How do I manage AI agents for software development tasks?

You can manage AI agents for software development by orchestrating an implementation agent and an advisory agent through tmux, directing the full lifecycle from investigation and planning to testing and final approval.

What is the best way to automate code implementation and review with AI?

Automating code implementation and review involves directing specialized AI agents to research, plan, code, and test features, then preparing a reviewable report to ensure the task is validated according to your instructions.

Can I use tmux to coordinate multiple AI agents for development workflows?

Yes, you can use tmux to coordinate multiple AI agents by directing an implementation agent and an advisory agent, ensuring strict adherence to a defined communication protocol for task integrity and quality.

Do I need to write code myself when using AI agent orchestration for task management?

No, AI agent orchestration allows you to oversee the entire development lifecycle from task inception to user approval without writing code yourself, as the agents handle the implementation and testing.

How does an advisory agent assist with code review and testing?

An advisory agent assists by providing advice during the development workflow, ensuring the implementation agent completes tasks with rigorous testing, verification, and reporting according to the defined protocol.

What are the limitations of using AI agents for end-to-end software development?

Limitations include the requirement for strict adherence to a defined workflow and communication protocol to ensure task integrity, as deviating from the protocol may compromise the quality of the automated development lifecycle.