dmux-workflows

Orchestrate parallel AI agent sessions across Claude Code, Codex, and OpenCode using dmux.

1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Michae2xl/claude-skills-michael --skill dmux-workflows-michae2xl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/Michae2xl/claude-skills-michael/tree/main/skills/dmux-workflows
Command: npx skills add https://github.com/Michae2xl/claude-skills-michael --skill dmux-workflows-michae2xl

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of managing parallel AI agent sessions, allowing users to coordinate and execute complex workflows across multiple AI tools simultaneously.

Core Features & Use Cases

  • Multi-agent Orchestration: Manage and synchronize workflows involving Claude Code, Codex, OpenCode, and other AI agents.
  • Parallel Sessions: Run multiple agent sessions in parallel, enhancing productivity for tasks that benefit from parallelism.
  • Use Case: For instance, while developing a new feature, you can use dmux to run tests, implement code, and review documentation in parallel, speeding up the development process.

Quick Start

Start a dmux session and create agent panes for different tasks, such as "Implement the auth middleware in src/auth/" and "Write tests for the user service".

Frequently Asked Questions about dmux-workflows

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

FAQPage Schema
How do I run parallel AI agent sessions to speed up development tasks?

You can orchestrate parallel AI agent sessions using dmux, a tmux-based pane manager, to execute complex workflows like running tests and implementing code simultaneously across multiple AI tools.

What is multi-agent orchestration and how does it work with tmux?

Multi-agent orchestration coordinates parallel AI sessions by managing separate tmux panes for each agent, synchronizing workflows across Claude Code, Codex, and OpenCode to execute tasks concurrently.

Can I use dmux to coordinate Claude Code and Codex agents in the same workflow?

Yes, dmux supports multi-agent orchestration across Claude Code, Codex, OpenCode, and other compatible harnesses, allowing you to synchronize and execute parallel workflows within a single tmux session.

Do I need dmux installed before I can orchestrate parallel AI workflows?

Yes, dmux is a required dependency for this Skill, serving as the tmux-based pane manager that enables parallel execution and coordination across multiple AI agents.

What's the best way to start a parallel workflow for code implementation and testing?

Start a dmux session and create dedicated agent panes for distinct tasks, such as implementing auth middleware in one pane and writing tests for a user service in another to run them in parallel.

When should I avoid using parallel AI agent sessions for my development workflow?

Parallel AI orchestration is less suitable for tasks with heavy sequential dependencies or tight coordination requirements, where managing concurrent agent outputs may introduce complexity rather than speed.