dmux-workflows

Orchestrate parallel AI agent sessions in tmux panes with dmux.

Updated Jul 27, 2026
One-click install
npx skills add https://github.com/kouiso/designdiff --skill dmux-workflows-kouiso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/kouiso/designdiff/tree/main/.claude/skills/dmux-workflows
Command: npx skills add https://github.com/kouiso/designdiff --skill dmux-workflows-kouiso

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines complex development tasks by enabling multiple AI agents to work concurrently on different parts of a project, significantly speeding up development cycles.

Core Features & Use Cases

  • Parallel Agent Execution: Run multiple AI agents simultaneously in separate tmux panes.
  • Workflow Orchestration: Coordinate multi-agent development across different tools like Claude Code and Codex.
  • Use Case: When tackling a new feature, you can assign one agent to implement the backend API, another to write frontend components, and a third to generate documentation, all at the same time.

Quick Start

Use dmux to start a new session and create three agent panes, one for each task: "Implement the auth middleware", "Write tests for the user service", and "Update API documentation".

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 in separate panes?

Parallel AI agent sessions run concurrently in separate tmux panes using dmux, a tmux pane manager that orchestrates multiple agents working on different project parts simultaneously.

Can I coordinate multi-agent workflows across Claude Code and Codex?

Multi-agent workflows coordinate across Claude Code, Codex, and other harnesses using dmux to facilitate parallel development sessions across different AI agent tools.

What is the best way to speed up development cycles with multiple AI agents?

Speed up development cycles by assigning concurrent tasks like backend API implementation, frontend component writing, and documentation generation to multiple AI agents working in parallel.

How do I start a parallel agent workflow for a new feature?

Start a parallel agent workflow by using dmux to create a new session with multiple agent panes, assigning each pane a specific task like implementing auth middleware or writing service tests.

Do I need tmux installed to use parallel agent workflows?

Tmux is required as dmux operates as a tmux pane manager to facilitate parallel agent sessions and coordinate multi-agent development workflows across various AI harnesses.

What are the limitations of orchestrating parallel agents with dmux?

Orchestrating parallel agents with dmux is limited to compatible AI harnesses like Claude Code and Codex, managing session coordination within tmux pane infrastructure boundaries.