dmux-workflows

Coordinate parallel AI agent sessions across multiple harnesses using dmux.

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/ldk-hub/broke-shopping --skill dmux-workflows-ldk-hub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/ldk-hub/broke-shopping/tree/main/.agent/.agents/skills/dmux-workflows
Command: npx skills add https://github.com/ldk-hub/broke-shopping --skill dmux-workflows-ldk-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate parallel AI agent sessions across multiple harnesses for scalable, coordinated task execution.

Core Features & Use Cases

  • Parallel agent sessions: Manage multiple AI panes concurrently to split research, implementation, and testing.
  • Cross-harness compatibility: Supports Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen for diverse toolchains.
  • Structured collaboration: Use tmux pane management to merge results back into a single workflow.

Quick Start

Start a dmux session and create agent panes by pressing 'n' to run prompts in parallel.

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 tmux?

You can coordinate parallel AI agents using tmux pane management with dmux. It allows you to create, merge, and manage independent agent panes to run concurrent prompts for research, implementation, and testing within a single terminal session.

What is multi-agent orchestration for AI workflows?

Multi-agent orchestration coordinates concurrent AI agent sessions across multiple harnesses. It enables scalable task execution by splitting workloads like research and implementation into independent panes that can be merged back into a single structured workflow.

Can I use tmux to manage different AI coding assistants at the same time?

Yes, you can manage multiple AI coding assistants concurrently. dmux supports cross-harness compatibility for Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen, enabling diverse toolchains to operate in parallel within coordinated tmux panes.

How do I merge results from multiple AI agents into one workflow?

You can merge results from multiple AI agents using dmux structured collaboration features. It leverages tmux pane management to combine outputs from independent agent panes, such as research and implementation tasks, back into a single unified workflow.

Do I need to install dmux separately to coordinate parallel agent work?

Yes, dmux installation is required to coordinate parallel AI agent work. The workflow depends on the dmux tool to leverage tmux pane management and hotkeys for creating and managing independent AI agent sessions across multiple harnesses.