dmux-workflows

Coordinate parallel AI agent sessions across tmux panes and harnesses.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/richardnpaul/everything-vscode-copilot --skill dmux-workflows-richardnpaul
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/richardnpaul/everything-vscode-copilot/tree/main/.github/skills/dmux-workflows
Command: npx skills add https://github.com/richardnpaul/everything-vscode-copilot --skill dmux-workflows-richardnpaul

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating multiple AI agent sessions across several harnesses can become chaotic and error-prone. This Skill centralizes pane-based orchestration using dmux (tmux pane manager) to streamline parallel work streams and reduce context switching.

Core Features & Use Cases

  • Parallel agent orchestration: manage multiple agent panes across Claude Code, Codex, OpenCode, Cline, Gemini, Qwen, and other harnesses from a single session.
  • Pattern-driven workflows: implement common multiprocessing patterns (Pattern 1: Research + Implement, Pattern 2: Multi-File Feature, Pattern 3: Test + Fix Loop, Pattern 4: Cross-Harness, Pattern 5: Code Review Pipeline) with pane splitting and merging.
  • Safe, modular collaboration: isolate tasks per pane and coordinate task handoffs to reduce conflicts.

Quick Start

Start a dmux session and create parallel agent panes for your current project tasks.

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 run parallel AI agent sessions by using a tmux pane manager to orchestrate multiple agent panes within a single session, enabling concurrent task execution across different harnesses.

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

Yes, cross-harness orchestration allows you to manage Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen panes from a single session to execute pattern-driven workflows and coordinate task handoffs.

What is the best way to manage multiple AI coding agents without context switching?

Orchestrating agents through a centralized tmux pane manager isolates tasks per pane and coordinates handoffs, which streamlines parallel work streams and reduces the chaos of context switching.

How do I set up a code review pipeline using parallel agent panes?

You can implement a code review pipeline by applying pattern-driven workflows that split and merge tmux panes, assigning specific review and implementation tasks to isolated parallel agent sessions.

Does parallel agent orchestration support test and fix loops?

Yes, parallel orchestration supports multiprocessing patterns like the test and fix loop, allowing you to dedicate separate panes to running tests and applying fixes concurrently across your harnesses.