skills.rest
derekhu0002
derekhu0002COMMUNITY
Explore all skills by this author →
WebsiteGitHub

dmux-workflows

Coordinate parallel AI agent sessions across Claude Code, Codex, and OpenCode harnesses.

Updated Mar 1, 2026
Search Tags:#agents#orchestration#tmux#parallel#workflows#dmux#harnesses
One-click install
npx skills add https://github.com/derekhu0002/ai4pb-orchestrator --skill dmux-workflows-derekhu0002
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/derekhu0002/ai4pb-orchestrator/tree/main/.agents/skills/dmux-workflows
Command: npx skills add https://github.com/derekhu0002/ai4pb-orchestrator --skill dmux-workflows-derekhu0002

SYSTEM DOCUMENTATION & REQUIREMENTS

## What problem does it solve? dmux Workflows provides a robust way to coordinate multiple AI agent sessions in parallel, enabling faster exploration and development by distributing tasks across panes.

## Core Features & Use Cases

  • Orchestrate parallel agent sessions across Claude Code, Codex, OpenCode, and other harnesses to accelerate complex tasks.
  • Pattern-based parallelization: split research, implementation, testing across panes and merge results when ready.
  • Cross-harness coordination with dmux pane management for synchronized outputs and unified progress tracking.

### Quick Start Start a dmux session and create parallel agent panes to run tasks concurrently.

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 complex development tasks?▼

You can run parallel AI agent sessions by distributing tasks across multiple panes using dmux. This approach splits research, implementation, and testing across concurrent agent panes to accelerate complex workflows and merge results upon completion.

What is dmux-based pane management for AI workflows?▼

Dmux-based pane management is a coordination method that synchronizes outputs and tracks progress across multiple AI agent sessions. It provides cross-harness coordination to manage concurrent tasks within a unified interface.

Can I coordinate Claude Code and Codex sessions concurrently in the same workflow?▼

Yes, you can coordinate Claude Code and Codex sessions concurrently. The dmux orchestration supports cross-harness coordination, allowing multiple tools like Claude Code, Codex, and OpenCode to run tasks in parallel.

How do I split development tasks across multiple agent panes and merge the results?▼

You can split tasks using pattern-based parallelization to assign research, implementation, and testing to separate agent panes. Once each parallel session completes its task, you merge the results back together.

Do I need any specific dependencies to start a dmux session for parallel orchestration?▼

No specific dependencies are required to start a dmux session for parallel orchestration. You can create parallel agent panes immediately to run tasks concurrently across your available harnesses.

Related Skills

Explore More Software Engineering Skills→
agentmattersagentmatters
3

dmux-workflows

Orchestrate parallel AI agent sessions across multiple harnesses using dmux.

Official
Intermediate
mitul-bhatiamitul-bhatia

dmux-workflows

Orchestrate parallel AI agent sessions across dmux-enabled panes.

Community
Advanced
compozycompozy
2.5k

smux

Coordinate AI agent messaging and pane control across tmux sessions.

Official
Intermediate
JeremyDev87JeremyDev87
31

taskmaestro

Orchestrate multiple Claude Code instances across tmux panes with isolated git worktrees.

Community
Advanced