skills.rest
yusufcmg
yusufcmgCOMMUNITY
Explore all skills by this author →
GitHub

dmux-workflows

Coordinate parallel AI agent sessions across multiple harnesses using dmux.

Updated Aug 27, 2026
Search Tags:#agents#orchestration#tmux#parallel#workflows#dmux
One-click install
npx skills add https://github.com/yusufcmg/Agent_Memory_Systems --skill dmux-workflows-yusufcmg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/yusufcmg/Agent_Memory_Systems/tree/main/.claude/skills/dmux-workflows
Command: npx skills add https://github.com/yusufcmg/Agent_Memory_Systems --skill dmux-workflows-yusufcmg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate parallel AI agent sessions using dmux to manage multiple harnesses (Claude Code, Codex, OpenCode, and more) from a single, coherent workflow.

Core Features & Use Cases

  • Support for parallel agent sessions with independent panes to run research, implementation, testing, and review tasks.
  • Keyboard-driven pane management: create new panes, focus, and merge results back into the main session to keep context lean.
  • Cross-harness orchestration: coordinate tasks across Claude Code, Codex, and other AI tools in a single orchestration plan.
  • Pattern-based workflows: implement common patterns such as Research + Implement, Multi-File Feature, and Test + Fix loops to speed delivery.
  • Lightweight integration: installs via npm and runs in a standard tmux environment.

Quick Start

Start a dmux session, create agent panes for your tasks, and merge the results back to the main session.

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?▼

Run parallel AI agent sessions in tmux by using dmux to create independent panes for research, implementation, and testing. It provides keyboard-driven pane management to coordinate multiple harnesses from a single workflow.

Can I orchestrate tasks across Claude Code and Codex simultaneously?▼

Yes, you can orchestrate tasks across Claude Code and Codex simultaneously. dmux provides cross-harness integration to coordinate complex multi-agent tasks, allowing you to manage multiple AI tools within a single coherent orchestration plan.

What is the best way to manage multiple AI agent workflows for research and implementation?▼

The best way to manage multiple AI agent workflows is applying pattern-based templates like Research + Implement or Test + Fix loops. dmux coordinates these parallel tasks across independent tmux panes and merges results back to keep context lean.

Do I need npm and tmux installed to coordinate parallel agent sessions?▼

Yes, you need npm and a standard tmux environment to coordinate parallel agent sessions. dmux installs lightweight via npm and relies on tmux to provide the underlying pane management for running multiple agent harnesses.

How do I merge results from independent agent panes back into a main session?▼

Merge results from independent agent panes back into a main session using dmux keyboard-driven commands. This pane merging functionality consolidates outputs from parallel research, implementation, or testing tasks while keeping your main context lean.

Related Skills

Explore More Software Engineering Skills→
agentmattersagentmatters
3

dmux-workflows

Orchestrate parallel AI agent sessions across multiple harnesses using dmux.

Official
Intermediate
WUIX69WUIX69

dmux-workflows

Coordinate parallel AI agent sessions across multiple development harnesses.

Community
Intermediate
asheshgoplaniasheshgoplani
691

agent-deck

Manage AI agent sessions across Claude, Gemini, Codex, and OpenCode.

Community
Advanced
SOLEROMSOLEROM

dmux-workflows

Coordinate parallel AI agent sessions across harnesses using tmux-based pane management.

Community
Advanced