dmux-workflows

Orchestrate parallel AI agent sessions with dmux for Claude Code, Codex, and OpenCode.

Updated Nov 19, 2025
One-click install
npx skills add https://github.com/Sake-Team/SmartSake --skill dmux-workflows-sake-team
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/Sake-Team/SmartSake/tree/main/backup/skills/dmux-workflows
Command: npx skills add https://github.com/Sake-Team/SmartSake --skill dmux-workflows-sake-team

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of managing multiple AI agent sessions in parallel, making it easier to coordinate complex workflows and run parallel tasks simultaneously.

Core Features & Use Cases

  • Parallel AI Agent Sessions: Orchestrate parallel sessions of AI agents like Claude Code, Codex, and OpenCode.
  • Workflow Patterns: Offers patterns for research, implementation, testing, and cross-harness workflows.
  • Quick Start: Use dmux to create and manage parallel agent sessions for various tasks.

Quick Start

Start a dmux session and create agent panes for parallel tasks, such as implementing code, writing tests, or updating 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 for complex workflows?

To run parallel AI agent sessions, you can use dmux to create and manage multiple tmux panes, allowing various AI agents like Claude Code, Codex, and OpenCode to execute tasks simultaneously.

What is dmux and how does it help with AI agent orchestration?

dmux is a tmux-based pane manager that enables AI agent orchestration by coordinating parallel sessions, making it easier to run complex workflows and implement tasks simultaneously across different agent harnesses.

Do I need tmux installed to coordinate multiple AI agents?

Yes, you need tmux installed because dmux operates as a tmux-based pane manager, serving as the foundational dependency for creating and orchestrating parallel AI agent sessions.

Can I use OpenCode and Codex together in the same parallel workflow?

Yes, you can use OpenCode and Codex together. The dmux workflow supports cross-harness orchestration, allowing you to coordinate multiple compatible AI agents within parallel tmux sessions.

What is the best way to structure research and implementation tasks across parallel AI agents?

The best way to structure these tasks is using dmux workflow patterns, which provide predefined configurations for research, implementation, testing, and cross-harness coordination across parallel AI agent panes.

What are the limitations of using tmux-based pane management for parallel AI agents?

Limitations include the strict dependency on tmux and compatible AI agent harnesses; without this specific environment setup, the parallel processing and agent orchestration workflows cannot function.