dmux-workflows

Orchestrate parallel AI agent sessions in tmux panes with dmux.

1|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/TakMczk/copilot-cli-ecc --skill dmux-workflows
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/TakMczk/copilot-cli-ecc/tree/main/.github/skills/dmux-workflows
Command: npx skills add https://github.com/TakMczk/copilot-cli-ecc --skill dmux-workflows

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the management of multiple AI agent sessions running concurrently, enabling complex, parallelized development workflows across different AI harnesses.

Core Features & Use Cases

  • Parallel Agent Execution: Launch and manage multiple AI agent sessions simultaneously in separate tmux panes.
  • Cross-Harness Compatibility: Works with Claude Code, Codex, OpenCode, and other agent frameworks.
  • Workflow Patterns: Provides pre-defined patterns for research and implementation, multi-file feature development, test-and-fix loops, and cross-tool collaboration.
  • Use Case: Coordinate a team of AI agents to simultaneously review code for security, performance, and test coverage, then merge their findings.

Quick Start

Run the dmux skill to start a new parallel agent session and create a pane for implementing the auth middleware.

Frequently Asked Questions about dmux-workflows

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage parallel AI agent sessions for concurrent development tasks?

You can manage parallel AI agent sessions by using tmux pane orchestration to launch multiple agents simultaneously, enabling divide-and-conquer parallelism for concurrent execution and output merging across development workflows.

Can I use tmux orchestration to run Claude Code and Codex agents at the same time?

Yes, tmux orchestration supports cross-harness compatibility, allowing you to run Claude Code, Codex, and OpenCode agent frameworks simultaneously in separate panes for multi-agent development workflows.

What is the best way to coordinate multiple AI agents reviewing code for security and performance?

The best way to coordinate multiple AI agents is by using pre-defined workflow patterns that launch a team of agents in parallel to simultaneously review code for security, performance, and test coverage, then merge their findings.

How do I isolate file changes when running multi-agent workflows across different AI harnesses?

You can isolate file changes in multi-agent workflows by integrating with git worktrees, ensuring that concurrent AI agent sessions operating across different harnesses maintain isolated and conflict-free file modifications.

Do I need npm to install parallel agent workflow tools?

Yes, you need npm to install the parallel agent workflow orchestration tool, which facilitates the setup of tmux pane management for concurrent AI agent execution and multi-file feature development.

What workflow patterns are available for test-and-fix loops and multi-file feature development?

Available workflow patterns include pre-defined configurations for research and implementation, multi-file feature development, test-and-fix loops, and cross-tool collaboration to streamline parallelized development tasks.