dmux-workflows

Coordinate parallel AI agent sessions across tmux panes and git worktrees.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/luongldptit/move-ticket --skill dmux-workflows-luongldptit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/luongldptit/move-ticket/tree/main/.agent/.agents/skills/dmux-workflows
Command: npx skills add https://github.com/luongldptit/move-ticket --skill dmux-workflows-luongldptit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually coordinating multiple parallel AI agent sessions across different harnesses like Claude Code and Codex is time-consuming and error-prone when splitting complex development tasks, leading to duplicated work and merge conflicts.

Core Features & Use Cases

  • Multi-Harness Support: Run parallel agent sessions across Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen in isolated tmux panes.
  • Prebuilt Workflow Patterns: Access ready-to-use templates for common multi-agent tasks including research-and-implement splits, parallel multi-file feature development, test-fix loops, and cross-perspective code reviews.
  • Conflict Avoidance: Integrate with git worktrees to isolate agent work on separate branches, eliminating file merge conflicts when combining parallel outputs.
  • Use Case: Split a new billing feature build into three parallel tracks: one agent builds the database schema, a second builds the API endpoints, and a third builds the UI components, cutting total development time significantly.

Quick Start

Use the dmux-workflows skill to split your complex feature development task into parallel agent sessions across your preferred AI harnesses to accelerate delivery.

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 without causing merge conflicts?

You can run parallel AI agent sessions safely by using tmux pane management combined with git worktrees to isolate each agent's work on a separate branch, eliminating file merge conflicts when combining outputs later.

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

Yes, multi-agent orchestration supports running Claude Code and Codex simultaneously alongside OpenCode, Cline, Gemini, and Qwen in isolated tmux panes to coordinate cross-tool development workflows.

What are common multi-agent workflow patterns for splitting complex development tasks?

Common parallel workflow patterns include research-and-implement splits, parallel multi-file feature development, iterative test-fix loops, and cross-perspective code reviews to divide and conquer complex builds.

Does coordinating multiple AI coding agents require manual tmux setup for each session?

No, dmux-workflows provides prebuilt workflow templates and automated tmux pane management, so you do not need to manually configure each parallel agent session or track API token usage by hand.

What is the best way to split a feature build across multiple AI agents?

The best way to split a feature build is assigning isolated tracks to parallel agents, such as one building the database schema, another the API endpoints, and a third the UI components, significantly cutting total development time.

How does git worktree integration help manage parallel AI agent outputs?

Git worktree integration isolates parallel agent work on separate branches, preventing file merge conflicts and duplicated effort when combining the outputs of multiple concurrent coding sessions.