skills.rest
sayasaya8039
sayasaya8039COMMUNITY
Explore all skills by this author →
GitHub

dmux-workflows

Coordinate multiple AI agent sessions in tmux panes with git worktree isolation.

2|Updated Mar 12, 2026
Search Tags:#multi-agent#tmux#git-worktrees#agent-orchestration#parallel-workflows#code-development#dmux
One-click install
npx skills add https://github.com/sayasaya8039/ZWG_Terminal --skill dmux-workflows-sayasaya8039
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/sayasaya8039/ZWG_Terminal/tree/main/.claude/skills/dmux-workflows
Command: npx skills add https://github.com/sayasaya8039/ZWG_Terminal --skill dmux-workflows-sayasaya8039

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually coordinating multiple AI agent sessions across different tools is slow, error-prone, and wastes time switching between panes and merging disjointed results.

Core Features & Use Cases

  • Parallel Agent Orchestration: Run multiple Claude Code, Codex, OpenCode, and other supported agent sessions side-by-side in tmux panes for divide-and-conquer development workflows.
  • Pre-built Workflow Patterns: Ready-to-use templates for common use cases including research + implementation, multi-file feature development, test-fix iteration loops, and cross-harness task assignment.
  • Isolation & Merge Support: Integrates with git worktrees to prevent file conflicts between parallel agents, with guided steps to merge completed work back into your main codebase.
  • Use Case Example: For a full-stack billing feature build, run one agent to design the database schema, another to build API endpoints, and a third to create frontend components in parallel, then merge all results seamlessly.

Quick Start

Use the dmux-workflows skill to split your complex development task into parallel agent workstreams, run each in its own tmux pane, and merge the completed results back into your 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 multiple AI coding agents in parallel for complex software development?▼

You can run multiple AI coding agents in parallel by orchestrating them across separate tmux panes. This approach uses git worktrees to isolate file changes between agents, preventing conflicts during divide-and-conquer development workflows.

What is the best way to prevent file conflicts when using multiple AI agents on the same project?▼

Using git worktrees is the best way to prevent file conflicts when running multiple AI agents simultaneously. Each agent operates in an isolated worktree, allowing overlapping file changes without corrupting the main codebase before a guided merge.

Can I coordinate Claude Code and Codex agents in the same parallel workflow?▼

Yes, you can coordinate Claude Code and Codex agents in the same parallel workflow. The orchestration supports cross-harness task assignment, allowing different agent sessions to run side-by-side in tmux panes for comprehensive software builds.

How do I merge results from parallel AI agent sessions back into my main codebase?▼

You merge results from parallel AI agent sessions by using guided steps to consolidate isolated git worktrees. This ensures completed work from each tmux pane is seamlessly integrated back into your main codebase without losing progress.

Do I need tmux to manage parallel AI agent workflows?▼

Yes, tmux is required to manage parallel AI agent workflows as it provides the pane management necessary to run sessions side-by-side. This enables efficient monitoring and coordination of divide-and-conquer development tasks across multiple agents.

What are common use cases for multi-agent orchestration in software development?▼

Common use cases for multi-agent orchestration include multi-file feature builds, cross-harness task assignment, test-fix iteration loops, and parallel code review. These workflows allow separate agents to handle database schemas, API endpoints, and frontend components simultaneously.

Related Skills

Explore More Software Engineering Skills→
JeremyDev87JeremyDev87
31

taskmaestro

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

Community
Advanced
otrebuotrebu
4

finish-feature

Merge a feature branch into main with conflict handling and push.

Community
Basic
ldk-hubldk-hub

dmux-workflows

Coordinate parallel AI agent sessions across multiple harnesses using dmux.

Community
Intermediate
automatedigitalautomatedigital
1

opencode

Delegate coding tasks to the OpenCode CLI autonomous agent.

Official
Intermediate