skills.rest
Manvendra08
Manvendra08COMMUNITY
Explore all skills by this author →
GitHub

dmux-workflows

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

1|Updated May 12, 2026
Search Tags:#multi-agent#tmux#ai-agents#development-workflows#parallel-workflows#dmux#code-orchestration
One-click install
npx skills add https://github.com/Manvendra08/TradingBot --skill dmux-workflows-manvendra08
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/Manvendra08/TradingBot/tree/main/_agent/skills/dmux-workflows
Command: npx skills add https://github.com/Manvendra08/TradingBot --skill dmux-workflows-manvendra08

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually coordinating multiple AI agent sessions across different tools for complex development tasks is time-consuming and prone to misalignment, leading to duplicated work and integration conflicts.

Core Features & Use Cases

  • Cross-harness agent orchestration: Run parallel sessions with Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen in isolated tmux panes.
  • Pre-built workflow patterns: Ready-to-use templates for common multi-agent tasks like research + implementation, multi-file feature development, test-fix loops, and parallel code review.
  • Conflict avoidance: Git worktree integration to isolate file changes across parallel agent sessions, eliminating merge conflicts.
  • Use Case: When building a new billing feature, you can run one agent to design the database schema, another to build the API endpoints, and a third to create the frontend UI components in parallel, then merge all results seamlessly.

Quick Start

Use the dmux-workflows skill to split your current feature implementation into parallel agent sessions for independent workstreams, then merge the completed results back into your main workflow once all panes finish.

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 merge conflicts?▼

You can run parallel AI agent sessions without merge conflicts by using tmux pane management and git worktree integration. This isolates file changes across different development harnesses, enabling structured merge workflows for multi-agent output.

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

Yes, cross-harness agent orchestration supports running Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen in isolated tmux panes. This allows you to coordinate multiple AI coding tools within a single parallel development workflow.

What is the best way to split feature implementation into parallel AI workstreams?▼

The best way to split feature implementation is using pre-built workflow patterns for multi-agent tasks. You can run one agent for database schemas, another for API endpoints, and a third for UI components, then merge the results seamlessly.

Does tmux pane management work for parallel code review and test-fix loops?▼

Tmux pane management works for parallel code review and test-fix loops by providing isolated environments for each AI agent. Pre-built workflow templates are available to automate these divide-and-conquer tasks across multiple development harnesses.

Do I need git worktrees to coordinate multiple AI coding agents?▼

You need git worktrees to coordinate multiple AI coding agents because they isolate file changes across parallel sessions, eliminating merge conflicts. This structured approach ensures outputs from different agents can be merged back cleanly.

When should I not use multi-agent orchestration for software development?▼

You should not use multi-agent orchestration for tightly coupled software development tasks where workstreams cannot be isolated. If changes require continuous manual alignment across files, parallel agent sessions will cause misalignment and integration conflicts.

Related Skills

Explore More Software Engineering Skills→
JeremyDev87JeremyDev87
31

taskmaestro

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

Community
Advanced
jpoutrinjpoutrin
14

parallel-execution

Execute multiple Claude Code agents in parallel with wave dependencies and git worktrees.

Community
Advanced
ThejanaJayalathThejanaJayalath

dmux-workflows

Orchestrate parallel AI agent sessions using tmux-based pane management.

Community
Advanced
tmalcolm-0607tmalcolm-0607

mad-parallel

Orchestrate wave-based parallel feature implementation across isolated git worktrees.

Community
Advanced