skills.rest
RUSHYOP
RUSHYOPCOMMUNITY
Explore all skills by this author →
Website𝕏@rushyyyyyyyyyyyGitHub

dmux-workflows

Orchestrate parallel AI agent sessions with dmux pane management.

Updated Mar 19, 2026
Search Tags:#workflow orchestration#ai agents#multi-agent#tmux#pane management#parallel sessions#dmux
One-click install
npx skills add https://github.com/RUSHYOP/imperium-cli --skill dmux-workflows-rushyop
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dmux-workflows
Source: https://github.com/RUSHYOP/imperium-cli/tree/main/content/skills/dmux-workflows
Command: npx skills add https://github.com/RUSHYOP/imperium-cli --skill dmux-workflows-rushyop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate parallel AI agent sessions using dmux, a tmux-based pane manager, to streamline multi-agent workflows.

Core Features & Use Cases

  • Pattern 1: Research + Implement — split research and implementation across panes to accelerate delivery.
  • Pattern 2: Multi-File Feature — parallelize work across independent files for faster iteration.
  • Pattern 3: Test + Fix Loop — run tests in one pane while fixing in another to shorten feedback loops.
  • Pattern 4: Cross-Harness — coordinate tasks across Claude Code, Codex, and other tools in parallel.
  • Pattern 5: Code Review Pipeline — aggregate independent reviews into a consolidated report.

Quick Start

Start a dmux session and create agent panes to begin parallel work.

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 in tmux?▼

You can run parallel AI agent sessions by using a tmux-based pane manager like dmux to split panes, distribute prompts, and merge outputs across multiple independent sessions.

How does multi-agent workflow orchestration coordinate different coding tools?▼

Multi-agent workflow orchestration coordinates different coding tools by managing pane prompts across Claude Code, Codex, and OpenCode simultaneously, allowing tasks to run in parallel within a single project.

What is the best way to parallelize research and implementation across AI agents?▼

The best way to parallelize research and implementation is splitting the tasks across separate panes, enabling one agent to gather requirements while another implements code for faster delivery.

Can I coordinate cross-harness workflows across Claude Code and Codex in one project?▼

Yes, you can coordinate cross-harness workflows by using dmux to manage panes that run Claude Code, Codex, and other tools in parallel, aggregating their outputs into a unified workspace.

Do I need tmux installed to manage parallel agent panes?▼

Yes, you need tmux installed because the orchestration relies on dmux, a tmux-based pane manager, to handle splitting, running, and merging agent sessions.

How to shorten test and fix feedback loops using parallel sessions?▼

You can shorten test and fix loops by running tests in one pane while applying fixes in another, allowing continuous validation without stopping the implementation workflow.

Related Skills

Explore More Software Engineering Skills→
agentmattersagentmatters
3

dmux-workflows

Orchestrate parallel AI agent sessions across multiple harnesses using dmux.

Official
Intermediate
arbisoftarbisoft
4

dmux-workflows

Coordinate parallel AI agent sessions across tmux panes with dmux.

Official
Intermediate
hector-mannyhector-manny

dmux-workflows

Orchestrate parallel AI agent sessions using dmux, a tmux-based pane manager.

Community
Advanced
brandon-frysliebrandon-fryslie
4

hire-a-minion

Spawn a parallel Claude instance in a tmux session for concurrent task execution.

Community
Intermediate