Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Dmux Workflows

ASecurity

Use when running multiple agent sessions in parallel with dmux/tmux panes across harnesses. Triggers on \"dmux\", \"multi-agent\", \"parallel agents\", \"tmux panes\".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsbashgitapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill dmux-workflows --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dmux Workflows?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Dmux Workflows
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-dmux-workflows/badge)](https://www.skillsdirectory.com/skills/majinmagros-dmux-workflows)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: dmux-workflows
description: "Use when running multiple agent sessions in parallel with dmux/tmux panes across harnesses. Triggers on \"dmux\", \"multi-agent\", \"parallel agents\", \"tmux panes\"."
metadata:
  origin: ECC
---

# dmux Workflows

Orchestrate parallel AI agent sessions using dmux, a tmux pane manager. Detalhes em `references/`.

## When to Activate

- Running multiple agent sessions in parallel
- Coordinating work across Claude Code, Codex, and other harnesses
- Complex tasks that benefit from divide-and-conquer parallelism
- User says "run in parallel", "split this work", "use dmux", or "multi-agent"

## Core Principles

1. **Independent tasks only** — never parallelize dependent outputs
2. **Clear boundaries** — each pane owns distinct files or concerns
3. **Merge strategically** — review pane output before merging
4. **Isolate with worktrees** when panes touch overlapping files
5. **Cap at 5-6 panes** — each pane is a full session burning tokens

## Example

```bash
dmux
# press 'n', then prompt per pane:
# Pane 1: "Create the billing schema and migrations"
# Pane 2: "Build the billing API endpoints"
# press 'm' to merge results back
```

## References

- `references/concepts-setup.md` — what is dmux, install, quick start, tools table
- `references/workflow-patterns.md` — research+implement, multi-file, test/fix, cross-harness, review
- `references/worktrees-orchestration.md` — git worktrees, ECC helper, seedPaths
- `references/signals-enrichment.md` — troubleshooting, cmux vs tmux, wait-for signals

## Checklist

- [ ] Tasks are independent with clear file/concern boundaries
- [ ] Worktrees created when file overlap is likely
- [ ] Pane count kept at 5-6 max for token control
- [ ] Output reviewed before merge; completion signal defined

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →