Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Agent Army

Orchestrates a 2-layer parallel agent hierarchy for large refactors, multi-file migrations, and codebase-wide audits.

Dev & CodingAdvanced★ 259⑂ 42AI score 9/10Last updated: Aug 11, 2026

What it does

Turns work that spans dozens of files into a two-layer agent organization running in parallel.

  • Commander (your session model) handles recon → composition → briefing → verification
  • Layer 1: 3–50+ domain specialists, each with its own full context window
  • Layer 2: every L1 agent must spawn 2+ sub-agents (enforced, not optional)
  • You pick army size (Conservative → Maximum) and power level (Max Power / Heavy / Balanced / Economy) which maps to the Opus/Sonnet/Haiku mix per layer
  • Creates a git checkout -b rollback checkpoint and forces a written Deployment Gate checklist
  • Cross-checks git diff --stat against agent reports to catch phantom completions (agents claiming work they never did)
  • Up to 4 waves: Execute → Audit → Propagate → Notify, with a .army-state.md scratchpad for resuming

Who it's for

  • Developers doing sweeping color/naming/API migrations across many files
  • Tech leads running security, a11y, performance, or dead-code audits
  • Advanced Claude Code users who want disciplined sub-agent fan-out
  • Not for you if the job is 1–5 files — the skill itself says to do it inline

Examples

  1. Theme migration: "Replace all neon Tailwind colors with our sand palette" → 45 files, 5 domains; a Foundation Agent fixes shared deps first, then 5 L1 teams fan out in parallel
  2. Codebase audit: sweep every API route for missing auth checks; agents only raise flags, and a later Audit wave fixes them
  3. Downstream propagation: after an interface change, a Propagate wave updates the tests, docs, and configs that referenced the old shape

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/OneWave-AI/claude-skills/HEAD/agent-army/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the agent-army folder from the GitHub repo OneWave-AI/claude-skills into my ~/.claude/skills/agent-army/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/OneWave-AI/claude-skills.git /tmp/claude-skills && mkdir -p ~/.claude/skills && cp -r /tmp/claude-skills/agent-army ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/OneWave-AI/claude-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill in: cp -r claude-skills/agent-army ~/.claude/skills/
  5. Raise your session model with /model inside Claude Code — the commander's quality caps the army's quality.
  6. Restart Claude Code and ask something like "use the agent army to run this refactor."
  7. Start with Conservative size and Balanced power on your first run to gauge token spend before scaling up.
View source on GitHub ↗License: MIT