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

Agent Teams Command

A bounded multi-agent command protocol that splits genuinely independent work across 5–100+ isolated workers, verifies outputs independently, and integrates serially.

AutomationAdvanced★ 140⑂ 22AI score 8/10Last updated: Sep 19, 2026

What it does

  • Triages the mission and picks the smallest viable tier: Squad (5), Squadron (10), Battle Group (50), or Fleet (100+).
  • Requires a pre-flight task list — owner, territory, expected output, verification command, token budget — before any parallel launch.
  • Assigns each worker an exclusive write territory (separate directory or git worktree) so file collisions are impossible by construction.
  • Tracks worker state (pending → active → review → accepted → closed) on a shared command board; separate evaluator/reviewer agents verify output — no self-certification.
  • Integrates serially in dependency order, runs the regression suite, then cleans up worktrees and persists execution receipts.
  • Ships explicit failure codes (NEEDS_INPUT, BLOCKED_DEPENDENCY, BUDGET_STOP, NO_PROGRESS...) with a hard 2-attempt retry cap.

Who it's for

  • Tech leads and senior engineers running large refactors or migrations across many agents.
  • Anyone whose parallel-agent experiments failed from file conflicts, runaway token burn, or unverifiable output.
  • Automation operators with isolated workers, git worktrees, and durable state storage.

Examples

  1. Add tests to 20 modules: one worker per module in its own worktree, reviewer checks coverage criteria, integrator merges serially and runs full regression.
  2. Large framework upgrade: partition territories by package, integrate in dependency order, and halt via BUDGET_STOP with a rollback plan if the token budget is exceeded.
  3. Bulk docs/translation pass: worker per file batch plus a dedicated review agent, merging only artifacts that clear the quality gates.

· · · 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/Mark393295827/third-brain-v7-skills/HEAD/skills/agent-teams-command/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 skills/agent-teams-command folder from the GitHub repo Mark393295827/third-brain-v7-skills into my ~/.claude/skills/agent-teams-command/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Mark393295827/third-brain-v7-skills.git /tmp/tb7 && mkdir -p ~/.claude/skills && cp -r /tmp/tb7/skills/agent-teams-command ~/.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/Mark393295827/third-brain-v7-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r third-brain-v7-skills/skills/agent-teams-command ~/.claude/skills/
  5. Confirm the references/ files came along with it.
  6. Restart Claude Code and try a prompt like "split this work across parallel agents with exclusive write territories".
  7. Start at Tier 1 (5 agents) with a small token budget before scaling up.
View source on GitHub ↗License: MIT