orchestrating-swarms

orchestrating-swarms is a command for Claude Code from HomenShum/NodeBenchAI. It costs 59 tokens per session (7,681 once invoked), scanned B, original, MIT.

A guide to coordinating multiple Claude Code agents working on related tasks. It explains teams, task assignments, dependencies, messages, and different ways teammates can run.

In plain words
What is it for?
Use it for parallel code reviews, divide-and-conquer coding, dependency-based pipelines, and task queues where several agents share responsibility.
Why use it?
Splitting a large job among agents can become difficult to track. This provides named work items and communication patterns for coordinating parallel or dependent work.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/homenshum/nodebenchai/orchestrating-swarms
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orchestrating-swarms

README.md
[![agentmods](https://agentmods.dev/badge/commands/homenshum/nodebenchai/orchestrating-swarms.svg)](https://agentmods.dev/commands/homenshum/nodebenchai/orchestrating-swarms)
Your own site
<a href="https://agentmods.dev/commands/homenshum/nodebenchai/orchestrating-swarms"><img src="https://agentmods.dev/badge/commands/homenshum/nodebenchai/orchestrating-swarms.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,681 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.07681
Opus 5 $0.00030 $0.03841
Sonnet 5 $0.00012 $0.01536
Haiku 4.5 $0.00006 $0.00768

Measured 3d ago against content hash 5a7be8f8ba22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

orchestrating-swarms scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

// Collect: cat ~/.claude/teams/code-review/inboxes/team-lead.json
.claude/commands/orchestrating-swarms.md · 813 lines

How it starts

The opening of the file, as written. The whole thing — 813 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.


Primitives

Primitive What It Is File Location
Agent A Claude instance that can use tools. You are an agent. Subagents are agents you spawn. N/A (process)
Team A named group of agents working together. One leader, multiple teammates. ~/.claude/teams/{name}/config.json
Teammate An agent that joined a team. Has a name, color, inbox. Spawned via Task with team_name + name. Listed in team config
Leader The agent that created the team. Receives teammate messages, approves plans/shutdowns. First member in config
Task A work item with subject, description, status, owner, and dependencies. ~/.claude/tasks/{team}/N.json
Inbox JSON file where an agent receives messages from teammates. ~/.claude/teams/{name}/inboxes/{agent}.json
Message A JSON object sent between agents. Can be text or structured (shutdown_request, idle_notification, etc). Stored in inbox files
Backend How teammates run. Auto-detected: in-process (same Node.js, invisible), tmux (separate panes, visible), iterm2 (split panes in iTerm2). See Spawn Backends. Auto-detected based on environment

How They Connect

TEAM:
  Leader (you) <--> messages via inbox <--> Teammate 1
  Leader (you) <--> messages via inbox <--> Teammate 2
  Teammate 1 <-.-> can message <-.-> Teammate 2

TASK LIST:
  #1 completed: Research      (owner: teammate1)
  #2 in_progress: Implement   (owner: teammate2)
  #3 pending: Test            (blocked by #2)

Lifecycle

1. Create Team → 2. Create Tasks → 3. Spawn Teammates → 4. Work → 5. Coordinate → 6. Shutdown → 7. Cleanup

Two Ways to Spawn Agents

Method 1: Task Tool (Subagents)

Use Task for short-lived, focused work that returns a result:

Task({
  subagent_type: "Explore",
  description: "Find auth files",
  prompt: "Find all authentication-related files in this codebase",
  model: "haiku"  // Optional: haiku, sonnet, opus
})

Read the full file on GitHub · 813 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 813 lines · 59 tokens per session scan B 5a7be8f8ba22

Subscribe to this mod's changes

orchestrating-swarms is a command published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 7,681 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other commands, from other repositories

shadcn-form-guide

This guide demonstrates proper ShadCN form implementation using @tanstack/react-form with the October 2025 component suite (Field, InputGroup, etc.).

dyeoman2/tanstack-start-template · 0 tokens

kill

run this command in the terminal.

dyeoman2/tanstack-start-template · 0 tokens

dark-mode

You are a rigorous UI accessibility and design reviewer for React apps using Tailwind CSS v4 and Shadcn UI. You must.

dyeoman2/tanstack-start-template · 0 tokens

review-as-tanner

Pretend you are the creator of Tanstack Start, Tanner Linsley, now review the following page structure, performance, data loading, etc to provide actionable feedback and suggestions. Create a file called REVIEW.md and log them all in an MD file so that I can make sure that we know everything has been reviewed and…

dyeoman2/tanstack-start-template · 0 tokens

review-critique

someone created the REVIEW.MD file with reccomendations because i'm not sure if they're actually good reccomendations. please review the file, review our code and see if you think: 1. the reccommendation is a good one, if so, keep it. 2. if you disagree or have a nuanced take of a reccommendation, update the file with…

dyeoman2/tanstack-start-template · 0 tokens

review-as-pocock

Fix this TypeScript code as if you were Matt Pocock: eliminate unsafe patterns, preserve inference, and rewrite with modern type-safety best practices (satisfies, generics, discriminated unions, type predicates), showing patch-ready fixes with brief explanations.

dyeoman2/tanstack-start-template · 0 tokens