Borrowing it
Nothing to install: this file belongs to HomenShum/NodeBenchAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HomenShum/NodeBenchAI/main/.claude/commands/orchestrating-swarms.mdgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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.
[](https://agentmods.dev/commands/homenshum/nodebenchai/orchestrating-swarms)<a href="https://agentmods.dev/commands/homenshum/nodebenchai/orchestrating-swarms"><img src="https://agentmods.dev/badge/commands/homenshum/nodebenchai/orchestrating-swarms/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/homenshum/nodebenchai/orchestrating-swarms"><img src="https://agentmods.dev/badge/commands/homenshum/nodebenchai/orchestrating-swarms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.07681 |
| Opus 5.5 | $0.00024 | $0.03072 |
| Sonnet 5.5 | $0.00012 | $0.01536 |
| Haiku 4.5 | $0.00006 | $0.00768 |
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 1mo 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 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
})
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.
- 1mo ago First seen · 813 lines · 59 tokens per session scan B 5a7be8f8ba22
orchestrating-swarms is a command published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 7,681 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
ralph-help
Explain Ralph Loop plugin and available commands.
t800-onboard
A command for newcomers that explains what is installed in Cursor globally and in the current project, plus what the T-800 team can do.