swarm

swarm is a skill for Claude Code, Codex from iii-experimental/agentos. It costs 17 tokens per session (245 once invoked), scanned B, original, Apache-2.0.

Instructions for coordinating several software agents as a group. The agents can work toward a shared goal, exchange proposals, and reach a consensus.

In plain words
What is it for?
Creating a group of agents, broadcasting tasks or proposals, collecting their responses, and checking whether they agree.
Why use it?
It provides a defined way to divide work and combine the agents' conclusions instead of coordinating every message manually.

Skill for Claude CodeCodex

Part of the agentos plugin — 10 skills, 5 commands, 5 agents, 2 hooks, 1 MCP server shipped together

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 skills/iii-experimental/agentos/swarm
Any agent
npx skills add iii-experimental/agentos --skill swarm
Clone the repo
git clone --depth 1 https://github.com/iii-experimental/agentos

Made for: Claude Code, Codex.

Or install agentos, the plugin that ships this one along with the rest of its 10 skills, 5 commands, 5 agents, 2 hooks, 1 MCP server.

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 swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/iii-experimental/agentos/swarm.svg)](https://agentmods.dev/skills/iii-experimental/agentos/swarm)
Your own site
<a href="https://agentmods.dev/skills/iii-experimental/agentos/swarm"><img src="https://agentmods.dev/badge/skills/iii-experimental/agentos/swarm.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 245 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. 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 $0.00017 $0.00245
Opus 5 $0.00009 $0.00122
Sonnet 5 $0.00003 $0.00049
Haiku 4.5 $0.00002 $0.00024

Measured 4d ago against content hash f72925e358e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

swarm scanned grade B with 2 findings 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 4d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

1. Create: `curl -X POST http://localhost:3111/api/swarm/create -H 'Content-Type: application/json' -d '{"goal": "<goal>", "agents": ["agent1", "agent2"], "strategy": "consensus"}'`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Create: `curl -X POST http://localhost:3111/api/swarm/create -H 'Content-Type: application/json' -d '{"goal": "<goal>", "agents": ["agent1", "agent2"], "strategy": "consensus"}'`
plugin/skills/swarm/SKILL.md · 14 lines

What it actually says

Swarm coordination:

  1. Create: curl -X POST http://localhost:3111/api/swarm/create -H 'Content-Type: application/json' -d '{"goal": "<goal>", "agents": ["agent1", "agent2"], "strategy": "consensus"}'
  2. Broadcast: curl -X POST http://localhost:3111/api/swarm/broadcast -H 'Content-Type: application/json' -d '{"swarmId": "<id>", "agentId": "claude-code", "type": "proposal", "content": "<proposal>"}'
  3. Collect: curl -X POST http://localhost:3111/api/swarm/collect -H 'Content-Type: application/json' -d '{"swarmId": "<id>"}'
  4. Consensus: curl -X POST http://localhost:3111/api/swarm/consensus -H 'Content-Type: application/json' -d '{"swarmId": "<id>"}'
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. 4d ago First seen · 14 lines · 17 tokens per session scan B f72925e358e7

Subscribe to this mod's changes

swarm is a skill published in the GitHub repository iii-experimental/agentos (162 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 245 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

python-package-management

Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.

microsoft/agent-framework · 43 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

verify-samples-tool

How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.

microsoft/agent-framework · 40 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens