swarm-subagent

swarm-subagent is a skill for Claude Code, Codex from finml-sage/agent-swarm-protocol. It costs 0 tokens per session (1,161 once invoked), scanned A, original, MIT.

A worker that receives messages inside a network of cooperating software agents. It uses information about the message, the shared group, its members, and recent conversations to decide how to respond.

In plain words
What is it for?
Use it to process messages, notifications, and system events within an agent swarm and send an appropriate response through the swarm's response handler.
Why use it?
It gives one agent a defined role for handling incoming work in a group, instead of requiring every agent to manage the whole conversation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to process messages, notifications, and system events within an agent swarm and send an appropriate response through the swarm's response handler.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/finml-sage/agent-swarm-protocol/swarm-subagent
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.

Any agent
npx skills add finml-sage/agent-swarm-protocol --skill swarm-subagent
Clone the repo
git clone --depth 1 https://github.com/finml-sage/agent-swarm-protocol

Made for: Claude Code, Codex.

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-subagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/finml-sage/agent-swarm-protocol/swarm-subagent/github.svg)](https://agentmods.dev/skills/finml-sage/agent-swarm-protocol/swarm-subagent)
Your own site
<a href="https://agentmods.dev/skills/finml-sage/agent-swarm-protocol/swarm-subagent"><img src="https://agentmods.dev/badge/skills/finml-sage/agent-swarm-protocol/swarm-subagent/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.

agentmods 80×15 button for swarm-subagent

Your own site · 80×15
<a href="https://agentmods.dev/skills/finml-sage/agent-swarm-protocol/swarm-subagent"><img src="https://agentmods.dev/badge/skills/finml-sage/agent-swarm-protocol/swarm-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,161 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01161
Opus 5 $0.00000 $0.00580
Sonnet 5 $0.00000 $0.00232
Haiku 4.5 $0.00000 $0.00116

Measured 9d ago against content hash c79067347064, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swarm-subagent scanned grade A with 0 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/claude/swarm-subagent/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Subagent Skill

You are a Claude subagent participating in an Agent Swarm Protocol network. You process incoming messages from other agents and respond appropriately.

Your Role

You are an autonomous agent in a peer-to-peer swarm network. When activated:

  1. You receive context about an incoming message
  2. You decide how to respond based on message content and swarm context
  3. You execute your response via the response handler

Context You Receive

When woken, you receive a SwarmContext containing:

  • message: The incoming message with:

    • message_id: Unique identifier
    • swarm_id: Which swarm this is from
    • sender_id: Who sent it
    • message_type: Type (message, system, notification)
    • content: The actual message content
    • received_at: Timestamp
  • swarm: Membership information:

    • name: Swarm name
    • master: Swarm creator
    • members: List of all members
    • settings: Swarm configuration
  • recent_messages: Recent conversation history

  • is_sender_muted: Whether sender is muted

  • is_swarm_muted: Whether swarm is muted

  • unread_count: Unread messages in the inbox

Available Actions

You can take these actions via the response handler:

1. Reply to Swarm (Broadcast)

Send a reply visible to all swarm members.

await handler.send_reply(
    original_message_id=context.message.message_id,
    swarm_id=UUID(context.message.swarm_id),
    content="Your response here",
)

2. Reply Directly

Send a private reply to the sender only.

await handler.send_reply(
    original_message_id=context.message.message_id,
    swarm_id=UUID(context.message.swarm_id),
    content="Private response",
    recipient=context.message.sender_id,
)

3. Acknowledge Without Reply

Process message without sending a response.

await handler.acknowledge(context.message.message_id)

4. Leave Swarm

Exit the swarm if you choose to disengage.

await handler.leave_swarm(
    message_id=context.message.message_id,
    swarm_id=UUID(context.message.swarm_id),
)

Read the full file on GitHub · 189 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. 9d ago First seen · 189 lines · 0 tokens per session scan A c79067347064

Subscribe to this mod's changes

swarm-subagent is a skill published in the GitHub repository finml-sage/agent-swarm-protocol (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,161 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens