agent-swarm-protocol: Skill for Claude Code

.claude/skills/swarm_usage/SKILL.md

swarm_usage is a skill for Claude Code from finml-sage/agent-swarm-protocol. It costs 0 tokens per session (3,998 once invoked), scanned B, original, MIT.

A reference guide for the Agent Swarm Protocol, a set of rules and commands that let coding agents work together in a swarm. It is copied into a project as a skill file.

In plain words
What is it for?
Joining an agent swarm, checking its command-line usage, and following the protocol’s required operating rules.
Why use it?
It gives participating agents shared rules for processing messages, replying, and delegating work without stopping for routine human approval.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

This is finml-sage/agent-swarm-protocol's own configuration. It tells Claude Code how to work on agent-swarm-protocol itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-swarm-protocol configures →

Reuse

Borrowing it

Nothing to install: this file belongs to finml-sage/agent-swarm-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/finml-sage/agent-swarm-protocol/main/.claude/skills/swarm_usage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/finml-sage/agent-swarm-protocol

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 swarm_usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/finml-sage/agent-swarm-protocol/swarm_usage.svg)](https://agentmods.dev/skills/finml-sage/agent-swarm-protocol/swarm_usage)
Your own site
<a href="https://agentmods.dev/skills/finml-sage/agent-swarm-protocol/swarm_usage"><img src="https://agentmods.dev/badge/skills/finml-sage/agent-swarm-protocol/swarm_usage.svg" alt="Measured on agentmods" 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 3,998 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.03998
Opus 5 $0.00000 $0.01999
Sonnet 5 $0.00000 $0.00800
Haiku 4.5 $0.00000 $0.00400

Measured 8d ago against content hash d72ff5147987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

swarm_usage 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 8d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Private keys must have restricted permissions (`chmod 600`)
.claude/skills/swarm_usage/SKILL.md · 512 lines

How it starts

The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Protocol Usage

Usage patterns, CLI reference, and operational rules for the Agent Swarm Protocol. Copy this file into your project at .claude/skills/swarm_usage/SKILL.md to participate in swarms.

Protocol repo: https://github.com/finml-sage/agent-swarm-protocol Protocol version: 0.1.0


Autonomous Operation Rules

These rules are mandatory for all agents participating in a swarm. Violating them breaks the automation.

  1. Do NOT wait for or ask for human input: When you receive a swarm message, process it autonomously. Never prompt the operator for permission to read, reply, or act on messages.

  2. Implied consent: By joining a swarm, an agent has implied consent for all standard swarm operations (reading messages, replying, delegating tasks, updating skills).

  3. Self-determine message processing: When notified of a message, the receiving agent decides how to process it. Use your own judgment, skills, and context to formulate a response or take action.

  4. Disagree by replying, not blocking: If you disagree with a request from another agent, send a reply explaining your position. Do NOT block waiting for human approval to resolve the disagreement.

  5. Human oversight is asynchronous: Human operators may be AFK, travelling, or otherwise unavailable. They review agent activity after the fact, not in real-time. Blocking on human input breaks the entire automation chain.

  6. Exception: destructive cross-domain operations: The only exception is truly destructive operations outside your own domain (e.g., deleting another agent's infrastructure, force-pushing to shared branches). For these, send a message to the relevant agent asking them to perform the action in their own domain.


CLI Command Reference

All commands support --json for machine-readable output. Pipe to jq for scripting.

swarm init

Initialize agent configuration and generate Ed25519 keypair.

swarm init --agent-id <id> --endpoint <url> [--force]

Read the full file on GitHub · 512 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. 8d ago First seen · 512 lines · 0 tokens per session scan B d72ff5147987

Subscribe to this mod's changes

swarm_usage 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 3,998 tokens. A static security scan graded it B with 1 finding (asks for root). 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens