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.
npx agentmods add instructions/phuryn/swarm-protocol/claude-mdgit clone --depth 1 https://github.com/phuryn/swarm-protocolWrote 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/instructions/phuryn/swarm-protocol/claude-md)<a href="https://agentmods.dev/instructions/phuryn/swarm-protocol/claude-md"><img src="https://agentmods.dev/badge/instructions/phuryn/swarm-protocol/claude-md.svg" alt="Measured on agentmods" 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 | $0.01026 | $0.01026 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
swarm-protocol CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Swarm Protocol is a headless MCP server for AI agent team coordination. It solves state synchronization when multiple people work through AI agents (Claude Code, etc.) on the same codebase simultaneously — preventing file conflicts, tracking work in flight, and managing task dependencies.
Status: Alpha — all 19 MCP tools implemented, integration tests written. See docs/SPEC.md for the full design.
Philosophy & Positioning
This is a coordination protocol, not a project management tool. The origin insight: "Jira was built for humans clicking buttons. This is coordination infrastructure for agent-first teams." The problem isn't Kanban or sprints — it's state synchronization when agents are the primary interface.
Key differentiator: Every existing tool (Claude Code Agent Teams, CCPM, tick-md, Agent-MCP, 1Code, etc.) solves single-developer multi-agent coordination. Swarm Protocol solves multi-human multi-agent coordination across teams. See docs/LANDSCAPE.md for the full competitive analysis.
When making implementation decisions:
- Protocol over product. Keep it minimal and composable. Resist feature creep toward traditional PM concepts (sprints, boards, velocity, story points).
- MCP-native is the differentiator. The "UI" is Claude Code itself. No REST API or web dashboard in v1.
- Ship fast, iterate in public. This is a first-mover play on the "agent coordination protocol" category. Simplicity and speed of adoption matter more than feature completeness.
- The CLAUDE.md integration pattern is as important as the server itself. The drop-in snippet in
claude-md/COORDINATION.mdis what makes adoption zero-friction — agents coordinate automatically without humans configuring anything.
Tech Stack
- Node.js + TypeScript
- PostgreSQL (raw SQL via
pgdriver, no ORM) @modelcontextprotocol/sdkfor the MCP server- No auth layer or UI in v1
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.
- 4d ago First seen · 77 lines · 1,026 tokens per session scan A b03bfddcb3a4
swarm-protocol CLAUDE.md is an instructions file published in the GitHub repository phuryn/swarm-protocol (53 stars, last pushed 5mo ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0051 per session on Opus 5. 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 2026-08-30.
Other instructions, from other repositories
helixir AGENTS.md
Instructions for bookedsolidtech/helixir, covering agent instructions, quick reference and landing the plane (session completion).
superpowers-zh CLAUDE.md
Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
spec-kit-zh AGENTS.md
AGENTS.md instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
Meta_Kim CLAUDE.md
Claude Code instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
tree-sitter-analyzer CLAUDE.md
Claude Code instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.