What is OpenSwarm CLAUDE.md?

Project instructions for building Agency Swarm applications, which coordinate multiple AI agents with different roles. They cover how agents communicate, use tools, and share orchestration work.

They help create agents and agencies, add tools to agents, convert tools to a code-execution pattern, write agent instructions, and plan multi-agent projects.

They give an agent builder a defined process and point to the project rules and commands needed for more complex multi-agent systems.

OpenSwarm CLAUDE.md — Instructions file for coding agents by VRSEN: Project instructions for building Agency Swarm applications, which coord

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 instructions/vrsen/openswarm/claude-md

Clone the repo

git clone --depth 1 https://github.com/VRSEN/OpenSwarm

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vrsen/openswarm/claude-md.svg)](https://agentmods.dev/instructions/vrsen/openswarm/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vrsen/openswarm/claude-md"><img src="https://agentmods.dev/badge/instructions/vrsen/openswarm/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,865 This file is loaded in full into every session.

When invoked 1,865 The same file — it is already loaded in full.

Security scan D 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.

Model	Per session	Once invoked
Fable 5	$0.01865	$0.01865
Opus 5	$0.00932	$0.00932
Sonnet 5	$0.00373	$0.00373
Haiku 4.5	$0.00186	$0.00186

Measured 4d ago against content hash a1ee5ac845d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

OpenSwarm CLAUDE.md scanned grade D 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

- OPENAI_API_KEY (required) - Show instructions how to get it

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

6. **Collect API keys BEFORE development** (with instructions from api-researcher):

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mcp-skill-creator-agency CLAUDE.md — 92% identical, 24 lines differ

CLAUDE.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agency Builder

You are a specialized agent that coordinates specialized sub-agents to build production-ready Agency Swarm v1.0.0 agencies.

Before proceeding with agent creation, please read the following instructions carefully:

.cursor/rules/agency-swarm-workflow.mdc - your primary guide for creating agents and agencies

The following files can be read on demand, depending on the task at hand:

.cursor/commands/add-mcp.md - how to add MCP servers to an agent
.cursor/commands/mcp-code-exec.md - how to convert an MCP server into the Code Execution Pattern (progressive tool disclosure, 98% token reduction)
.cursor/commands/write-instructions.md - how to write effective instructions for AI agents
.cursor/commands/create-prd.md - how to create a PRD for an agent (use for complex multi agent systems)

Background

Agency Swarm is an open-source framework designed for orchestrating and managing multiple AI agents, built upon the OpenAI Assistants API. Its primary purpose is to facilitate the creation of "AI agencies" or "swarms" where multiple AI agents with distinct roles and capabilities can collaborate to automate complex workflows and tasks.

A Note on Communication Flow Patterns

In Agency Swarm, communication flows are uniform, meaning you can define them in any way you want. Below are some examples:

Orchestrator-Workers (Most Common)

agency = Agency(
    ceo,  # Entry point for user communication
    communication_flows=[
        (ceo, worker1),
        (ceo, worker2),
        (ceo, worker3),
    ],
    shared_instructions="agency_manifesto.md",
)

Sequential Pipeline (handoffs)

from agency_swarm.tools.send_message import SendMessageHandoff

# Each agent needs SendMessageHandoff as their send_message_tool_class
agent1 = Agent(..., send_message_tool_class=SendMessageHandoff)
agent2 = Agent(..., send_message_tool_class=SendMessageHandoff)

agency = Agency(
    agent1,
    communication_flows=[
        (agent1, agent2),
        (agent2, agent3),
    ],
    shared_instructions="agency_manifesto.md",
)

Read the full file on GitHub · 193 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.

4d ago First seen · 193 lines · 1,865 tokens per session scan D a1ee5ac845d8

Subscribe to this mod's changes

OpenSwarm CLAUDE.md is an instructions file published in the GitHub repository VRSEN/OpenSwarm (2,858 stars, last pushed 1mo ago), licensed MIT. It adds 1,865 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it D with 2 findings (asks the agent to reveal its instructions, harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

OpenSwarm CLAUDE.md