OpenSwarm is an open-source multi-agent system in which specialized agents coordinate to produce deliverables such as presentations, research reports, data visualizations, documents, images, and videos. It is intended for people who want to request complex creative or analytical work from a terminal, with connections to external services. Its catalogue entries define agents, commands, rules, and instructions for those workflows.
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 rules/vrsen/openswarm/agency-swarm-workflowgit clone --depth 1 https://github.com/VRSEN/OpenSwarmWrote 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/rules/vrsen/openswarm/agency-swarm-workflow)<a href="https://agentmods.dev/rules/vrsen/openswarm/agency-swarm-workflow"><img src="https://agentmods.dev/badge/rules/vrsen/openswarm/agency-swarm-workflow.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 | $0.04621 | $0.04621 |
| Opus 5 | $0.02311 | $0.02311 |
| Sonnet 5 | $0.00924 | $0.00924 |
| Haiku 4.5 | $0.00462 | $0.00462 |
Grade A, and why
agency-swarm-workflow 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- workflow — 88% identical, 88 lines differ
How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Swarm Agent Creator Instructions
Agency Swarm is the framework built on the OpenAI Agents SDK. It allows anyone to create a collaborative swarm of agents (Agencies), each with distinct roles and capabilities. Your primary role is to architect tools and agents that fulfill specific needs within the agency.
The following steps outline how to build AI agents with Agency Swarm:
- Setup: Create a to-do list for yourself and activate a virtual environment. If virtual environment does not exist, create it.
- Project Exploration: Understand the existing project structure, check for PRD, and remove example agents if present.
- Folder Structure and Template Creation: Create the Agent Templates for each agent using the CLI Commands provided below.
- Tool Development: Develop each tool and place it in the correct agent's tools folder, ensuring it is robust and ready for production environments.
- Agent Creation: Create agent classes and instructions for each agent, ensuring correct folder structure.
- Agency Creation: Create the agency class in the agency folder, properly defining the communication flows between the agents.
- Testing: Test each tool for the agency, and the agency itself, to ensure they are working as expected.
- Iteration: Repeat the above steps as instructed by the user, until the agency performs consistently to the user's satisfaction.
You will find a detailed guide for each of the steps below. Read this entire file first before proceeding.
Step 1: Project Exploration
Before starting any work, you must understand the current state of the project and prepare it for agent creation.
Exploration Checklist
- Activate virtual environment: Check if venv exists and activate it. If not, create it and install the
requirements.txtfile. (Note: venv might be named either venv or .venv. Check both.) - Check root directory structure: List files and folders in the project root
- Look for PRD: Check if
prd.txtexists in the root directory - Check for example agents: Look for folders like
example_agent/orexample_agent2/ - Review existing files: Read
agency.py,shared_instructions.md,agent_name/instructions.md,agent_name/tools/, etc.
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.
- 5d ago First seen · 450 lines · 4,621 tokens per session scan A 773bb03be1ec
agency-swarm-workflow is a cursor rule published in the GitHub repository VRSEN/OpenSwarm (2,858 stars, last pushed 1mo ago), licensed MIT. It adds 4,621 tokens to every session, about $0.0231 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.