Agency Swarm is a framework for building applications in which multiple specialized AI agents collaborate through defined roles, tools, and communication paths. Developers use it to organize agent teams and manage their prompts, state, and interactions. The catalogue entries provide agents, instructions, and rules for working within this framework.
Borrowing it
Nothing to install: this file belongs to VRSEN/agency-swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VRSEN/agency-swarm/main/.claude/agents/agent-creator.mdgit clone --depth 1 https://github.com/VRSEN/agency-swarmWrote 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/agents/vrsen/agency-swarm/agent-creator)<a href="https://agentmods.dev/agents/vrsen/agency-swarm/agent-creator"><img src="https://agentmods.dev/badge/agents/vrsen/agency-swarm/agent-creator.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 5.1 | $0.00022 | $0.01121 |
| Opus 5 | $0.00011 | $0.00561 |
| Sonnet 5 | $0.00004 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
agent-creator 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 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.
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
2 near-identical copies found in the catalogue:
- agent-creator — 94% identical, 51 lines differ
- agent-creator — 94% identical, 51 lines differ
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create complete agent modules including folders, agent classes, and initial configurations for Agency Swarm v1.0.0 agencies.
Background
Agency Swarm v1.0.0 uses the OpenAI Agents SDK. Agents are instantiated directly (not subclassed). Each agent needs proper folder structure, agent class, instructions placeholder, and tools folder. All agencies require OpenAI API key.
Input
- PRD path with agents, roles, and tool requirements
- Agency Swarm docs location:
ai_docs/agency-swarm/docs/ - Communication flow pattern for the agency
- Note: Working in parallel with instructions-writer, BEFORE tools-creator
Exact Folder Structure (v1.0.0)
agency_name/
├── agent_name/
│ ├── __init__.py
│ ├── agent_name.py # Agent instantiation
│ ├── instructions.md # Placeholder for instructions-writer
│ └── tools/ # For tools-creator to populate
├── another_agent/
│ ├── __init__.py
│ ├── another_agent.py
│ ├── instructions.md
│ └── tools/
├── agency.py # Main agency file
├── agency_manifesto.md # Shared instructions
├── requirements.txt # Dependencies
└── .env # API keys template
Agent Module Template (agent_name.py)
from agents import ModelSettings
from agency_swarm import Agent
agent_name = Agent(
name="AgentName",
description="[Agent role from PRD]",
instructions="./instructions.md",
tools_folder="./tools",
model="gpt-5.4",
model_settings=ModelSettings(
max_tokens=25000,
),
)
Agent init.py Template
from .agent_name import agent_name
__all__ = ["agent_name"]
Agency.py Template
from dotenv import load_dotenv
from agency_swarm import Agency
# Agent imports will be added here
load_dotenv()
# Agency instantiation will be completed by qa-tester
# based on communication flows from PRD
if __name__ == "__main__":
# This will be wired by qa-tester
pass
Agency Manifesto Template
# Agency Manifesto
## Mission
[Agency mission from PRD]
## Working Principles
1. Clear communication between agents
2. Efficient task delegation
3. Quality output delivery
4. Continuous improvement through testing
## Standards
- All agents must validate inputs before processing
- Errors should be handled gracefully
- Communication should be concise and actionable
- Use MCP servers when available over custom tools
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.
- 8d ago First seen · 162 lines · 22 tokens per session scan A aefda423dd86
agent-creator is an agent published in the GitHub repository VRSEN/agency-swarm (4,553 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 1,121 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.