Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/agency-ai-solutions/agencii-mcp-tools-deployment-templatenpx agentmods add rules/agency-ai-solutions/agencii-mcp-tools-deployment-template/workflowWrote 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/agency-ai-solutions/agencii-mcp-tools-deployment-template/workflow)<a href="https://agentmods.dev/rules/agency-ai-solutions/agencii-mcp-tools-deployment-template/workflow"><img src="https://agentmods.dev/badge/rules/agency-ai-solutions/agencii-mcp-tools-deployment-template/workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/agency-ai-solutions/agencii-mcp-tools-deployment-template/workflow"><img src="https://agentmods.dev/badge/rules/agency-ai-solutions/agencii-mcp-tools-deployment-template/workflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02334 | $0.02334 |
| Opus 5 | $0.01167 | $0.01167 |
| Sonnet 5 | $0.00467 | $0.00467 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade B, and why
workflow 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 11d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Do not run any commands globally. How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Creator Agent Instructions
Agency Swarm is a framework that allows anyone to create a collaborative swarm of agents (Agencies), each with distinct roles and capabilities. Your primary role is to architect tools that fulfill specific needs within the agency. This involves:
- To-Do List Creation: Create a to-do list of the steps to follow.
- Requirements Gathering: Gather information to draft a Product Requirements Document (PRD) for the agency.
- Research & PRD Creation: Search the web for the most relevant documentation about the packages and APIs that will be used to create the tools. Then, create the PRD file.
- Environment Setup: Setup the environment for the tools.
- Tool Development: Develop each tool and place it in the correct agent's tools folder, ensuring it is robust and ready for production environments.
- Testing: Test each tool for the agency, and the agency itself, to ensure they are working as expected.
You will find a detailed guide for each of the steps below.
Repository Structure
This is a repository that deploys tools as an MCP server. It has the following structure:
mcp-tools-template/
├── .cursor/
│ └── rules/
│ └── workflow.mdc # Do not touch
│ └── PRD.md # Product Requirements Document
├── tools/
│ ├── ToolName.py # Shared tools go here (available to all MCP instances)
│ ├── marketing_mcp/ # MCP instance-specific tools (by convention use _mcp suffix)
│ │ └── ToolName.py
│ └── analytics_mcp/ # Another MCP instance
│ └── ToolName.py
├── server/
│ └── ... # MCP server files (do not touch)
├── requirements.txt # Dependencies
├── .env # Environment variables
├── README.md
└── [other files] # Do not touch
Folder Structure Rules:
Follow this folder structure when further creating or modifying any files.
- The main 'tools' folder contains shared tools available to all MCP instances.
- By convention, create subdirectories with "_mcp" suffix for separate MCP instances (e.g., marketing_mcp, analytics_mcp).
- Tool files must be named exactly as the tool class name, with the .py extension.
- Tools in these folders are automatically deployed to the MCP server.
- All new tool requirements must be added to the requirements.txt file.
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.
- 11d ago First seen · 203 lines · 2,334 tokens per session scan B daf452f88014
workflow is a cursor rule published in the GitHub repository agency-ai-solutions/agencii-mcp-tools-deployment-template (14 stars, last pushed 27d ago), licensed MIT. It adds 2,334 tokens to every session, about $0.0117 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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-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.