01-architecture-overview

01-architecture-overview is a cursor rule for Cursor from gargoyle92/agentify-mcp. It costs 606 tokens per session, scanned A, original, MIT.

A project architecture guide for a TypeScript server. It shows the main entry file, the folders for sessions, tools, resources, types, logging, and notifications, plus required design rules.

In plain words
What is it for?
Use it when adding or changing server modules, tools, resources, shared types, logging, or event-based state handling.
Why use it?
It gives contributors one shared map of the codebase and helps keep new modules consistent with its existing structure.

Cursor rule for Cursor

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 rules/gargoyle92/agentify-mcp/01-architecture-overview
Clone the repo
git clone --depth 1 https://github.com/gargoyle92/agentify-mcp

Made for: Cursor.

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.

agentmods badge for 01-architecture-overview

README.md
[![agentmods](https://agentmods.dev/badge/rules/gargoyle92/agentify-mcp/01-architecture-overview.svg)](https://agentmods.dev/rules/gargoyle92/agentify-mcp/01-architecture-overview)
Your own site
<a href="https://agentmods.dev/rules/gargoyle92/agentify-mcp/01-architecture-overview"><img src="https://agentmods.dev/badge/rules/gargoyle92/agentify-mcp/01-architecture-overview.svg" alt="Measured on agentmods" height="20"></a>
Per session 606 This file is loaded in full into every session.
When invoked 606 The same file — it is already loaded in full.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00606 $0.00606
Opus 5 $0.00303 $0.00303
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00061 $0.00061

Measured 3d ago against content hash fc0aca8c49bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

01-architecture-overview 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 3d 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.

.cursor/rules/01-architecture-overview.mdc · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

01-Architecture-Overview

Project Structure

The main entry point is index.ts, which initializes the AgentifyMCPServer.

Core Components Architecture

src/
├── server/               # Core server modules
│   ├── agentify-mcp.ts  # Main MCP server implementation
│   ├── session-manager.ts      # Client session management
│   └── state-tracker.ts        # File system & state monitoring
├── tools/                # MCP tool implementations
│   └── tool-registry.ts        # Tool registration & execution
├── resources/            # MCP resource implementations
│   └── resource-manager.ts     # Resource management & serving
├── types/                # TypeScript type definitions
│   └── index.ts               # Central type exports
└── utils/                # Utility modules
    ├── logger.ts             # Logging system
    └── notification-manager.ts # Alert & notification system

CRITICAL RULES - MUST FOLLOW

✅ ALWAYS DO:

  1. Import from central types: Always import types from types/index.ts
  2. Use dependency injection: Pass Logger instance to all modules that need logging
  3. Follow EventEmitter pattern: All core classes extend EventEmitter for loose coupling
  4. Implement proper error handling: Use try-catch blocks and emit error events
  5. Validate client types: Always check AgentClientType before executing client-specific logic

❌ NEVER DO:

  1. Direct console.log: Always use the Logger instance - never use console.log/error directly
  2. Hardcode client detection: Use the detectClientType method in AgentifyMCPServer
  3. Skip error handling: Every async operation must have proper error handling
  4. Bypass session manager: Always use SessionManager for client operations
  5. Create circular dependencies: Keep clear separation between server, tools, and resources

Design Patterns Applied

  • Observer Pattern: EventEmitter-based communication
  • Registry Pattern: Tool and Resource registries for extensibility
  • Dependency Injection: Logger and manager instances passed to constructors
  • Strategy Pattern: Client-type specific tool and resource handling

Read the full file on GitHub · 56 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.

  1. 3d ago First seen · 56 lines · 606 tokens per session scan A fc0aca8c49bb

Subscribe to this mod's changes

01-architecture-overview is a cursor rule published in the GitHub repository gargoyle92/agentify-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 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 2026-08-31.