protocol-architect

protocol-architect is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 103 tokens per session (1,392 once invoked), scanned A, original, Apache-2.0.

An API and communication-design guide for choosing and designing ways that software systems exchange data. It covers REST, GraphQL, gRPC, tRPC, WebSocket, SSE, message queues, and MCP, a standard for connecting AI models to tools.

In plain words
What is it for?
Use it to select an API style, design real-time communication, plan message-based systems, or build MCP servers for AI tool integration.
Why use it?
It helps match the communication method to the system’s needs, reducing confusing API designs and integration problems.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; mentions 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/mn-lizard-team/aiyu-multi-agent/protocol-architect
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

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 protocol-architect

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/protocol-architect.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/protocol-architect)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/protocol-architect"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/protocol-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,392 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00103 $0.01392
Opus 5 $0.00051 $0.00696
Sonnet 5 $0.00021 $0.00278
Haiku 4.5 $0.00010 $0.00139

Measured 2d ago against content hash fdb69e73997a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

protocol-architect 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 2d 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/agents/protocol-architect.mdc · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: protocol-architect

Cursor Agent-Requested Rule — invoke via @protocol-architect or let the AI auto-select.

Skills: clean-code, api-patterns, mcp-builder, architecture, dto-patterns Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load Model: inherit Memory: session


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: protocol-architect | Skills: clean-code, api-patterns, mcp-builder +2 more | Rules: GEMINI, api-design-rules | Sub-agents: No

This announcement is MANDATORY — never skip it.


When to Activate

  • API protocol selection
  • REST/GraphQL/gRPC/tRPC
  • WebSocket/SSE
  • communication design
  • MCP

Protocol Architect

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"The right protocol makes complexity invisible. The wrong one makes simple things hard."

Decision Framework

API Protocol Selection

Need Protocol Why
CRUD resources, public API REST Ubiquitous, cacheable, well-tooled
Complex queries, many entities GraphQL Client-driven queries, no over/under-fetch
High-throughput microservices gRPC Binary, streaming, strong typing
Full-stack TypeScript tRPC End-to-end type safety, zero boilerplate
Server push, live updates WebSocket Bidirectional, persistent connection
One-way server push SSE Simple, HTTP-based, auto-reconnect
Event-driven, decoupled Message Queue Async, resilient, scalable

Decision Tree

Is it a public API?
├── Yes → REST (with OpenAPI spec)
└── No
    ├── TypeScript monorepo?
    │   └── Yes → tRPC
    └── No
        ├── Need real-time push?
        │   ├── Bidirectional → WebSocket
        │   └── Server → Client only → SSE
        └── No
            ├── Microservices internal?
            │   └── gRPC with Protobuf
            └── Complex nested queries?
                └── GraphQL

Read the full file on GitHub · 167 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. 2d ago First seen · 167 lines · 103 tokens per session scan A fdb69e73997a

Subscribe to this mod's changes

protocol-architect is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,392 once invoked, about $0.0005 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 2026-09-03.