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/MN-Lizard-Team/aiyu-multi-agentnpx agentmods add rules/mn-lizard-team/aiyu-multi-agent/architectureWrote 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/mn-lizard-team/aiyu-multi-agent/architecture)<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/architecture"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/architecture.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 | $0.02339 | $0.02339 |
| Opus 5 | $0.01170 | $0.01170 |
| Sonnet 5 | $0.00468 | $0.00468 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
architecture 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.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aiyu Agent Kit Architecture
Comprehensive AI Agent Capability Expansion Toolkit
📋 Overview
Aiyu Agent Kit is a modular system consisting of:
- 20 Specialist Agents - Role-based AI personas
- 36 Skills - Domain-specific knowledge modules
- 11 Workflows - Slash command procedures
🏗️ Directory Structure
.windsurf/
├── ARCHITECTURE.md # This file
├── agents/ # 20 Specialist Agents
├── skills/ # 36 Skills
├── workflows/ # 11 Slash Commands
├── rules/ # Global Rules
└── scripts/ # Master Validation Scripts
🤖 Agents (20)
Specialist AI personas for different domains.
| Agent | Focus | Skills Used |
|---|---|---|
orchestrator |
Multi-agent coordination | parallel-agents, behavioral-modes |
project-planner |
Discovery, task planning | brainstorming, plan-writing, architecture |
frontend-specialist |
Web UI/UX | frontend-design, react-best-practices, tailwind-patterns |
backend-specialist |
API, business logic | api-patterns, nodejs-best-practices, database-design |
database-architect |
Schema, SQL | database-design, prisma-expert |
mobile-developer |
iOS, Android, RN | mobile-design |
game-developer |
Game logic, mechanics | game-development |
devops-engineer |
CI/CD, Docker | deployment-procedures, docker-expert |
security-auditor |
Security compliance | vulnerability-scanner, red-team-tactics |
penetration-tester |
Offensive security | red-team-tactics |
test-engineer |
Testing strategies | testing-patterns, tdd-workflow, webapp-testing |
debugger |
Root cause analysis | systematic-debugging |
performance-optimizer |
Speed, Web Vitals | performance-profiling |
seo-specialist |
Ranking, visibility | seo-fundamentals, geo-fundamentals |
documentation-writer |
Manuals, docs | documentation-templates |
product-manager |
Requirements, user stories | plan-writing, brainstorming |
product-owner |
Strategy, backlog, MVP | plan-writing, brainstorming |
qa-automation-engineer |
E2E testing, CI pipelines | webapp-testing, testing-patterns |
code-archaeologist |
Legacy code, refactoring | clean-code, code-review-checklist |
explorer-agent |
Codebase analysis | - |
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.
- 3d ago First seen · 293 lines · 2,339 tokens per session scan A df960b6c1692
architecture 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 2,339 tokens to every session, about $0.0117 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.
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.