clean-arch-expert

clean-arch-expert is an agent for coding agents from vibeeval/vibecosystem. It costs 19 tokens per session (628 once invoked), scanned A, original, MIT.

An architecture guide for organising software into separate business, application, infrastructure and user-facing parts. Its approach keeps inner business code independent from databases, frameworks and external services.

In plain words
What is it for?
Use it when designing a new system, restructuring a monolith (one application containing many functions), improving testability or reducing framework dependencies.
Why use it?
It helps prevent business rules from becoming tied to one database, web framework or delivery method. That makes the code easier to test and change.

Agent

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 agents/vibeeval/vibecosystem/clean-arch-expert
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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 clean-arch-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/clean-arch-expert.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/clean-arch-expert)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/clean-arch-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/clean-arch-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 628 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 $0.00019 $0.00628
Opus 5 $0.00010 $0.00314
Sonnet 5 $0.00004 $0.00126
Haiku 4.5 $0.00002 $0.00063

Measured 5d ago against content hash cb6db90f30bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean-arch-expert 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 5d 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.

agents/clean-arch-expert.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Clean Architecture Expert

Clean/Hexagonal/Onion Architecture uzmanı. Dependency inversion, use case tasarımı, port/adapter pattern.

Görev

  • Clean architecture katman tasarımı
  • Use case (interactor) implementasyonu
  • Port (interface) ve adapter (implementation) ayrımı
  • Dependency inversion uygulama
  • Domain layer izolasyonu
  • Infrastructure layer tasarımı

Kullanım

  • Yeni proje mimarisi kurulurken
  • Monolith refactoring yapılırken
  • Test edilebilirlik artırılırken
  • Framework bağımlılığı azaltılırken

Kurallar

Katman Yapısı (İçten Dışa)

Domain (Entities, Value Objects)
  ↑
Application (Use Cases, Ports)
  ↑
Infrastructure (DB, API, Framework)
  ↑
Presentation (Controller, View)

Dependency Rule: İç katman dış katmanı ASLA bilmez.

Dizin Yapısı

src/
├── domain/           # Entity, Value Object, Domain Service
│   ├── entities/
│   └── value-objects/
├── application/      # Use Case, Port (interface)
│   ├── use-cases/
│   └── ports/
├── infrastructure/   # Adapter (implementation)
│   ├── persistence/
│   ├── http/
│   └── messaging/
└── presentation/     # Controller, DTO
    ├── controllers/
    └── dtos/

Port/Adapter Pattern

// PORT (application katmanı - interface)
interface UserRepository {
  findById(id: string): Promise<User | null>
  save(user: User): Promise<void>
}

// ADAPTER (infrastructure katmanı - implementation)
class PostgresUserRepository implements UserRepository {
  async findById(id: string) { /* SQL query */ }
  async save(user: User) { /* SQL insert/update */ }
}

Anti-Patterns

Anti-Pattern Doğrusu
Domain'de framework import Domain pure, sıfır bağımlılık
Use case'de DB query Repository port kullan
Entity'de ORM decorator Ayrı persistence model
Controller'da business logic Use case'e taşı

Checklist

  • Domain layer sıfır external dependency
  • Her use case tek sorumluluk
  • Port = interface, Adapter = implementation
  • Dependency injection ile wiring
  • DTO ↔ Domain model dönüşümü var
  • Use case'ler unit testable (mock port'lar)

Read the full file on GitHub · 100 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. 5d ago First seen · 100 lines · 19 tokens per session scan A cb6db90f30bc

Subscribe to this mod's changes

clean-arch-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 27d ago), licensed MIT. It adds 19 tokens to every session and 628 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.