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.
npx agentmods add rules/jhl-labs/vibe-project/architecturegit clone --depth 1 https://github.com/jhl-labs/vibe-projectWrote 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/jhl-labs/vibe-project/architecture)<a href="https://agentmods.dev/rules/jhl-labs/vibe-project/architecture"><img src="https://agentmods.dev/badge/rules/jhl-labs/vibe-project/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 | $0.00000 | $0.00532 |
| Opus 5 | $0.00000 | $0.00266 |
| Sonnet 5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Architecture Rules
Layer Structure
src/
├── domain/ # Core business logic (PURE)
├── application/ # Use cases, orchestration
├── infrastructure/ # External services, DB
└── presentation/ # HTTP, API, UI
Dependency Rules (CRITICAL)
Presentation → Application → Domain
↓
Infrastructure
- Domain has NO external dependencies
- Application depends only on Domain
- Infrastructure implements Domain interfaces
- Presentation calls Application use cases
Domain Layer
// Entity - pure business logic
export class User {
private constructor(private props: UserProps) {}
static create(props: CreateUserProps): User {
// Validation and business rules
return new User({ ...props, id: generateId() });
}
// Business methods
deactivate(): User {
if (!this.isActive) throw new Error('Already inactive');
return new User({ ...this.props, status: 'inactive' });
}
}
// Repository interface (port)
export interface UserRepository {
findById(id: string): Promise<User | null>;
save(user: User): Promise<User>;
}
Application Layer
// Use case - orchestrates domain logic
export class CreateUserUseCase {
constructor(
private userRepo: UserRepository,
private emailService: EmailService,
) {}
async execute(input: CreateUserInput): Promise<CreateUserOutput> {
const user = User.create(input);
await this.userRepo.save(user);
await this.emailService.sendWelcome(user.email);
return { id: user.id };
}
}
Infrastructure Layer
// Repository implementation (adapter)
export class PrismaUserRepository implements UserRepository {
constructor(private prisma: PrismaClient) {}
async findById(id: string): Promise<User | null> {
const data = await this.prisma.user.findUnique({ where: { id } });
return data ? this.toDomain(data) : null;
}
}
Presentation Layer
// Controller/Route - thin, delegates to use case
router.post('/users', async (req, res) => {
const result = await createUserUseCase.execute(req.body);
res.status(201).json(result);
});
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.
- 4d ago First seen · 100 lines · 0 tokens per session scan A 85612c4b880f
architecture is a cursor rule published in the GitHub repository jhl-labs/vibe-project (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 532 tokens. 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.
Other cursor rules, from other repositories
architecture-for-apps
ArchiPy clean architecture for apps — layers, import direction, and base types.
config-and-di
ArchiPy BaseConfig, FastAPIConfig/uvicorn, and DI container wiring.
using-archipy-adapters
Using and writing adapters in ArchiPy apps — extras, ports, mocks, boundary errors.
using-archipy-utils
ArchiPy helpers/utils — pure utilities, AppUtils FastAPI/gRPC factories.
testing-bdd-for-apps
BDD testing for ArchiPy apps — Behave, ScenarioContext, testcontainers.
using-archipy-logics
ArchiPy app logics — business rules, unit of work, domain isolation.