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/andr-ca/agentharness/clean-architecturegit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00032 | $0.01008 |
| Opus 5 | $0.00016 | $0.00504 |
| Sonnet 5 | $0.00006 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
clean-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 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Architecture (Hexagonal / Ports & Adapters)
Core rule: business logic must not depend on infrastructure. Infrastructure depends on business logic.
┌─────────────────────────────────────────┐
│ Infrastructure │
│ (HTTP, DB, Queue, Email, S3, ...) │
│ │
│ ┌───────────────────────────┐ │
│ │ Application Layer │ │
│ │ (Use cases, Commands) │ │
│ │ │ │
│ │ ┌─────────────────┐ │ │
│ │ │ Domain Layer │ │ │
│ │ │ (Entities, │ │ │
│ │ │ Value Objects, │ │ │
│ │ │ Domain Events) │ │ │
│ │ └─────────────────┘ │ │
│ └───────────────────────────┘ │
└─────────────────────────────────────────┘
Dependencies only point INWARD →
Layers
Domain (innermost)
- Entities: objects with identity and lifecycle (
Order,User) - Value Objects: immutable, defined by value (
Money,Email) - Domain Events: things that happened (
OrderPlaced,PaymentFailed) - Domain Services: stateless logic that spans entities
- Zero infrastructure imports — no SQLAlchemy, FastAPI, Stripe, etc.
Application
- Use cases / handlers: orchestrate domain objects
- Input/output ports (interfaces): what the use case needs from outside
- No infrastructure imports — depends only on domain + port interfaces
Infrastructure (outermost)
- Adapters that implement ports:
SqlUserRepository,StripePaymentGateway - Framework glue: FastAPI routes, Django views, Express controllers
- Depends on application layer — adapters implement domain/application interfaces
Ports & Adapters
A port is an interface defined in the domain/application layer. An adapter is an infrastructure class that implements a port.
# Port (in application/domain layer)
class UserRepository(Protocol):
def find_by_id(self, id: UserId) -> User | None: ...
def save(self, user: User) -> None: ...
# Adapter (in infrastructure layer)
class SqlUserRepository:
def __init__(self, session: Session) -> None:
self._session = session
def find_by_id(self, id: UserId) -> User | None:
return self._session.get(UserModel, id.value)
def save(self, user: User) -> None:
self._session.merge(UserModel.from_domain(user))
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.
- 2d ago First seen · 113 lines · 32 tokens per session scan A 52e830bc4816
clean-architecture is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,008 once invoked, about $0.0002 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.
Other cursor rules, from other repositories
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
cursorrules
This repo has a GraphPilot structural code-graph available via MCP. Use it before grep on structural questions.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.