engineering-architecture

engineering-architecture is a cursor rule for coding agents from adonai-labs/agent-runway. It costs 870 tokens per session, scanned A, original, MIT.

A set of general principles for designing software structure, independent of any particular programming language or framework. It guides decisions about modules, dependencies, boundaries, and interfaces.

In plain words
What is it for?
Use it when designing or reviewing architecture, choosing patterns, defining system boundaries, or planning how software should change over time.
Why use it?
It helps avoid unnecessary layers and abstractions while keeping business rules independent from infrastructure and vendor details.

Cursor rule

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/adonai-labs/agent-runway/engineering-architecture
Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway

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 engineering-architecture

README.md
[![agentmods](https://agentmods.dev/badge/rules/adonai-labs/agent-runway/engineering-architecture.svg)](https://agentmods.dev/rules/adonai-labs/agent-runway/engineering-architecture)
Your own site
<a href="https://agentmods.dev/rules/adonai-labs/agent-runway/engineering-architecture"><img src="https://agentmods.dev/badge/rules/adonai-labs/agent-runway/engineering-architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 870 This file is loaded in full into every session.
When invoked 870 The same file — it is already loaded in full.
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 $0.00870 $0.00870
Opus 5 $0.00435 $0.00435
Sonnet 5 $0.00174 $0.00174
Haiku 4.5 $0.00087 $0.00087

Measured 5d ago against content hash 93592e8bb5f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

engineering-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 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.

src/core/rules/engineering-architecture.mdc · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Architecture

Universal architecture principles applied when making structural decisions, reviewing proposals, or designing systems.


Complexity must be proportionate to the problem

  • Introduce a pattern, layer, or abstraction only when the problem forces it
  • Patterns chosen by reputation rather than fit create accidental complexity
  • If the architecture is harder to explain than the problem, the design is probably wrong

Dependencies should point toward policy, not detail

  • High-level business policy should not depend on infrastructure, framework, or transport
  • Dependencies should be inward: outer layers depend on inner layers; inner layers have no knowledge of outer layers
  • Framework and vendor types belong at the edges; they should not shape the core model

Boundaries reflect different reasons to change

  • A module, service, or bounded context boundary is only useful when it separates concerns that change for different reasons
  • If two things always change together, keep them together
  • If two things change independently, separate them

Contracts are stable interfaces for consumers

  • Public APIs are contracts designed for consumers, not exposures of internal implementation
  • Prefer additive changes over breaking changes
  • Do not leak internal models, persistence fields, or domain details to external consumers
  • Version only when the resource concept changes meaningfully

Architecture should express the domain

  • Folder and module structure should communicate what the system does, not what framework it uses
  • Names should reflect domain capabilities: Orders/, Payments/, not Controllers/, Services/
  • A new developer should understand the system's purpose from its structure

Testability is structural, not incidental

  • If important behaviour cannot be tested without infrastructure, it is in the wrong place
  • Each important layer should be independently testable
  • Prefer pure functions and injectable ports for business-critical logic

Read the full file on GitHub · 119 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 · 119 lines · 870 tokens per session scan A 93592e8bb5f2

Subscribe to this mod's changes

engineering-architecture is a cursor rule published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 15d ago), licensed MIT. It adds 870 tokens to every session, about $0.0043 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.