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.
git clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/node-architecture)<a href="https://agentmods.dev/rules/adonai-labs/agent-runway/node-architecture"><img src="https://agentmods.dev/badge/rules/adonai-labs/agent-runway/node-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/adonai-labs/agent-runway/node-architecture"><img src="https://agentmods.dev/badge/rules/adonai-labs/agent-runway/node-architecture.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00589 |
| Opus 5 | $0.00000 | $0.00295 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
node-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 7d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Node.js Architecture Guidelines
Applied when working with Node.js service architecture. Australian English spelling throughout.
Project Structure
- Separate concerns into
domain/,application/,infrastructure/,api/, andshared/— dependency flow is always inward - Keep business rules (domain and application) independent of Express, Fastify, or any HTTP framework
- Centralise all
process.envaccess in a typed config module; validate at startup with Zod
Layer Rules
- Domain: no external dependencies; entities, value objects, port interfaces
- Application: depends on domain only; defines port interfaces infrastructure must implement
- Infrastructure: implements ports; contains DB adapters, queue clients, HTTP clients
- API: depends on application; maps HTTP to use cases and results to responses
- Shared: cross-cutting utilities; imports nothing from domain, application, or infrastructure
Multiple Entry Points (Hexagonal)
When a service has both HTTP and queue consumers, treat each as an independent adapter calling the same application use cases. The core (domain + application) never knows which adapter triggered it.
Config
- Use Zod to validate and type all environment variables at startup — fail fast on missing config
- Export a single typed
configobject; never readprocess.envdirectly outside the config module - Do not default-fill secrets; a missing secret at startup is safer than silent misconfiguration
Process Entry Point
- Compose the application from the outside in: validate config → create infrastructure → wire use cases → start server/workers → register shutdown handlers
- Handle
SIGTERMandSIGINTfor graceful shutdown - Exit with non-zero code on startup failure via an uncaught rejection handler on
main()
Module System
- Prefer ESM (
"type": "module") for new projects - Use
node:prefix for built-in imports — explicit and avoids naming conflicts - Avoid barrel
index.tsfiles in large codebases — they slow type-checking and break tree-shaking
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.
- 7d ago First seen · 68 lines · 0 tokens per session scan A 9e2c1f3809d5
node-architecture is a cursor rule published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 589 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 2026-09-03.
Other cursor rules, from other repositories
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.
cloudflare-email-telegram-cursorrules-prompt-file
Cursor rules for setting up email-to-Telegram forwarding via Cloudflare Email Routing and Workers using the mail2tg CLI.
sveltekit-typescript-guide-cursorrules-prompt-file
Cursor rules for SvelteKit development with TypeScript integration.
python
Python best practices and patterns for modern software development with Flask and SQLite.
react-query-cursorrules-prompt-file
Cursor rules for React development with React Query integration.
kotlin-springboot-rules
A set of coding rules for Kotlin applications built with Spring Boot, a Java-based framework for web services. It covers project layout, naming, Kotlin style, and common design patterns.