cursorrules

Project-specific rules for Urule, an open-source coordination system for AI agents, built with TypeScript, Fastify, PostgreSQL, NATS, Next.js, and related tools.

In plain words
What is it for?
Use it whenever you add or change Urule routes, services, database code, events, tests, or frontend code.
Why use it?
It keeps new code aligned with the project's required IDs, validation, errors, logging, service boundaries, tests, and commit format.

Cursor rule for Cursor

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/urule-ai/urule/cursorrules
Clone the repo
git clone --depth 1 https://github.com/urule-ai/urule

Made for: Cursor.

Per session 315 This file is loaded in full into every session.
When invoked 315 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 $0.00315 $0.00315
Opus 5 $0.00158 $0.00158
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash 49a6cb431ff7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 22 lines

What it actually says

You are working on Urule, the open-source coordination layer for AI agents.

Tech stack: TypeScript ESM, Fastify 5, Drizzle ORM, PostgreSQL 16, NATS, Vitest, Next.js 14, React 18, Tailwind CSS, Zustand.

Rules:

  • Always use ESM imports with .js extension for local files
  • Use ULID (not UUID) for all IDs: import { ulid } from 'ulid'
  • Use Zod for all request body validation with safeParse()
  • Return 400 with { error: 'Validation failed', details: parsed.error.issues } on validation failure
  • Return 404 with { error: { code: 'ENTITY_NOT_FOUND', message } } for missing resources
  • TypeScript strict mode — never use any, use unknown with validation
  • Use Fastify app.inject() for route tests, never start a real server
  • Use request.log (Pino) for logging, never console.log in services
  • Each service has its own PostgreSQL schema — never cross-query
  • Services communicate via HTTP APIs and NATS events — never import between services
  • Follow Conventional Commits: feat:, fix:, docs:, test:, refactor:, chore:
  • Auth middleware uses skipAuth: true in tests
  • Public routes go in the publicRoutes array (healthz, /docs, webhooks)
  • All list endpoints support limit/offset pagination (max 100)

See CLAUDE.md for detailed patterns, recipes, and architecture.

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. yesterday First seen · 22 lines · 315 tokens per session scan A 49a6cb431ff7

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository urule-ai/urule (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 315 tokens to every session, about $0.0016 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.