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/materialize-labs/ai-optimized-starter-appWrote 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/materialize-labs/ai-optimized-starter-app/backend)<a href="https://agentmods.dev/rules/materialize-labs/ai-optimized-starter-app/backend"><img src="https://agentmods.dev/badge/rules/materialize-labs/ai-optimized-starter-app/backend/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/materialize-labs/ai-optimized-starter-app/backend"><img src="https://agentmods.dev/badge/rules/materialize-labs/ai-optimized-starter-app/backend.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 | $0.00009 | $0.02619 |
| Opus 5.5 | $0.00004 | $0.01048 |
| Sonnet 5.5 | $0.00002 | $0.00524 |
| Haiku 4.5 | $0.00001 | $0.00262 |
Grade A, and why
backend 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 2mo 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 — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Architecture Guidelines
This document outlines our backend architecture and coding standards. Our backend stack includes:
- Database: PostgreSQL via Supabase
- ORM: Drizzle for type-safe database access
- API Layer: Next.js Server Actions
- Infrastructure: Serverless via Vercel
Core Principles
- Type Safety: Maintain full type safety between database and application code
- Scalability: Design for scale from the beginning
- Maintainability: Follow consistent patterns across the codebase
- Security: Validate all inputs and handle user permissions properly
- Performance: Optimize database queries and API responses
Database Schema Design
Directory Structure
db/
├── db.ts # Main database configuration
├── index.ts # Public exports
├── migrations/ # Database migrations
└── schema/ # Database schema definitions
├── [entity].ts # Individual entity schemas
Schema Definition Standards
Naming Conventions
- Use kebab-case for files:
contacts.ts - Use camelCase for table and column names in code
- Use snake_case for the actual database column names
- Export types with standardized prefixes:
Select[Entity]andInsert[Entity]
Required Fields
All tables should include these standard fields:
{
// Always use UUID for primary keys
id: uuid("id").defaultRandom().primaryKey(),
// User association (when applicable)
userId: text("user_id").notNull(),
// Timestamps
createdAt: timestamp("created_at", { withTimezone: true }).defaultNow().notNull(),
updatedAt: timestamp("updated_at", { withTimezone: true })
.defaultNow()
.notNull()
.$onUpdate(() => new Date())
}
Using Enums
For fields with a fixed set of values, use PostgreSQL enums:
import { pgEnum } from "drizzle-orm/pg-core"
// Define the enum
export const statusEnum = pgEnum("status", ["active", "pending", "archived"])
// Use it in your schema
status: statusEnum("status").notNull().default("pending")
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.
- 2mo ago First seen · 435 lines · 9 tokens per session scan A a7f2697e27aa
backend is a cursor rule published in the GitHub repository materialize-labs/ai-optimized-starter-app (16 stars, last pushed 1y ago), licensed MIT. It adds 9 tokens to every session and 2,619 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other cursor rules, from other repositories
sql-queries-not-asts
Name built-and-lowered SQL units "queries", not "asts".
supabase
Do not use the Supabase Client, instead use the Jawn Client and put all new endpoints in controllers. Don't use RLS policies, instead enable RLS for new tables and revoke privledges. Example.
java-springboot-jpa-cursorrules-prompt-file
Cursor rules for Java development with Springboot and JPA integration.
vibes-plug-backend
Vibes-Plug Backend & Systems Engineering — Node 24, Bun 1.2, Hono, Fastify, Prisma 6, Drizzle, PostgreSQL DDL with RLS, and RFC 9457 errors.
windsurfrules
Node.js ESM + EloquentJS ORM + PostgreSQL/MongoDB + Express/Fastify.
fastapi-database-interaction
A set of rules for connecting FastAPI, a Python framework for building web APIs, to databases using asynchronous libraries such as asyncpg or aiomysql and SQLAlchemy 2.0.