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/mckaywrigley/o1-pro-template-systemWrote 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/mckaywrigley/o1-pro-template-system/backend)<a href="https://agentmods.dev/rules/mckaywrigley/o1-pro-template-system/backend"><img src="https://agentmods.dev/badge/rules/mckaywrigley/o1-pro-template-system/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/mckaywrigley/o1-pro-template-system/backend"><img src="https://agentmods.dev/badge/rules/mckaywrigley/o1-pro-template-system/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 | $0.01699 |
| Opus 5.5 | $0.00004 | $0.00680 |
| Sonnet 5.5 | $0.00002 | $0.00340 |
| Haiku 4.5 | $0.00001 | $0.00170 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Rules
Follow these rules when working on the backend.
It uses Postgres, Supabase, Drizzle ORM, and Server Actions.
General Rules
- Never generate migrations. You do not have to do anything in the
db/migrationsfolder inluding migrations and metadata. Ignore it.
Organization
Schemas
- When importing schemas, use
@/db/schema - Name files like
example-schema.ts - All schemas should go in
db/schema - Make sure to export the schema in
db/schema/index.ts - Make sure to add the schema to the
schemaobject indb/db.ts - If using a userId, always use
userId: text("user_id").notNull() - Always include createdAt and updatedAt columns in all tables
- Make sure to cascade delete when necessary
- Use enums for columns that have a limited set of possible values such as:
import { pgEnum } from "drizzle-orm/pg-core"
export const membershipEnum = pgEnum("membership", ["free", "pro"])
membership: membershipEnum("membership").notNull().default("free")
Example of a schema:
db/schema/todos-schema.ts
import { boolean, pgTable, text, timestamp, uuid } from "drizzle-orm/pg-core"
export const todosTable = pgTable("todos", {
id: uuid("id").defaultRandom().primaryKey(),
userId: text("user_id").notNull(),
content: text("content").notNull(),
completed: boolean("completed").default(false).notNull(),
createdAt: timestamp("created_at").defaultNow().notNull(),
updatedAt: timestamp("updated_at")
.defaultNow()
.notNull()
.$onUpdate(() => new Date())
})
export type InsertTodo = typeof todosTable.$inferInsert
export type SelectTodo = typeof todosTable.$inferSelect
And exporting it:
db/schema/index.ts
export * from "./todos-schema"
And adding it to the schema in db/db.ts:
db/db.ts
import { todosTable } from "@/db/schema"
const schema = {
todos: todosTable
}
And a more complex schema:
import { pgTable, text, timestamp, uuid } from "drizzle-orm/pg-core"
export const chatsTable = pgTable("chats", {
id: uuid("id").defaultRandom().primaryKey(),
userId: text("user_id").notNull(),
name: text("name").notNull(),
createdAt: timestamp("created_at").defaultNow().notNull(),
updatedAt: timestamp("updated_at")
.defaultNow()
.notNull()
.$onUpdate(() => new Date())
})
export type InsertChat = typeof chatsTable.$inferInsert
export type SelectChat = typeof chatsTable.$inferSelect
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.
- yesterday First seen · 248 lines · 9 tokens per session scan A 3e8a424edccc
backend is a cursor rule published in the GitHub repository mckaywrigley/o1-pro-template-system (142 stars, last pushed 1y ago), licensed MIT. It adds 9 tokens to every session and 1,699 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 2026-10-14.
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.
windsurfrules
Node.js ESM + EloquentJS ORM + PostgreSQL/MongoDB + Express/Fastify.
background-work
Background work on the backend, cron jobs in the scheduler vs tasks in the Postgres queue, transactional enqueue, retries, idempotent handlers.
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.