core

core is a cursor rule for Cursor from nikandr-surkov/ai-saas-starter. It costs 258 tokens per session, scanned A, original, MIT.

A set of rules for developing this web application. They cover package commands, testing, server-side actions, authentication, data handling, database migrations, payment webhooks, secrets, and visual design.

In plain words
What is it for?
Use it as the baseline for every change in the repository, especially features involving authentication, payments, credits, database migrations, environment variables, or the user interface.
Why use it?
It gives developers fixed boundaries for making safe, consistent changes. The rules help prevent security problems, accidental data damage, and code that does not match the application’s conventions.

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/nikandr-surkov/ai-saas-starter/core
Clone the repo
git clone --depth 1 https://github.com/nikandr-surkov/ai-saas-starter

Made for: Cursor.

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 core

README.md
[![agentmods](https://agentmods.dev/badge/rules/nikandr-surkov/ai-saas-starter/core.svg)](https://agentmods.dev/rules/nikandr-surkov/ai-saas-starter/core)
Your own site
<a href="https://agentmods.dev/rules/nikandr-surkov/ai-saas-starter/core"><img src="https://agentmods.dev/badge/rules/nikandr-surkov/ai-saas-starter/core.svg" alt="Measured on agentmods" height="20"></a>
Per session 258 This file is loaded in full into every session.
When invoked 258 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 $0.00258 $0.00258
Opus 5 $0.00129 $0.00129
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured 3d ago against content hash 49ff983a1560, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core 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 3d 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.

.cursor/rules/core.mdc · 25 lines

What it actually says

Full manual: AGENTS.md at the repo root. The essentials:

  • pnpm only. Never npm or yarn.
  • Done = pnpm typecheck && pnpm lint && pnpm test pass; new features include tests.
  • Server Actions for mutations; API routes only for webhooks and the Better Auth handler. Server Components by default; "use client" only for interactivity.
  • Zod at every external boundary (forms, webhooks, env). Env is read only through src/lib/env.ts.
  • Re-check the session server-side in every action and (app) page — never trust middleware alone.
  • Money in integer cents; credits in integers.
  • NEVER: edit applied migrations in drizzle/; mutate/delete credit_transactions rows; touch credit tables outside src/lib/credits/; weaken Stripe webhook signature checks; log secrets; commit .env.
  • ASK FIRST: new dependencies, schema changes, plan/price changes.
  • UI follows DESIGN.md: 2px radius, no gradients/shadows/blur, ledger rows not card grids, accent green scarce, no emoji.
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. 3d ago First seen · 25 lines · 258 tokens per session scan A 49ff983a1560

Subscribe to this mod's changes

core is a cursor rule published in the GitHub repository nikandr-surkov/ai-saas-starter (15 stars, last pushed 1mo ago), licensed MIT. It adds 258 tokens to every session, about $0.0013 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 2026-08-30.