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/nikandr-surkov/ai-saas-starterWrote 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/nikandr-surkov/ai-saas-starter/core)<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/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/nikandr-surkov/ai-saas-starter/core"><img src="https://agentmods.dev/badge/rules/nikandr-surkov/ai-saas-starter/core.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 | $0.00258 | $0.00258 |
| Opus 5.5 | $0.00103 | $0.00103 |
| Sonnet 5.5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
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 1mo 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.
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 testpass; 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/deletecredit_transactionsrows; touch credit tables outsidesrc/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.
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.
- 1mo ago First seen · 25 lines · 258 tokens per session scan A 49ff983a1560
core is a cursor rule published in the GitHub repository nikandr-surkov/ai-saas-starter (24 stars, last pushed 2mo ago), licensed MIT. It adds 258 tokens to every session, about $0.0010 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
skill-creator
Create, edit, evaluate, and debug the skills in this repo, including running their evals and fixing a description that fails to trigger. Use when user says 'help me build a new skill', 'add a skill for X', 'run the evals for the tf skill', 'run the behavioral evals', 'my skill is not triggering', 'fix this skill's…
file-organization
Project file and folder organization patterns.
skill-router
Use before starting any task in Cursor to check whether a skill file must be read first. Routes PRD, test-writing and code-verification tasks to the skill path to read before writing code.
tf-plan
Review a Terraform plan before applying it: destroys and replacements of data-bearing resources, secrets readable in plan output, out-of-band drift, blast radius, and whether the apply is bound to the plan you actually reviewed. Use when user says 'review my plan', 'is this plan safe to apply', 'check tfplan', 'what…
orchestrator-main
Rules for the main orchestrator agent in multi-agent workflows.
task
Task execution rules for Glitch Payment Gateway engineering work — verification gates, plan node, self-improvement loop.