Borrowing it
Nothing to install: this file belongs to Kerim-Sabic/elite-engineer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kerim-Sabic/elite-engineer/main/.cursorrulesgit clone --depth 1 https://github.com/Kerim-Sabic/elite-engineerWrote 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/kerim-sabic/elite-engineer/cursorrules)<a href="https://agentmods.dev/rules/kerim-sabic/elite-engineer/cursorrules"><img src="https://agentmods.dev/badge/rules/kerim-sabic/elite-engineer/cursorrules/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/kerim-sabic/elite-engineer/cursorrules"><img src="https://agentmods.dev/badge/rules/kerim-sabic/elite-engineer/cursorrules.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 | $0.02899 | $0.02899 |
| Opus 5.5 | $0.01160 | $0.01160 |
| Sonnet 5.5 | $0.00580 | $0.00580 |
| Haiku 4.5 | $0.00290 | $0.00290 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elite Engineer — Cursor Rules
The operating system for elite software engineering in TypeScript, React, and Next.js.
Every principle traces to a named source. Every directive is actionable.
THE STANDARD
Code exhibits taste — Torvalds' term for finding the formulation where special cases disappear. Seek representations where edge cases become impossible, the type system proves correctness, and the API guides users into the pit of success.
Five commitments:
- Carmack's vigilance — Make state visible. Prefer straightline execution. Distrust abstraction that hides what's happening.
- Hickey's discipline — Simple ≠ easy. Simple means "one fold" (does one thing). Easy means "nearby" (familiar). Choose simple.
- Brooks' realism — Most complexity is essential (domain-inherent), not accidental (tool-introduced). Model the domain correctly first.
- Metz's patience — "Duplication is far cheaper than the wrong abstraction." Start with Shameless Green. Abstract only with 3+ concrete instances.
- Ousterhout's strategy — Tactical programmers optimize for the next feature. Strategic programmers optimize for great design. Invest 10-20% in design improvements.
BEFORE THE FIRST LINE
Answer before writing code:
- What is the essential complexity? (Brooks) — What's inherent to the domain?
- Where are the boundaries? (Evans) — Use domain vocabulary for all names.
- What is the pit of success? (Mariani) — Make correct usage easier than incorrect.
- Is this the simplest solution? (Hickey) — Fewest moving parts, fewest ways to misuse.
- Should I abstract? (Metz) — Only with 3+ instances. Otherwise, duplicate.
ARCHITECTURE LAWS
Deep Modules Win (Ousterhout)
A module's value = functionality provided minus interface complexity. useAuth() returning
{ user, login, logout, isLoading } while hiding token management is deep. A hook
requiring callers to manage tokens and headers is shallow.
Define Errors Out of Existence (Ousterhout)
deleteItem(id) succeeds whether the item exists or not — postcondition satisfied either way.
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 · 269 lines · 2,899 tokens per session scan A 8897168f1ed8
cursorrules is a cursor rule published in the GitHub repository Kerim-Sabic/elite-engineer (5 stars, last pushed 6mo ago), licensed MIT. It adds 2,899 tokens to every session, about $0.0116 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 2026-08-31.
Other cursor rules, from other repositories
20-frontend-nextjs
Next.js frontend rules.
component-development
Modern React + TypeScript component patterns — hooks, typed props, performance optimization, forms, and testing.
10-backend-fastapi
FastAPI backend rules.
angular
Angular: signals, standalone components, RxJS patterns.
typescript
Strict TypeScript: generics, discriminated unions, no any.
bun
Bun runtime: Bun.serve, Bun.file, bundler, test runner.