agentmods.dev

tasarim-denetcisi

tasarim-denetcisi is a cursor rule for Cursor from muhammedsevimli/sistemler. It costs 567 tokens per session, scanned A, original, MIT.

A design-audit rule that evaluates a webpage from a screenshot across eight areas, such as typography, spacing, contrast, buttons, alignment, and image consistency. It measures visible problems instead of redesigning the page.

In plain words
What is it for?
Use it to review a page screenshot and report what is wrong, what the target should be, and why the difference matters. The report follows a fixed order and notes approximate pixel values when relevant.
Why use it?
It gives a structured explanation of why a page may look inexpensive or inconsistent. It also separates observable measurements from things that cannot be judged from one screenshot.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

not rated 2repo 1mo ago A scan 567 tokens original MIT

Good fit Use it to review a page screenshot and report what is wrong, what the target should be, and why the difference matters. The report follows a fixed order and notes approximate pixel values when relevant.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/muhammedsevimli/sistemler/tasarim-denetcisi
View source ↗ muhammedsevimli/sistemler
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.

Clone the repo
git clone --depth 1 https://github.com/muhammedsevimli/sistemler

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 tasarim-denetcisi

README.md
[![agentmods](https://agentmods.dev/badge/rules/muhammedsevimli/sistemler/tasarim-denetcisi/github.svg)](https://agentmods.dev/rules/muhammedsevimli/sistemler/tasarim-denetcisi)
Your own site
<a href="https://agentmods.dev/rules/muhammedsevimli/sistemler/tasarim-denetcisi"><img src="https://agentmods.dev/badge/rules/muhammedsevimli/sistemler/tasarim-denetcisi/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.

agentmods 80×15 button for tasarim-denetcisi

Your own site · 80×15
<a href="https://agentmods.dev/rules/muhammedsevimli/sistemler/tasarim-denetcisi"><img src="https://agentmods.dev/badge/rules/muhammedsevimli/sistemler/tasarim-denetcisi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 567 This file is loaded in full into every session.
When invoked 567 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00567 $0.00567
Opus 5 $0.00283 $0.00283
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 10d ago against content hash 50150590e22f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tasarim-denetcisi 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 10d 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.

tasarim-denetcisi/.cursor/rules/tasarim-denetcisi.mdc · 45 lines

What it actually says

Tasarım Denetçisi · Otomatik Okuma Kuralı

Bu klasörde çalışırken bu kural her zaman geçerlidir. Aynı kuralın tamamı CLAUDE.md ve AGENTS.md dosyalarında.

Amaç: kullanıcının kurduğu sayfanın neden ucuz göründüğünü ölçmek. Girdi tek bir ekran görüntüsüdür, kod dosyası istenmez.

Duruş (değişmez)

Sayfa yeniden tasarlanmaz. Neyin yanlış olduğu ölçülür, neden yanlış olduğu söylenir, nasıl düzeltileceği yazılır. Karar kullanıcınındır.

Denetim istendiğinde sırayla oku

  1. sen/01-marka.md
  2. format/olcutler.md
  3. format/rapor-format.md
  4. ekranlar/ klasöründeki tüm görüntüler

Okumadan üretme. Önce "marka + ölçütler + format + ekranlar okundu" de.

Sekiz başlık (sırası sabit)

  1. Yazı hiyerarşisi
  2. Satır uzunluğu ve satır aralığı
  3. Boşluk ritmi
  4. Renk ve kontrast
  5. Gölge, kenarlık ve köşe yarıçapı
  6. Buton ve tıklanabilir öğeler
  7. Hizalama ve ızgara
  8. Görsel ve ikon tutarlılığı

Her başlıkta üç satır: şu an ne, olması gereken ne, neden. Sekizini de geç, sorun yoksa "temiz" yaz.

Değişmez kurallar

  • Ölçmediğini yazma, "bu görüntüden ölçülemez" bölümüne koy.
  • Piksel değerleri yaklaşıktır, öyle işaretle.
  • Beğeni bildirme, her cümle bir ölçüme dayanır.
  • Metni, bölüm sırasını, konsepti değiştirmeyi önerme.
  • Marka rengine ve yazı tipine dokunma (sen/01-marka.md doluysa).
  • Em dash kullanma.

Çıktı

ciktilar/YYYY-AA-GG-<sayfa-adi>-denetim.md. Bölümler: envanter, sekiz başlık tablosu, önem sırasına dizili bulgular, yapıştırılabilir düzeltme talimatı, ölçülemeyenler.

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. 10d ago First seen · 45 lines · 567 tokens per session scan A 50150590e22f

Subscribe to this mod's changes

tasarim-denetcisi is a cursor rule published in the GitHub repository muhammedsevimli/sistemler (2 stars, last pushed 1mo ago), licensed MIT. It adds 567 tokens to every session, about $0.0028 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 2026-08-31.

Design and UX
Related

Other cursor rules, from other repositories

prototype-previewer

Build interactive prototype reviewers with synced review notes and Figma capture pages.

chocpink123/prototype-previewer-skill · 14 tokens

figma-performance

Handling large documents efficiently in the Plugin API.

hoshikitsunoda/figma-plugins-vibe-coding-template · 0 tokens

ant-design

A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.

TideTree/awesome-cursor-rules-mdc-zh · 0 tokens

7-day-nextjs-web-design-cursor

A seven-day design workflow for web products that will be built in Next.js.

mattcsnyder/7-day-mobile-and-web-design-skill · 16 tokens

clone-ai

Site Clone AI — website klonlama pipeline kuralları.

Omerfaruk-aydn/sitecloner · 374 tokens

mermaid

Diagram Creator. Load when the user requests "Create a diagram".

johnlindquist/rules · 13 tokens