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/omergulcicek/omergulcicek.comWrote 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/omergulcicek/omergulcicek.com/ui)<a href="https://agentmods.dev/rules/omergulcicek/omergulcicek.com/ui"><img src="https://agentmods.dev/badge/rules/omergulcicek/omergulcicek.com/ui/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/omergulcicek/omergulcicek.com/ui"><img src="https://agentmods.dev/badge/rules/omergulcicek/omergulcicek.com/ui.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 | $0.00000 | $0.00618 |
| Opus 5.5 | $0.00000 | $0.00247 |
| Sonnet 5.5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
ui 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 4d 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.
This is a copy
89% identical to ui — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI
Components
components/ui: primitives without data or store access.components/shared: reused app components.features/<feature>/components: domain UI.- Add primitives with
pnpm dlx shadcn@latest add <component>; do not hand-write them. - Find the primitive library first:
styleincomponents.json(base-…orradix-…), elsepackage.json(@base-ui/reactor@radix-ui/*). Never mix them. - Merge classes with
cn()(@/lib/utils), never template strings. - Data-driven UI has loading (a skeleton of the final size), empty and error states.
- Animate with
motion/reactand respect reduced motion.
Tailwind CSS 4
- Theme tokens and the default scale only (
bg-background,p-4). No hex, rgb or arbitrary values likep-[13px]. - v4 class names:
bg-linear-to-rinstead ofbg-gradient-to-r,size-4instead ofw-4 h-4. - Mobile first from 320px; check every breakpoint up to
xl.
Accessibility
- Semantic HTML:
buttonfor actions, links for navigation, oneh1per page, no skipped heading levels. - Every control has a name: visible text, a
<label>, oraria-labelif nothing is visible. - Everything works by keyboard and focus is visible.
- Dialogs and menus use the primitive's focus handling, never a custom focus trap.
- Text contrast meets WCAG AA (4.5:1). Never show state with color alone.
- Meaningful
alttext;alt=""for decorative images.
Bans
onClickondivorspan.- The generic "AI look": indigo or purple defaults, gradients everywhere,
rounded-2xlon everything, identical card grids. Lorem ipsum.
type StatCardProps = { label: string; value: string; className?: string };
export function StatCard({ label, value, className }: StatCardProps) { return ( <section className={cn("rounded-lg border bg-card p-4 md:p-6", className)}> {label} {value} ); }
</example>
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.
- 4d ago First seen · 55 lines · 0 tokens per session scan A 5de91b535662
ui is a cursor rule published in the GitHub repository omergulcicek/omergulcicek.com (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 618 tokens. A static security scan graded it A with 0 findings. It is 89% identical to ui, differing in 3 lines, and is treated as a copy.
Other cursor rules, from other repositories
color-token-management
Comprehensive guide for adding, modifying, and managing color tokens in the @vibe/style package. Covers SCSS theme files, build process, naming conventions, and special handling for hacker theme.
chakra-ui-best-practices
A set of rules for building React interfaces with Chakra UI, a component library for styled and accessible user interfaces. It covers themes, responsive layouts, accessibility, performance, and reusable components.
nextjs-react-tailwind-cursorrules-prompt-file
Cursor rules for Next.js development with React and Tailwind CSS integration.
chakra-ui---responsive-design
Guidance for making Chakra UI layouts adapt to different screen sizes. It uses responsive style values, breakpoints, layout components, and conditional display rules for phones, tablets, and desktops.
react-components-creation-cursorrules-prompt-file
Cursor rules for React component creation and development.
react-chakra-ui-cursorrules-prompt-file
Cursor rules for React development with Chakra UI integration.