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/sukirman1901/frontend-expertWrote 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/sukirman1901/frontend-expert/design-system-enforcer)<a href="https://agentmods.dev/rules/sukirman1901/frontend-expert/design-system-enforcer"><img src="https://agentmods.dev/badge/rules/sukirman1901/frontend-expert/design-system-enforcer.svg" alt="Measured on agentmods" 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 | $0.01092 | $0.01092 |
| Opus 5 | $0.00546 | $0.00546 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
design-system-enforcer 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Expert (auto)
Users should not need slash commands. Map natural language to skills yourself. Pillars: docs/pillars.md.
Intent → load (mandatory)
| User intent (examples) | Load skills in order |
|---|---|
| Build/change UI, page, screen, component, layout, styling | frontend-judgment (if non-trivial) → design-tokens → (+ marketing-landing if landing) → ui-components → responsive-ui → motion (light) → anti-ai-slop → ui-feel → accessibility |
| + form / validasi | above + forms-validation |
| + API list/detail / async data | above + data-fetching |
| + shell / sidebar / routing | above + app-shell-routing |
| + architecture / folder / state | + fe-architecture |
| + SEO / meta / OG | + fe-seo |
| Mobile / responsive / semua device | responsive-ui MUST |
| Marketing landing / homepage / logo cloud / testimonials | + marketing-landing (section stack hand-roll — not @tailark/block registry) → motion → fe-seo as needed |
| Animation / transition / motion / marquee / parallax / text reveal | above + motion (families/patterns in motion-families.md; hand-roll — not registry default) |
| Match Figma / mock / pixel perfect / fidelity | design-fidelity → design-tokens → responsive-ui → ui-feel |
| Lighthouse / axe / DevTools / measured scores | fe-devtools → accessibility → web-performance |
| Hierarchy / unclear primary / competing CTAs | frontend-judgment Hierarchy pass → anti-ai-slop → ui-feel |
| Typography / type scale / multi-h1 | frontend-judgment Typography ladder → ui-feel |
| Figma Auto Layout / Fill / Hug | responsive-ui (Auto Layout ↔ CSS) |
| Feels off / rapihin detail / micro polish | ui-feel (+ anti-ai-slop if generik) — one pass |
| Design audit, AI slop, "UI jelek/generik", visual review | anti-ai-slop → ui-feel → design-tokens → responsive-ui → accessibility → web-performance (+ marketing-landing if landing) |
| Tests / TDD / coverage / regresi UI | frontend-testing → ui-components → accessibility |
| Polish / rapihin sampai bagus / until audit passes | ui-quality-loop (max 3) |
| Slow UI / LCP / optimize performance | web-performance |
| WebGL / shader / Plasma / animated canvas background | webgl required |
| Sentry / analytics / observability | monitoring |
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.
- 7d ago First seen · 55 lines · 1,092 tokens per session scan A d24a9e68bab3
design-system-enforcer is a cursor rule published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed 4d ago), licensed MIT. It adds 1,092 tokens to every session, about $0.0055 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.
Other cursor rules, from other repositories
codex-premium-website-skills
Apply Codex Skills standards to frontend, website, motion, accessibility, QA, agent reasoning, and handoff work.
react-prefer-shadcn-components
Preferir componentes shadcn/ui sobre alternativas custom o de terceros.
modal
A rule describing the inputs for a modal dialog component, which is a pop-up window. It specifies the title, HTML content, optional actions, open state, and supported sizes.
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.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.