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.
npx skills add pekral/cursor-rules --skill frontend-design-directiongit clone --depth 1 https://github.com/pekral/cursor-rulesWrote 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/skills/pekral/cursor-rules/frontend-design-direction)<a href="https://agentmods.dev/skills/pekral/cursor-rules/frontend-design-direction"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/frontend-design-direction/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/skills/pekral/cursor-rules/frontend-design-direction"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/frontend-design-direction.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 | $0.00040 | $0.00997 |
| Opus 5.5 | $0.00016 | $0.00399 |
| Sonnet 5.5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
frontend-design-direction 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraints
- Apply
@rules/laravel/filament.mdc— for custom Blade + Tailwind, create and register a custom theme; use Heroicon, not raw icon strings. - Apply
@rules/laravel/livewire.mdc— keep Blade presentation-only; reuse existing Livewire/Blade patterns before inventing new ones. - Apply
@rules/security/frontend.mdonly if the direction introduces dynamic output, inline styles, or CSP-sensitive markup — sanitize before DOM insertion and prefer safe rendering. - Stack is Blade + Livewire + Alpine.js + Filament + Tailwind. No React/Vue/Next.
Use when
- The user asks to build a page, app, dashboard, component, landing page, or UI.
- The user asks to make an interface more polished, distinctive, or less generic.
- The work needs visual hierarchy, typography, color, motion, and layout decisions.
- The current UI works but reads as flat, templated, or mismatched to its audience.
This skill is about judgment, not mechanics. Pair it with design-system (tokens/audit), frontend-patterns (implementation), and frontend-a11y (accessibility).
Choose a direction before coding
Decide these five things explicitly first:
- Purpose — what job does this interface do?
- Audience — who repeats this workflow, and what must they scan first?
- Tone — name it: utilitarian, editorial, playful, industrial, refined, technical, maximal, minimal, dense, or calm.
- Memorable detail — one deliberate idea that makes the result feel intentional rather than generated.
- Constraints — framework, accessibility, performance, responsiveness, and the existing design system.
Match the direction to the domain. A SaaS operations tool — including most Filament panels — should usually be dense, quiet, and scannable. A portfolio, launch page, or editorial piece can be expressive. Do not force a marketing-landing composition onto a tool meant for repeated daily use.
Implementation guidance
- Build the actual usable experience as the first screen unless the user explicitly asks for marketing copy.
- Reuse what exists first — existing Blade components (
<x-…>), Tailwind design tokens, the Filament theme, Heroicon, and established Livewire patterns — before introducing a new visual system. New components should consume current tokens, not hard-coded values. - Use real or generated assets when the interface depends on images, charts, products, or inspectable media.
- Prefer contextual typography and spacing over generic oversized hero text.
- Keep palettes multi-dimensional — avoid a UI dominated by one hue family. Drive color from Tailwind tokens / CSS variables so the direction stays coherent across light/dark and component states.
- Design responsive constraints explicitly: grids, aspect ratios, min/max sizes, and stable toolbars should not shift when labels or hover states appear.
- Use motion sparingly and deliberately — prefer high-signal Alpine transitions and
wire:loadingfeedback that clarify state over decorative animation, and respectmotion-reduce:. - Verify text fit on mobile and desktop; long labels must wrap or resize, not overflow.
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 · 75 lines · 40 tokens per session scan A 78e8346b658f
frontend-design-direction is a skill published in the GitHub repository pekral/cursor-rules (11 stars, last pushed 19d ago), licensed MIT. It adds 40 tokens to every session and 997 once invoked, about $0.0002 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 skills, from other repositories
brand-landingpage
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established…
powergrid-theme
Create or update a PowerGrid v7 theme using the Theme abstract class, per-section token methods (layout/header/table/footer/cols/tabs plus filter/editable/toggleable), config themeoverrides, or ArrayTheme.
upgrade-theme-v6-to-v7
Migrates a v6 Theme class to the v7 architecture: a tiny struct() plus per-section token methods (layout/header/table/footer/cols/tabs + filter/editable/toggleable) with parentTheme inheritance.
align-grid
Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one. Encodes the discipline (columns + modules + baseline, grotesque type, flush-left, restrained black/white/red palette) AND the hard-won front-end engineering to make the grid…
larapilot-design
Writes HTML/CSS mockups under .larapilot/mockups/, presents and revises them with the user, and can build a custom design system for the client. Use for a mockup, landing, design-system choice, a change to existing mockups, or a client design system. Italian: mockup, prototipo visivo, design system, modifica mockup.
cecil-theme
Create, structure and package themes for Cecil (visual themes and component themes), following the conventions of the official Cecilapp/theme- repositories.