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 monkilabs/opencastle --skill frontend-designgit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/frontend-design)<a href="https://agentmods.dev/skills/monkilabs/opencastle/frontend-design"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/frontend-design/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/monkilabs/opencastle/frontend-design"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/frontend-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00587 |
| Opus 5.5 | $0.00019 | $0.00235 |
| Sonnet 5.5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
frontend-design 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 16d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Design Workflow
- Ground it in the subject. Read the brief and the product: who it is for, what it sells, what it should feel like.
- Write a short plan in a comment at the top of the main CSS file: the aesthetic named in 2–3 words, 4–6 named colors, the type pairing and the role of each face, one sentence per layout, and the one unforgettable detail.
- Critique the plan against the brief before writing code. Every choice that would fit any other product, or matches a tell below, gets replaced.
- Define every color, space, and radius as a
:rootcustom property; build components from those tokens only — no ad-hoc values. - Wrap motion in
@media (prefers-reduced-motion: no-preference); keep key animations under 500ms. - Verify before marking done: contrast ≥4.5:1 body text and ≥3:1 large text, no overflow at mobile sizes.
Avoid the generic look
These read as AI-generated on sight:
- A fade-and-slide-up (
fadeUp) entrance on every section, or a staggered hero reveal. Use one orchestrated page-load moment, or none. - Glass cards, and identical rounded cards with a soft grey shadow (
rgba(0,0,0,.12)) that lift on hover. - A near-black background with a single bright orange, acid-green or vermilion accent; a cream background with a serif display and terracotta.
- Inter, Roboto, Arial or the system stack as the display face; purple gradients on white.
- Template chrome: tracked all-caps labels, middle-dot metadata, one accented word in the headline.
Design principles and the reasoning behind them: REFERENCE.md.
Typography
Choose a pairing that fits the subject. Always ship a metric-preserving fallback chain (e.g. 'Fraunces', 'Georgia', serif).
Several agents building UI at once
Build the foundation first, in one task, and start the pages only when it is done: the design tokens (:root custom properties in one file), the shared layout, and the UI components. Every page task then imports those and adds none of its own — no new color, font or spacing value, no copied component, no inline style. Give each page task the paths to the tokens, the layout and the components, the aesthetic in its 2–3 words, and the content tone.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed · +2 lines 3ac9c087233b
- 18d ago Changed · +10 lines · -20 tokens per session ff11fe71d188
- 1mo ago First seen · 24 lines · 68 tokens per session scan A c594e0b9bb34
frontend-design is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 587 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 2026-08-30.
Other skills, from other repositories
antislop-ui
UI and visual skill for antislop. Use when building or editing any interface: color, layout, components, motion. Load with the core.
devexpress-wpf-from-screenshot
Builds a DevExpress WPF screen from a mockup — a screenshot, an image, or a Figma frame — choosing a DevExpress control per region, writing the XAML, running the app and comparing the result against the mockup. Use it even when the request never names DevExpress — "build this screen", "which control fits this layout"…
uicraft
Create, improve, audit, and polish distinctive production-grade web interfaces, including marketing/landing pages and personal portfolio sites. Use for UI or frontend design, responsive layouts, typography, color, motion, UX copy, accessibility, performance, design-system alignment, onboarding, edge cases, or visual…
ardot-design-to-code
Use this skill for Ardot canvas tasks that convert a design into frontend code, or extract a design system / style guide from a website. Covers: design-to-code, design → HTML/CSS/JS, export as webpage, pixel-perfect reproduction, generate an Application from a design, slide transitions, responsive scaling; and website…
ardot-ui-design
A workflow for designing user interfaces in the Ardot canvas, including websites, web apps, dashboards, mobile screens, forms, tables, and design systems. A user interface is the screens and controls people use to operate software.
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…