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 drewnekota/cetus --skill web-designgit clone --depth 1 https://github.com/drewnekota/cetusWrote 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/drewnekota/cetus/web-design)<a href="https://agentmods.dev/skills/drewnekota/cetus/web-design"><img src="https://agentmods.dev/badge/skills/drewnekota/cetus/web-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/drewnekota/cetus/web-design"><img src="https://agentmods.dev/badge/skills/drewnekota/cetus/web-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 | $0.00080 | $0.02440 |
| Opus 5.5 | $0.00032 | $0.00976 |
| Sonnet 5.5 | $0.00016 | $0.00488 |
| Haiku 4.5 | $0.00008 | $0.00244 |
Grade A, and why
web-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 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web design
Your default web output regresses to the mean of the training set — and the mean is ugly: system fonts, a centered hero over a purple gradient, three identical cards, emoji headers. That look reads instantly as "AI-made". This skill exists to pull every page off that mean and onto something that looks deliberately designed. Follow the process; don't free-style from scratch.
Process (do these in order)
-
Commit to one aesthetic direction. Before any markup, pick a single point of view that fits the content and name it in a comment. Examples:
- Editorial — serif display, wide measure, strong hierarchy, ink-on-paper.
- Technical / precise — mono or grotesk, tight grid, hairlines, data-dense.
- Warm / organic — humanist sans, soft neutrals, generous radius, gentle.
- Brutalist — flat, high-contrast, oversized type, raw structure.
- Refined product — neutral grotesk, restrained accent, soft depth. Pick ONE and carry it through everything. Mixing directions = slop.
-
Set tokens first. Define type, color, space, radius as CSS custom properties at the top (see baseline below). Build from tokens, never hardcode one-off values. Consistency is most of what "designed" means.
-
Layout with a real grid + asymmetry. Use CSS grid. Constrain text measure to ~60–72ch. Do NOT center everything — anchor content, use deliberate asymmetry, let whitespace do work. Generous, uneven spacing reads as intentional; uniform padding reads as a template.
-
Compose components from the patterns below, restyled to your direction.
-
Self-review against the checklist, then — when it matters — open the page in the browser, look at it, and fix whatever reads as cheap before sending.
Typography (80% of the result)
- Load a real typeface from a CDN. Never ship the system default. Good,
free, characterful pairings:
- Editorial:
FrauncesorLibre Caslon Textdisplay +Inter/Newsreaderbody. - Technical:
Space Grotesk+IBM Plex Mono, orGeist+Geist Mono. - Warm:
Bricolage Grotesque+Instrument Sans. - Refined:
General Sans/Satoshi(Fontshare) for both. Use at most two families.
- Editorial:
- Type scale with real contrast. Display should be dramatically larger than
body (use
clamp()for fluid display). A flat scale where h1≈h2≈body is the #1 tell of an undesigned page. - Body: line-height 1.5–1.7, measure ≤72ch, weight 400, generous paragraph spacing. Headings: tighter line-height (1.05–1.2), often a heavier or contrasting weight, slightly negative letter-spacing on large display sizes.
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 · 168 lines · 80 tokens per session scan A 4f4356afe5ac
web-design is a skill published in the GitHub repository drewnekota/cetus (148 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,440 once invoked, about $0.0003 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
design_demo
Put a visual choice before a person as one self-contained page: one scene at their real size, variants swapped in place, A recommended, short plain questions; then record their reaction.
ui_design
Design or change anything people look at (app UI, widget, mockup, HTML page or report, chart, icon) so it fits the existing system, uses real content and states, and is checked by eye and by measurement at the viewer's real size.
前端设计工程师工作流程（林澄）
A front-end design engineering workflow for creating HTML, CSS, JavaScript, SVG, email templates, landing pages, data visualizations, and presentation or document source files. It combines visual planning with implementation and saves reviewable files.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.