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 fusengine/agents --skill design-webgit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/design-web)<a href="https://agentmods.dev/skills/fusengine/agents/design-web"><img src="https://agentmods.dev/badge/skills/fusengine/agents/design-web/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/fusengine/agents/design-web"><img src="https://agentmods.dev/badge/skills/fusengine/agents/design-web.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 | $0.00036 | $0.03100 |
| Opus 5.5 | $0.00014 | $0.01240 |
| Sonnet 5.5 | $0.00007 | $0.00620 |
| Haiku 4.5 | $0.00004 | $0.00310 |
Grade A, and why
design-web 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Covers hero discipline (headline/subhead word caps, single primary CTA), body-sequence selection against the canonical-order default, asymmetric grids instead of a uniform 3-column layout, and a set of mechanical anti-slop flags (uniform grids, uniform padding, the AI-signature entrance motion, the reflex blue/Inter/rounded-2xl combo).
Declares the three reproduced elements (Je reproduis, corpus procedures vs sector register) that design-review verdicts, and runs the silhouette Lookalike Test before the page can be called done: a fail is structural and goes back to the hero/body picks, not to a cosmetic tweak.
Design Web — Marketing & Landing, Register Brand
When
After design-system tokens exist and design-method's Gate 0 has locked register
brand (one dominant, expressive message). Read design-method's routing table first —
a dashboard/app/utility surface routes to design-webapp instead. Exception: a
marketing-adjacent surface living inside an app shell (e.g. an in-app pricing page) still
routes here for that one page (see design-webapp's reciprocal note).
Input
design-system.md— OKLCH palette, type pair, spacing density, the 3 dials.../design-method/references/register/brand.md— the page's POV sentence and the per-section Competitor Lift Test (loaded once per task, not re-read per step).- The
generatemove report (../design-method/references/moves/generate.md) if this task started from Gate 0 — steps 1-4 of that report (register, inspiration, tokens, and step 4's two picks: hero treatment + body sequence) are inputs here, not repeated.
Steps
- Structure comes from register + two structural picks, never from template
reproduction.
references/design-inspiration.mdsources taste in a fixed order: the local corpus (references/refs-design/, fifteen rebuilt pages whosetokens-*.mdcarry measured procedures) supplies palette, typography, depth and craft; 1-2 real production sites in the client's own sector supply register only — vocabulary, codes, level of formality. Section flow, spacing rhythm and layout are never copied from either. The actual skeleton is the pair named indesign-method'sgeneratemove: a hero treatment from../design-method/references/macrostructure-bank.md(first screen only — it decides nothing past the fold) plus a body sequence from../design-method/references/body-sequence-bank.md, both filtered through the POV inregister/brand.md. Naming one without the other is an incomplete plan. Reproducing an inspiration site's structure verbatim is the single biggest source of templated output — treat it as a hard boundary, not a style preference.
What ships with it
60 files 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.
- references/21st-dev.md 3.7 KB
- references/buttons-guide.md 4.5 KB
- references/cards-guide.md 6.1 KB
- references/component-composition-ref.md 2.7 KB
- references/component-examples.md 1.9 KB
- references/component-variants-ref.md 2.7 KB
- references/design-inspiration-urls.md 4.9 KB
- references/design-inspiration.md 17 KB
- references/design-patterns.md 8.3 KB
- references/forms-guide.md 5.5 KB
- references/gemini/gemini-design-workflow.md 3.9 KB
- references/gemini/gemini-feedback-loop.md 2.7 KB
- references/gemini/gemini-tool-signatures.md 2.6 KB
- references/grids-layout.md 6.0 KB
- references/icons-guide.md 4.7 KB
- references/layout-discipline.md 6.1 KB
- references/layouts/navigation/footer.md 2.6 KB
- references/layouts/navigation/mobile-nav.md 2.9 KB
- references/layouts/navigation/navbar.md 2.7 KB
- references/layouts/navigation/sidebar.md 2.8 KB
- references/layouts/page-architecture.md 3.0 KB
- references/photos-images.md 19 KB
- references/premium-patterns/01-numbered-services/description.md 4.1 KB
- references/premium-patterns/02-alternating-sections/description.md 6.9 KB
- references/premium-patterns/03-hero-badge-inline/description.md 3.5 KB
- references/premium-patterns/04-bento-grid/description.md 4.7 KB
- references/premium-patterns/05-fullbleed-hero/description.md 4.4 KB
- references/premium-patterns/06-gradient-steps/description.md 3.6 KB
- references/premium-patterns/07-cta-giant-typography/description.md 3.5 KB
- references/premium-patterns/08-radical-alternation/description.md 4.2 KB
- references/premium-patterns/09-tabs-image-swap/description.md 4.3 KB
- references/premium-patterns/10-accordion-carousel/description.md 6.4 KB
- references/premium-patterns/PATTERNS.md 12 KB
- references/reference-index.md 5.1 KB
- references/refs-design/cursor-recode/design-system.md 9.2 KB
- references/refs-design/cursor-recode/index.html 112 KB
- references/refs-design/cursor-recode/motion-nav.js 6.9 KB runs code
- references/refs-design/cursor-recode/motion-scroll.js 7.3 KB runs code
- references/refs-design/cursor-recode/motion.js 4.0 KB runs code
- references/refs-design/cursor-recode/styles.css 97 KB
- references/refs-design/cursor-recode/tokens-cursor.md 31 KB
- references/refs-design/dispatch-recode/design-system.md 8.8 KB
- references/refs-design/dispatch-recode/img/glow.webp 28 KB
- references/refs-design/dispatch-recode/img/hero.webp 38 KB
- references/refs-design/dispatch-recode/img/nebula.webp 313 KB
- references/refs-design/dispatch-recode/img/trails.webp 122 KB
- references/refs-design/dispatch-recode/index.html 39 KB
- references/refs-design/dispatch-recode/motion.js 9.4 KB runs code
- references/refs-design/dispatch-recode/styles.css 41 KB
- references/refs-design/dispatch-recode/tokens-dispatch.md 39 KB
- references/refs-design/endlesstools-recode/design-system.md 9.6 KB
- references/refs-design/endlesstools-recode/index.html 46 KB
- references/refs-design/endlesstools-recode/motion.js 8.9 KB runs code
- references/refs-design/endlesstools-recode/styles.css 33 KB
- references/refs-design/endlesstools-recode/tokens-endlesstools.md 25 KB
- references/refs-design/fora-recode/design-system.md 8.3 KB
- references/refs-design/fora-recode/index.html 35 KB
- references/refs-design/fora-recode/motion.js 21 KB runs code
- references/refs-design/fora-recode/styles.css 68 KB
- references/refs-design/fora-recode/tokens-fora.md 34 KB
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 · 180 lines · 36 tokens per session scan A 0f310abbfa90
design-web is a skill published in the GitHub repository fusengine/agents (33 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 3,100 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
designing-interfaces
Creates a design system for software with a UI. Use when a project has a user interface and architecture is confirmed — whether creating from scratch or extracting patterns from existing code.
visual
Define a brand's visual identity — logo usage rules and variations, a color palette with contrast ratios, typography and type scale, and photography, illustration and icon style. Use when the user needs to settle their brand colors, fonts, logo rules or imagery style, or formalize the visual assets they already have.
a11y-audit
Audit a Figma component or frame for accessibility in one pass — design lint, contrast, color-blindness simulation, focus order — with fixes. Use when the user points at a Figma design and wants a quick accessibility check before it goes to development. Not for a full WCAG-EM audit of a built site or app, or mentoring…
design-review
Create a Figma Slides deck summarizing a component's design journey — research, contract, options, prototype and test results — with title and summary slides. Use when the user needs to present a component's design work to stakeholders or walk a team through it. Not for feedback on a design; see /coaching:ux or…
export-tokens
Export the design tokens (variables) from a Figma file as CSS custom properties, Tailwind config or JSON, optionally saved to a file. Use when the user wants Figma colors, spacing and type values in code, or gives a Figma URL and asks for its tokens. Not for an inventory of the whole design system; see…
system-overview
Summarize a Figma file's design system — components, styles, token collections and modes, and page structure — in one structured overview. Use when the user is new to a Figma design system or wants to know what it contains before working with it. Not for exporting tokens as code; see /design:export-tokens.