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 glifxyz/glif-mcp-server --skill web-visualsgit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/web-visuals)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/web-visuals"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/web-visuals/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/glifxyz/glif-mcp-server/web-visuals"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/web-visuals.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 | $0.00203 | $0.01416 |
| Opus 5.5 | $0.00081 | $0.00566 |
| Sonnet 5.5 | $0.00041 | $0.00283 |
| Haiku 4.5 | $0.00020 | $0.00142 |
Grade A, and why
web-visuals scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL "<media url>" -o public/images/hero.png How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make the visuals a web page needs and put them in the project. The user's explicit instructions come first, within host safety rules.
1. Take inventory
Read the page or component. List each visual slot:
- Hero: full-bleed or split, and which side the headline sits on.
- Section backgrounds: soft gradients, paper grain, material close-ups.
- Textures and patterns: must tile seamlessly.
- Illustrations: feature cards, empty states, 404, onboarding. Ask for SVG when the style is flat.
- Cutouts: product or people photos on a transparent background, to sit on page colors.
- Infographics and stat cards: keep the numbers and labels in HTML; let Glif make the art around them.
- Device or hardware surface: a photoreal laptop, phone or panel with a pure
#00FF00screen area that your code draws live UI into. - OG image: 1200×630, one per major route.
- Motion (optional): a looping background, or a scroll-scrubbed hero video.
Use what the user already has first. Never replace a supplied logo, product photo or screenshot. Glif fills the gaps.
2. Match the site's style
Pull the palette (CSS variables or Tailwind theme), fonts, mood and any existing images. Put hex colors and a one-line mood in the brief. If a logo or screenshot sets the style, upload it with upload_file and attach the returned fileUrl.
If the site supports dark mode, ask for matched light and dark versions with the same size and crop.
3. Check cost, then batch
Generation spends the user's Glif credits.
- If the user asked for these visuals, go ahead.
- If adding visuals was your idea, show the slot list in one line each and wait for a yes.
- Video uses more credits than images. Offer it; never make it unasked.
- When the look is still open, ask for 2 or 3 directions for the hero first, then make the rest in the chosen style.
Send one compose_project call for the whole page. For each asset, give:
- filename, such as
hero.pngortexture-paper.png - exact pixel size and aspect ratio
- where it goes and what it must show
- where to leave empty space for headline text
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.
- 7d ago Changed · +11 tokens per session 1d9eb375883d
- 8d ago First seen · 88 lines · 192 tokens per session scan A 1b8e01755d35
web-visuals is a skill published in the GitHub repository glifxyz/glif-mcp-server (215 stars, last pushed 7d ago), licensed MIT. It adds 203 tokens to every session and 1,416 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
frontend-design
Generates distinctive, production-grade frontend interfaces and artifacts (React, Vue, HTML/CSS). Prioritizes bold aesthetics, unique typography, and motion to avoid generic designs. Use when building websites, landing pages, dashboards, posters, or when the user requests to style, beautify, or create visually…
Aesthetic Web Design
Apply professional, premium UI/UX design standards when building or styling web interfaces. Use this skill when the user asks to create a website, landing page, web app, dashboard, UI component, or any visual interface — or when they ask to make something look better, more professional, or more beautiful. Covers…
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers design systems, anti-pattern detection, brand vs product registers, typography, color (OKLCH), spacing, motion, copy, and…
taste-soft
High-end visual design like a premium agency. Defines exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks common defaults that make AI designs look cheap or generic. Based on taste-skill by Leon Lin & blueemi, improved by shokunin.
design-taste-frontend
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
shadcn-sveltekit-design
Use when building, redesigning, beautifying, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, charts, sidebars, auth screens, blocks, responsive layouts…