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 archetypeai/agent-skills --skill atai-design-systemgit clone --depth 1 https://github.com/archetypeai/agent-skillsWrote 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/archetypeai/agent-skills/atai-design-system)<a href="https://agentmods.dev/skills/archetypeai/agent-skills/atai-design-system"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-design-system/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/archetypeai/agent-skills/atai-design-system"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-design-system.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 | $0.00259 | $0.03382 |
| Opus 5 | $0.00130 | $0.01691 |
| Sonnet 5 | $0.00052 | $0.00676 |
| Haiku 4.5 | $0.00026 | $0.00338 |
Grade A, and why
atai-design-system 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archetype AI Design System — Scaffold, Don't Reinvent
There is a real, published, MIT-licensed design system on npm. Front-ends are assembled by installing it, not by transcribing tokens or copy-pasting component markup. The ds CLI scaffolds a SvelteKit + Tailwind v4 project, installs the packages, wires the order-critical CSS, and drops the design system's own agent configuration (CLAUDE.md/AGENTS.md + ds-manifest.json) into your repo. After that, defer to that shipped config — it owns components, fonts, fallback behavior, and styling. This file only gets you to the scaffold.
The packaged components currently ship for Svelte 5 — Svelte 5 + SvelteKit + Tailwind v4 + the DS packages, exactly what ds create scaffolds; a React port is in progress. Prefer that stack for Newton demo front-ends. On any other stack (React, Flask, plain HTML), @archetypeai/ds-lib-tokens is pure CSS and usable from any framework — tokens and base styles only, no components.
When to Apply
- User wants to start a new Newton demo front-end / dashboard / monitoring UI
- User wants to add Archetype AI branding + tokens to an existing SvelteKit app
- User wants branded components: menubar, logo, cards, badges, tables, dialogs, sensor/scatter/area charts, a video player, a code block, toasts
Do not use this skill when:
- The task is Newton API / model work — text·image·video reasoning, embeddings, KNN, data prep. Use the
atai-newton-fusion-model,atai-newton-omega-model, oratai-newton-omega-model-data-prepskills (source).
The System (MIT)
Four packages under the @archetypeai/ scope:
| Package | Role | What you get |
|---|---|---|
@archetypeai/ds-lib-tokens |
Tailwind v4 theme | OKLCH semantic tokens (background, foreground, card, primary, muted, destructive, border, ring, chart-1..5, sidebar, atai-{neutral,good,warning,critical}) + brand colors (brand-{babyblue,yellow,black,white}) + full shade palettes (the Tailwind scales plus custom mauve/olive/mist/taupe, 50–950) + spacing/radius/icon-stroke scales + .dark variant + font-family stacks with system fallbacks + a semantic HTML base layer that styles bare h1–h6/p/code on-brand. Pure CSS — no JS. |
@archetypeai/ds-ui-svelte-console |
Stable primitives | ~24 Svelte 5 components: alert, badge, button, card, checkbox, codeblock, collapsible, dialog, dropdown-menu, dropzone, empty-state, input, input-group, item, label, progress, select, separator, sonner, spinner, table, tabs, textarea, tooltip — plus a theme helper and utils (cn). |
@archetypeai/ds-ui-svelte-labs |
Experimental primitives (composes console) | aspect-ratio, chart, kbd, logo, menubar, scatter-chart, sensor-chart, slider, switch, toggle, video-player. Charts are built on layerchart (pinned to an exact prerelease). |
@archetypeai/ds-cli (ds) |
Scaffold + agent config | create / init / add. Installs the packages + peers, writes the order-critical layout.css, sets up shadcn-svelte, and installs the design system's own agent config. |
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.
- 9d ago First seen · 112 lines · 259 tokens per session scan A 59dc03b856d1
atai-design-system is a skill published in the GitHub repository archetypeai/agent-skills (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 259 tokens to every session and 3,382 once invoked, about $0.0013 per session on Opus 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
vue-base-skill
A parent guide for building Vue interface components with shared rules for cards, buttons, labels, and tables. It requires these components to sit inside a base card and use shared CSS design values.
ui-ux-design
Generate design systems and implement UX/UI for software products using Astro, Svelte, Tailwind CSS, Material Design 3, and OKLCH color system. Covers style selection, color palettes, typography, layout patterns, accessibility, and frontend code generation. Triggers on "design system", "UI design", "color palette"…
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, responsive layouts, theming, icon selection, and requests to…
pandacss-styling
Use when panda CSS zero-runtime styling — token system, patterns, recipes, conditions, JSX styles. Use when working with pandacss styling.
od-vue-export
Use this plugin when the user wants to hand an accepted Open Design artifact to a Vue 3 project.
tavern-ui
A front-end development guide for building interfaces shown inside SillyTavern chat messages, using HTML, CSS, JavaScript, or Vue 3. It also covers message placeholders, MVU variable access, packaging, deployment, and local previews.