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 OneWave-AI/claude-skills --skill design-style-installergit clone --depth 1 https://github.com/OneWave-AI/claude-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/onewave-ai/claude-skills/design-style-installer)<a href="https://agentmods.dev/skills/onewave-ai/claude-skills/design-style-installer"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/design-style-installer/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/onewave-ai/claude-skills/design-style-installer"><img src="https://agentmods.dev/badge/skills/onewave-ai/claude-skills/design-style-installer.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 | $0.00079 | $0.00875 |
| Opus 5 | $0.00039 | $0.00438 |
| Sonnet 5 | $0.00016 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
design-style-installer 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Style Installer
Apply a full design system to a project the way a brand refresh actually works: tokens first, wiring second, components last, and nothing hardcoded that the tokens already define. Sources: the seven production themes in Open Agent Stack design-styles/ -- each ships tokens.json (W3C design-tokens), theme.css, tailwind.tokens.js, and a WCAG contrast worksheet -- or any local W3C-format tokens file.
Workflow
- Pick the style. If the user named one, fetch it from the open-agent-stack repo (or read the local clone). If not, show the seven options with their one-line personalities -- aurora-mesh (soft futuristic dark, gradient mesh), cirrus (light cloud/sky, frosted), liquid-glass (translucent layered), mono-brutalist (stark, type-led), neo-terminal (CRT green-on-black), sand-terra (warm editorial neutrals), tidal (deep ocean blues) -- and ask which fits the product.
- Read the project. Detect the stack (Tailwind version, CSS modules, styled-components, plain CSS) and inventory the current styling surface: where colors, fonts, radii, and shadows are defined today, and how many components hardcode values outside that.
- Install the tokens. Wire the theme by stack: Tailwind -- merge
tailwind.tokens.jsintotheme.extend(v4: emit@themeCSS variables); otherwise -- addtheme.csscustom properties at:root/[data-theme]. Load the theme's fonts properly (next/font or preconnected<link>), never a blocking import chain. - Repaint. Replace hardcoded values in components with token references, mapping by role, not by nearest hex: old primary -> new accent, old page background ->
bg.base, old card ->surface. Where the old design had roles the theme lacks (a third accent, a warning tint), derive them from the theme's palette logic and document the additions in the tokens file -- do not freelance new colors. - Verify. Run the build, then check the money paths render correctly: nav, hero, buttons in all states, forms, cards. Confirm text/background pairs still meet the contrast worksheet's AA levels after any derivations. Output
design-install-report.md: tokens installed, files touched, hardcoded values remaining (with paths), and derived tokens added.
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 · 35 lines · 79 tokens per session scan A 33cad1a33d7c
design-style-installer is a skill published in the GitHub repository OneWave-AI/claude-skills (291 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 875 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
vertical-site-conventions
Compose pages and sites that read as their vertical: ecommerce-catalog storefronts that look like storefronts, hospitality-food sites that look like restaurants, b2b-manufacturer sites that look industrial. Use this skill whenever the user wants to build a site that looks like the vertical it serves, fix a build that…
suede-design
Suede Labs AI design skill for making an interface feel intentional instead of templated: design tokens, color strategy, OKLCH ramps, type scale, fluid type, visual hierarchy, dark mode, spacing, component laws, motion, and source-to-implementation visual QA. Use when asked to design, restyle, polish, or audit a…
frontend-design-review
Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…