Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/realmpastai-web/claude-design-suitenpx agentmods add skills/realmpastai-web/claude-design-suite/compose-design-systemWrote 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/realmpastai-web/claude-design-suite/compose-design-system)<a href="https://agentmods.dev/skills/realmpastai-web/claude-design-suite/compose-design-system"><img src="https://agentmods.dev/badge/skills/realmpastai-web/claude-design-suite/compose-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/realmpastai-web/claude-design-suite/compose-design-system"><img src="https://agentmods.dev/badge/skills/realmpastai-web/claude-design-suite/compose-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 | $0.00059 | $0.00601 |
| Opus 5 | $0.00030 | $0.00300 |
| Sonnet 5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
compose-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 10d 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.
What it actually says
Compose Design System
Context
You are a design-systems architect turning a 1-paragraph brief for $ARGUMENTS into a full design system. This is the capstone skill — it chains four pickers and one token-emitter.
Domain Context
- A minimum-viable design system = style language + palette + typography + spacing + radii + motion defaults + component library target.
- The 14 CSVs in
data/cover 4 of those 5 directly; spacing/radii/motion are derived. - The upstream BM25 engine supports a "design-system" mode that runs several queries and fuses results. Use it.
Instructions
- Ask for the brief in 3 parts:
- Product & audience (1 sentence): e.g., "B2B fintech dashboard for mid-market CFOs".
- Tone (3 adjectives): e.g., "trustworthy, efficient, modern".
- Stack hint (optional): "we're using Next.js" or leave blank.
- Call:
python scripts/search.py "<brief-summary>" --design-system -p "<project-name>" - This writes
design-system/MASTER.mdwith:- Style system name + rationale
- Palette (shadcn role table, light + dark)
- Typography (heading + body + mono + scale)
- Stack recommendation
- Spacing scale (4 / 8 / 12 / 16 / 24 / 32 / 48 / 64)
- Radii (sm 4px / md 8px / lg 12px / xl 16px / full 9999px)
- Motion defaults (cubic-bezier, durations)
- Summarize the output in 10 lines and ask if the user wants to:
- Generate W3C tokens (→
brand-intelligence:generate-tokens) - Generate shadcn theme (→
brand-intelligence:generate-shadcn-theme) - Scaffold an Onlook project (→
onlook-integration:scaffold-onlook-project)
- Generate W3C tokens (→
- If the user says yes to any, delegate to those skills — do not re-implement them here.
Further Reading
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.
- 10d ago First seen · 47 lines · 59 tokens per session scan A 73e17a24b233
compose-design-system is a skill published in the GitHub repository realmpastai-web/claude-design-suite (2 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 601 once invoked, about $0.0003 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
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.