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 jxoesneon/Ciel --skill design-systemgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/design-system)<a href="https://agentmods.dev/skills/jxoesneon/ciel/design-system"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/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/jxoesneon/ciel/design-system"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/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 | $0.00073 | $0.02437 |
| Opus 5.5 | $0.00029 | $0.00975 |
| Sonnet 5.5 | $0.00015 | $0.00487 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade A, and why
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 15d 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.
This is a copy
100% identical to design-system-skill — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building on a Design System (frontend code)
A way to build UI in a frontend codebase on top of an existing design system. You discover the system, record what you find in a per-project reference, reuse its components, and bind to its tokens — accreting knowledge as you go. The skill holds the method; the per-project reference holds the system.
Rules
- Read-only by default. Treat the codebase as read-only until the user points you at where to write.
- Confirm before writing. Name what you're about to change and get a clear go-ahead. Don't infer permission from intent.
- Verify the system before building; never invent it. Confirm the resolved design-system source with the user, and surface what you can and can't reproduce from it, before generating UI. If the system is ambiguous or incomplete, or a token / component / icon can't be sourced from it, ask — do not silently substitute an invented token, a look-alike component, or a hand-drawn icon and present it as on-system. Fabricated fidelity is worse than a flagged gap.
How to operate
- Find the design system — and confirm the source before building. The system's source may be (a) the codebase — dependencies (a UI package like MUI / Chakra / shadcn / Radix, or an internal
@org/ui), a local components directory, and the token source (Tailwind config, CSS custom properties, a tokens file/DTCG, a theme object) — or (b) a Figma reference the user provides (a library/file URL), when the real system lives in Figma rather than in code (e.g. a native app with no web component library). Detect (a) by inspecting the codebase; take path (b) whenever a Figma reference is passed (see "Figma-sourced design systems" below). If neither is present, surface what's installed or available and offer those as options, or ask which to adopt — don't invent one. Then confirm the resolved source — and what you can/can't reproduce from it — with the user before building (Rule 3). Also confirm what you're building and where it's allowed to write. - Discover foundations by introspection (see the Foundations checklist below) — read the types, the theme/token source, and any Storybook/docs — and record them by copying
design-system-reference.template.mdinto the project (or a section ofCLAUDE.md). - Discover components on use. The first time you reach for a component, introspect its props — its TypeScript types, Storybook args, or source. Record the selection axes + key props + any non-introspectable gotcha.
- Build on the framework. Reuse the app shell / layouts / page or route templates the system or app already defines, rather than recomposing chrome from primitives. If undocumented, inspect or ask where new UI belongs.
- Capture as you go. Add confirmed patterns and gotchas to the reference so the next session doesn't re-learn them.
What ships with it
2 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.
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.
- 15d ago Changed · -3 lines · -2 tokens per session 8704d5f59d1e
- 22d ago First seen · 102 lines · 75 tokens per session scan A a0138afb9875
design-system is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,437 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to design-system-skill, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
ui-features
Implementing UI/UX features in sidecar including modals (internal/modal library), keyboard shortcuts, mouse support, scrolling, pill/tab rendering, and pane resizing. Use when implementing UI features, handling user input, adding keyboard shortcuts, building modals, or working on UX improvements.
impeccable
Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.
a11y-audit
Run a Maestro-style accessibility audit for WCAG compliance, ARIA usage, keyboard navigation, and screen reader compatibility.
accessibility-basics
Use on every UI change - semantic HTML, labels for controls, keyboard-navigable dialogs/menus, visible focus, and never color as the only signal.
lov-maintain-partners
Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…
lov-oh-my-landingpage
A landing-page creation and redesign skill that derives a product’s positioning, story, and visual direction from its actual product and brand facts. It then implements the page responsively and checks the result against the intended product message.