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 mshadmanrahman/claude-for-designers --skill design-tokensgit clone --depth 1 https://github.com/mshadmanrahman/claude-for-designersWrote 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/mshadmanrahman/claude-for-designers/design-tokens)<a href="https://agentmods.dev/skills/mshadmanrahman/claude-for-designers/design-tokens"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/design-tokens/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/mshadmanrahman/claude-for-designers/design-tokens"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/claude-for-designers/design-tokens.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 | $0.00027 | $0.00710 |
| Opus 5 | $0.00014 | $0.00355 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
design-tokens 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 12d 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
You are establishing the design system foundation. Tokens defined here are used by every component in /frontend-design. Get this right before building anything.
First, check: does a design system already exist for this project? Ask the user to confirm. If yes, document the existing tokens rather than inventing new ones. Pull from Figma or existing CSS files if accessible.
If starting from scratch, create CSS custom properties across these five categories:
Color
Brand colors (primary, secondary, accent), semantic colors (action, destructive, success, warning), neutral scale (background, surface, border, text), feedback colors (error, warning, success, info). Name every token by its purpose, not its value. Use --color-action not --color-blue. Use --color-text-primary not --color-gray-900.
Typography Font family (body, heading, mono if needed), type scale (xs, sm, base, lg, xl, 2xl, 3xl), font weights (regular, medium, semibold, bold), line heights (tight, normal, relaxed).
Spacing
A consistent scale, not arbitrary values. Use a base unit (4px or 8px) and name steps by feel: --spacing-tight, --spacing-comfortable, --spacing-spacious. At minimum: 4px, 8px, 12px, 16px, 24px, 32px, 48px, 64px.
Border radius Small (input, button), medium (card), large (modal, sheet), full (pill, avatar).
Motion A duration scale (fast, default, slow) and one easing curve. Justify the slow end against the slowest device your user is actually holding.
Output as a ready-to-paste CSS :root block. Include a brief comment above each category explaining the system logic. No inline documentation that pads length; every comment must earn its space.
Dark mode: structure the tokens so that dark mode requires only new token values, not new components. Use semantic names so a dark theme can override --color-background without touching component code.
Token audit (use this when Figma and the frontend do not match)
If a value looks correct in Figma but renders differently in the browser, run this audit before filing a bug. Paste your Figma token export and your CSS file and ask:
"I am going to paste two things: a Figma token export and a CSS file. Compare them. Tell me: (1) which tokens in the export are not referenced anywhere in the CSS, (2) which CSS values are hardcoded instead of using a token, and (3) whether there are any unit mismatches between the token values and the CSS values (for example, a px value in the token but a rem value in the CSS). List each issue with the specific token name and the line in the CSS where the problem appears."
The four most common causes of a mismatch: the token was never exported from Figma, the token was exported but the CSS references a hardcoded value instead, the units differ (px in Figma, rem in CSS), or the comparison is being made at different zoom levels. Confirm all four before concluding something is broken.
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.
- 12d ago First seen · 38 lines · 27 tokens per session scan A 52771c52ec49
design-tokens is a skill published in the GitHub repository mshadmanrahman/claude-for-designers (28 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 710 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
frontend-enhancer
This skill should be used when enhancing the visual design and aesthetics of web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. REQUIRES ui-research skill first. Use this skill for tasks like improving styling, creating responsive designs…
generic-design-system
Complete design system reference for any project - colors, typography, spacing, components, animations. Adapts to project theme and tech stack. Use when implementing UI, choosing colors, creating animations, or ensuring brand consistency. For new design systems, use ui-research skill first.
generic-react-design-system
Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.
generic-static-design-system
Complete design system reference for static HTML/CSS/JS sites. Covers colors, typography, component patterns, animations, and accessibility. Use when implementing UI, choosing colors, or ensuring brand consistency.
generic-static-ux-designer
Professional UI/UX design expertise for static HTML/CSS/JS sites. Covers design thinking, user psychology, visual hierarchy, minimalist interaction patterns, accessibility, and performance-driven design. Use when designing features, improving UX, or conducting design reviews.
ak-elementor-studio
AK Elementor Studio — built by Abanoub Khalil (akstudio.me). Converts ANY input — HTML/CSS/JS code, screenshots, images (PNG, JPG, WebP), PDFs, Figma exports, design mockups, wireframes, or any visual file — into fully structured Elementor page JSON templates importable into WordPress. Activate this skill whenever the…