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 skillmds/skillmd --skill claude-design-analysisgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/claude-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/claude-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/claude-design-analysis/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/skillmds/skillmd/claude-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/claude-design-analysis.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 | $0.00123 | $0.08720 |
| Opus 5.5 | $0.00049 | $0.03488 |
| Sonnet 5 | $0.00025 | $0.01744 |
| Haiku 4.5 | $0.00012 | $0.00872 |
Grade A, and why
Claude-design-analysis 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 4d 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 — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Claude.com is the warmest, most editorial interface in the AI-product category. The base atmosphere is a tinted cream canvas ({colors.canvas} — #faf9f5) — distinctly warm, deliberately not the cool gray-white that every other AI brand uses. Headlines run a slab-serif display ("Copernicus" / Tiempos Headline) at weight 400 with negative letter-spacing, paired with StyreneB / Inter body sans. The combination feels like a literary publication, not a SaaS marketing page.
Brand voltage comes from the cream + coral pairing — coral ({colors.primary} — #cc785c) is the signature Anthropic accent, used on every primary CTA, on the brand wordmark, and on full-bleed callout cards. The coral is warm, slightly muted, never cyan/blue — a deliberate counter-positioning against OpenAI's cool slate, Google's saturated blue, and Microsoft's corporate cyan.
The system has three surface modes that alternate page-by-page:
- Cream canvas (
{colors.canvas}) — default body floor - Light cream cards (
{colors.surface-card}) — feature card backgrounds - Dark navy product surfaces (
{colors.surface-dark}) — code editor mockups, model showcase cards, pre-footer CTAs, footer itself
The dark surfaces are where Claude shows its product chrome — code blocks, terminal output, model comparison tables, agentic-flow diagrams. The cream-to-dark contrast is the page's pacing rhythm.
Key Characteristics:
- Warm cream canvas (
{colors.canvas}— #faf9f5) with dark warm-ink text ({colors.ink}— #141413). The brand's defining color choice. - Coral primary CTA (
{colors.primary}— #cc785c). Used scarcely on individual buttons, generously on full-bleed coral callout cards. - Slab-serif display headlines via Copernicus / Tiempos Headline at weight 400 with negative letter-spacing. Pairs with humanist sans body for a literary editorial voice.
- Dark navy product mockup cards (
{colors.surface-dark}— #181715) carrying code blocks, terminal panels, model comparison data — the brand shows the product chrome at scale rather than abstract marketing illustrations. - Light cream feature cards (
{colors.surface-card}— #efe9de) — slightly darker than canvas, used for content-driven feature explanations. - Anthropic radial-spike mark — a small black asterisk-like glyph (4-spoke radial) — appears as the brand wordmark prefix and as a content marker.
- Border radius is hierarchical:
{rounded.md}(8px) for buttons + inputs,{rounded.lg}(12px) for content + product cards,{rounded.xl}(16px) for the hero illustration container,{rounded.pill}for badges. - Section rhythm
{spacing.section}(96px) — modern-SaaS standard. Internal card padding stays generous at{spacing.xl}(32px).
What ships with it
1 file 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.
- 4d ago First seen · 590 lines · 123 tokens per session scan A 0993266cce3d
Claude-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 8,720 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…