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 vimoxshah/skills --skill design-kitgit clone --depth 1 https://github.com/vimoxshah/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/vimoxshah/skills/design-kit)<a href="https://agentmods.dev/skills/vimoxshah/skills/design-kit"><img src="https://agentmods.dev/badge/skills/vimoxshah/skills/design-kit.svg" alt="Measured on agentmods" 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 | $0.00167 | $0.02433 |
| Opus 5 | $0.00084 | $0.01216 |
| Sonnet 5 | $0.00033 | $0.00487 |
| Haiku 4.5 | $0.00017 | $0.00243 |
Grade B, and why
design-kit scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
SKILLS=${SKILLS:-$(ls -d ~/.claude/skills ~/.agents/skills ~/.cursor/skills 2>/dev/null | head -1)} How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-kit — one design brain for every surface
Install note. scripts/check-font-coverage.py and scripts/import-house-themes.py read the deck template from a sibling house-decks/ skill directory. Install house-decks alongside this skill if you use those two scripts; everything else here works standalone.
Role. You own the values — color, type, motion, chart ramps — that every
presentation surface consumes. You do not own layout or narrative: house-decks
owns deck grammar, html-artifact owns published pages, hyperframes owns
video. This skill exists so those three stop each inventing their own palette.
Context. Two independent picks, validated as a pair:
- theme = the world (color roles, emphasis hues, semantics, rationing)
- font pairing = the voice (display / body / mono + tracking + transform)
Not every voice suits every world, so each theme declares which pairings it is
compatible with and gives a reason for each one it refuses. The compiler
enforces that; it is not a suggestion.
themes/ 11 themes + _motion.yaml (shared motion tokens)
fonts/catalog.yaml 9 pairings, first-class and reusable across themes
fonts/cache/ fetched woff2 (10–24 KB per face)
fonts/LICENSES.md generated: declared license vs live-API verified
scripts/dk.py the compiler + gates
references/ schema · fonts · adapters · charts
SKILLS=${SKILLS:-$(ls -d ~/.claude/skills ~/.agents/skills ~/.cursor/skills 2>/dev/null | head -1)}
The registry
House themes — transcribed from the deck template, not authored here. These are the proven look; reach for them first.
| Theme | Mode | Default pairing | Use it for |
|---|---|---|---|
| house-purple ★ | light | house-plex | The house look. The default. Purple accent, light content slides, dark moment slides |
| house-aurora | light | house-plex | Same structure, cyan-blue accent — calmer |
| house-boot | dark | house-plex | The house dark theme: deep navy, terminal-heavy content |
| house-keynote | light | house-plex | The house warm theme: paper-cream, terracotta |
What ships with it
24 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.
- fonts/catalog.yaml 8.0 KB
- fonts/LICENSES.md 2.1 KB
- references/adapters.md 5.8 KB
- references/charts.md 3.8 KB
- references/fonts.md 6.9 KB
- references/schema.md 4.9 KB
- scripts/check-deck-structure.py 6.0 KB runs code
- scripts/check-font-coverage.py 5.2 KB runs code
- scripts/check-ramps.py 4.2 KB runs code
- scripts/dk.py 40 KB runs code
- scripts/import-house-themes.py 11 KB runs code
- scripts/showcase.py 12 KB runs code
- themes/_motion.yaml 2.0 KB
- themes/cobalt-grid.yaml 1.9 KB
- themes/festival.yaml 2.2 KB
- themes/house-aurora.yaml 3.3 KB
- themes/house-boot.yaml 3.3 KB
- themes/house-keynote.yaml 3.2 KB
- themes/house-purple.yaml 3.4 KB
- themes/jewel-velvet.yaml 1.8 KB
- themes/poster-bone.yaml 1.8 KB
- themes/spectrum-light.yaml 4.7 KB
- themes/sunset-editorial.yaml 1.8 KB
- themes/terminal-neon.yaml 1.8 KB
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.
- 6d ago First seen · 177 lines · 167 tokens per session scan B 302e4cb2e1b0
design-kit is a skill published in the GitHub repository vimoxshah/skills (1 stars, last pushed 7d ago), licensed MIT. It adds 167 tokens to every session and 2,433 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
frontend-ui-ux-wizard
Designs and builds real, production-ready websites — landing pages, marketing sites, web apps, redesigns — with an intentional, non-templated visual identity (distinctive typography pairing, real design-token system, real spacing/color scale), then checks the build for errors, pushes to GitHub, and deploys it live.…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
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…
ui-designer/design-system
A shared set of rules for a product’s visual design, covering colors, fonts, spacing, corner shapes, shadows, and animations.