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 saajunaid/caddis-plugin --skill design-mdgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/design-md)<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/design-md"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/design-md/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/saajunaid/caddis-plugin/design-md"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/design-md.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 | $0.00045 | $0.01320 |
| Opus 5.5 | $0.00018 | $0.00528 |
| Sonnet 5.5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
design-md 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 29d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DESIGN.md
Google's open spec (Apache-2.0) for writing visual identities as structured files that coding agents can consume. Combines machine-readable YAML tokens with human-readable Markdown rationale.
Not the same as design-system-tokens: that skill covers our internal three-layer token architecture (primitive→semantic→component) for building actual CSS systems. design-md is a specification format — a document you write to describe a brand to an agent, with a CLI for validation and export.
When to Use
- Creating a formal design spec a coding agent will reference when building UI
- Multi-project brand consistency where the spec needs to be version-controlled
- Validating color palette for WCAG AA contrast compliance
- Exporting to Tailwind theme JSON or W3C DTCG token format
- Working with teams who want a single source of truth for design tokens
Use popular-web-designs or warm-editorial-ui instead for one-off prototypes or visual inspiration.
File Structure
DESIGN.md
Single file. YAML front matter (tokens) + Markdown body (rationale).
---
version: alpha
name: "Brand Name"
description: "One-line description of the visual identity"
colors:
primary: "#6366f1"
primary-hover: "#4f46e5"
background: "#ffffff"
surface: "#f8fafc"
text: "#0f172a"
text-secondary: "#64748b"
border: "#e2e8f0"
success: "#10b981"
warning: "#f59e0b"
danger: "#ef4444"
typography:
font-heading: "Inter"
font-body: "Inter"
font-mono: "JetBrains Mono"
size-xs: "0.75rem"
size-sm: "0.875rem"
size-base: "1rem"
size-lg: "1.125rem"
size-xl: "1.25rem"
size-2xl: "1.5rem"
size-3xl: "1.875rem"
size-4xl: "2.25rem"
spacing:
xs: "0.25rem"
sm: "0.5rem"
md: "1rem"
lg: "1.5rem"
xl: "2rem"
2xl: "3rem"
rounded:
sm: "0.25rem"
md: "0.375rem"
lg: "0.5rem"
xl: "0.75rem"
full: "9999px"
---
Markdown Sections (canonical order)
## Overview
One paragraph: brand personality, target audience, emotional goal.
## Colors
Why each color was chosen. Contrast ratios for key pairs. Light/dark mode notes.
## Typography
Font selection rationale. Hierarchy explanation. When to use heading vs body.
## Layout
Grid system. Max content width. Whitespace philosophy.
## Elevation & Depth
Shadow system. Z-index scale. When to use each elevation level.
## Shapes
Border-radius philosophy. When to use rounded vs sharp.
## Components
Key component decisions. Button variants. Card patterns. Form style.
## Do's and Don'ts
Concrete usage rules. What breaks the brand. Common mistakes.
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.
- 29d ago Changed · -9 tokens per session eed39c52bdcc
- 1mo ago First seen · 168 lines · 54 tokens per session scan A 2a4c90e02d5e
design-md is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,320 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
render-html-page
Convert a finished trip plan into a polished, self-contained HTML page using the design system.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
anti-slop-frontend
A mechanical, countable anti-slop checklist for AI-generated frontend. Catches the specific signatures an undirected model defaults to: AI-purple glows, Inter-everywhere, em-dashes, div-based fake screenshots, eyebrow-on-every-section, beige+brass "premium" palettes, generic Jane Doe / Acme data. Advisory layer that…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.