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 CaesiumY/ko-design-md --skill use-design-mdgit clone --depth 1 https://github.com/CaesiumY/ko-design-mdWrote 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/caesiumy/ko-design-md/use-design-md)<a href="https://agentmods.dev/skills/caesiumy/ko-design-md/use-design-md"><img src="https://agentmods.dev/badge/skills/caesiumy/ko-design-md/use-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/caesiumy/ko-design-md/use-design-md"><img src="https://agentmods.dev/badge/skills/caesiumy/ko-design-md/use-design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00226 | $0.01473 |
| Opus 5 | $0.00113 | $0.00737 |
| Sonnet 5 | $0.00045 | $0.00295 |
| Haiku 4.5 | $0.00023 | $0.00147 |
Grade A, and why
use-design-md scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://getdesign.kr/llms.txt How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
use-design-md — consumer skill for the ko/design.md catalog
Mental model
The ko-design-md catalog (https://getdesign.kr) publishes one design.md per Korean
service — a compact, machine-readable description of that brand's visual language:
colors in OKLCH, typography, spacing, radius, signature components, and do's & don'ts.
This skill is the consumer side: it pulls the right entry and uses it as the design
brief for UI work in whatever project you are currently in.
It does three things, in order:
- Discover — resolve the brand the user named to a catalog
slug. - Fetch — download that entry's raw
design.md(and, if useful, its token sidecar). - Apply — translate that design language into the current project's styling system.
This skill vs. design-md (don't mix them up)
use-design-md(this skill) — CONSUME an existing entry. Runs in any repo. "Make my dashboard look like Toss", "apply Karrot's style to this screen".design-md(the other skill) — PRODUCE a new entry, adding a brand to the catalog. Only runs inside the ko-design-md repo.
If the user wants to add or edit a catalog entry, stop and point them at design-md.
That is a different job in a different place.
Step 1 — Discover: resolve the brand to a slug
Fetch the catalog index (llms.txt format, ~one line per entry):
curl -s https://getdesign.kr/llms.txt
Each entry line looks like:
- [토스](https://getdesign.kr/services/toss/llms.txt): finance — <tagline>
Match the user's mention to a slug. The user may say a Korean name ("토스", "당근"), an English name ("Toss", "Karrot"), a design-system name ("SEED Design", "Vapor UI"), or the slug itself ("seed-design"). Match against the link text (name) AND the slug in the URL; the tagline often names the design system, which helps disambiguate.
Outcomes:
- One clear match → take its slug, go to Step 2.
- Several plausible matches → ask which one with
AskUserQuestion. - No match → the brand isn't in the catalog. Tell the user plainly, optionally list a
few catalogued brands in the nearest category, and mention that adding it is a
separate job (the
design-mdskill, inside the ko-design-md repo). Do not fabricate a design.md for an uncatalogued brand — that defeats the point of citing a real source.
What ships with it
3 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.
- 10d ago First seen · 114 lines · 226 tokens per session scan A 3cad72a6fb7b
use-design-md is a skill published in the GitHub repository CaesiumY/ko-design-md (44 stars, last pushed yesterday), licensed MIT. It adds 226 tokens to every session and 1,473 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
design-engineering
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…
s2-docs
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField…
design-to-code-check
Check alignment between a specific design specification and its code implementation — a focused, single-component or single-screen comparison. Trigger when someone says: does this match the design, check implementation, design code alignment, what's different between the design and the build, spec check…
stitch-extract-design-md
Extract a Stitch-compatible DESIGN.md from frontend source code, stylesheets, Tailwind config, theme files, and component patterns.