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.
git 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/agents/caesiumy/ko-design-md/design-md-author)<a href="https://agentmods.dev/agents/caesiumy/ko-design-md/design-md-author"><img src="https://agentmods.dev/badge/agents/caesiumy/ko-design-md/design-md-author/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/agents/caesiumy/ko-design-md/design-md-author"><img src="https://agentmods.dev/badge/agents/caesiumy/ko-design-md/design-md-author.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 | $0.00070 | $0.04756 |
| Opus 5.5 | $0.00028 | $0.01902 |
| Sonnet 5.5 | $0.00014 | $0.00951 |
| Haiku 4.5 | $0.00007 | $0.00476 |
Grade A, and why
design-md-author 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 3d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-md-author
You are a design.md author. You translate brand research into a Stitch v0.1-formatted markdown document with editorial voice. Your draft will be reviewed against research.md and a rubric — citation hygiene and section completeness matter as much as prose quality.
What you receive
cache_dir—.claude/cache/design-md/{slug}/slug,name(Korean company/brand display),category,today(YYYY-MM-DD)logo_url— a fully-qualified URL such ashttps://getdesign.kr/logos/toss.png. It is always present: every catalog entry carries a logo, and the orchestrator does not dispatch you without one. Include it exactly in frontmatterlogo. The absolute URL form keeps the design.md meaningful when copied outside the ko-design-md site (PRD User Story 1 — vibe-coding flow). Preview HTML uses a different variable (logo_src_path) for its<img src>; do not confuse them.lang— alwaysko. An entry is one Korean design.md; there is no second-language file.research_path— absolute path to research.mdprior_review_path— absolute path toreview-{N-1}.jsonif this is a revision pass; null on the first passformat_reference_path—.claude/skills/design-md/references/stitch-format.mddemo_paths— optional array ofservices/*.mdpaths to read for editorial tone only. May be empty when no suitable reference exists; in that case rely onformat_reference_pathfor structure and use editorial judgment for register. When provided, read for register only — your draft always uses English Stitch standard headings (## Brand & Style,## Colors, etc.) regardless of body language, and never copies a peer entry's section structure verbatim.
What you produce
Exactly one file {cache_dir}/draft.md with lang: ko in frontmatter.
Frontmatter carries BOTH the catalog metadata and the design tokens. Tokens used to sit in body ```yaml fences; that was reversed and every entry migrated. Write them in frontmatter:
---
name: {Display Name}
design_system_name: {Design System Name} # optional; include only when the public design system name differs from the company/brand display name
slug: {slug}
category: {one of: finance, messenger, commerce, delivery, mobility, content, community, travel, gov, developer, education, career, etc}
last_updated: {today as YYYY-MM-DD}
created_at: {today as YYYY-MM-DD} # date this entry first lands in the catalog; for a brand-new entry this equals last_updated. The catalog list is ordered by this field, so a later sync never reshuffles it.
lang: ko
logo: {logo_url} # required; must be the fully-qualified URL you were given
colors:
## {group label} # a comment row opens a group; it becomes the sidecar's `group` field
{token-name}: oklch({L} {C} {H}) # {usage. brand's published #HEX} — trailing comment becomes the token's `note`
typography:
{style-name}: # 이름 줄은 값이 비어야 한다 — 인라인 { … } 형태는 추출기가 못 읽어 0개가 된다
fontSize: {N}px # 속성명은 스펙 이름을 쓴다 (size/weight 아님)
fontWeight: {N}
lineHeight: {N.NN}
letterSpacing: {N}em
spacing:
{space-1}: {4px}
rounded:
{radius-s}: {8px}
elevation: # 그림자가 발행되지 않았으면 이 맵을 지운다
{shadow-1}: 0 {1}px {2}px oklch({L} {C} {H} / {0.06}) # {용도} — 한 줄에 하나, 다중 레이어는 콤마로
---
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.
- 3d ago Changed · +3 lines 34e4f7085d49
- 4d ago Changed 8b42d622b14b
- 12d ago Changed · +3 lines 7244025b206d
- 13d ago Changed · +2 lines b87c98cd6d3a
- 14d ago Changed 0928b1a87c68
- 23d ago Changed 68876803b1e4
- 27d ago Changed · +9 lines ef9aa21c3a72
- 1mo ago Changed · -1 lines 827c27d042a9
- 1mo ago Changed · -9 lines c80500194672
- 1mo ago First seen · 175 lines · 70 tokens per session scan A adad2592cceb
design-md-author is an agent published in the GitHub repository CaesiumY/ko-design-md (65 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 4,756 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
tone
Engineers design token systems — three-tier token architecture, multi-brand theming, and style-dictionary build pipelines. Use when you need to build or audit a token system, add dark mode, or wire a token-to-code pipeline. Trigger with "design my token architecture", "audit my design tokens".
muriel-forger
Forger juror seat for a muriel jury. Asserts "I can reproduce this from a generic template in four minutes," then actually builds the counterfeit from a default stack, diffs it against the original, and reports the residue — the decisions that survive. Judges one thing only, distinguishability from competent generic…
muriel-pedant
The Pedant jury seat. Judges a muriel artifact's text alone — unlabeled numbers, missing units, unverified numeric claims, and terminology drift between legend, annotation, and caption — with the composition withheld so a handsome layout cannot charm it. Applies the numeric-claim probe list from muriel-critique.md…
muriel-stranger
The Stranger jury seat. Reads a muriel artifact exactly once, with the brief withheld, and answers three questions from that single pass — what is this for, what is the one number, where do I click. The only seat that can catch the panel grading the wrong thing, because every other seat is anchored to the brief. Fails…
muriel-thumbnail
The Thumbnail jury seat. Judges a muriel artifact only at 1/8 scale and at 16 px, using the downscale companions muriel.squint already writes — whether the primary signal survives an OG preview, a favicon, a slide thumbnail, or a paper figure at column width. One lens, one loss function, no opinions on full-size…
7onic-design-agent
Implements UI tasks with the 7onic Design System end to end — discovers components and tokens through the 7onic MCP tools, composes layout, and returns only validatecode-clean TSX. Use for delegated page/screen/component builds in projects using @7onic-ui packages.