oh-my-design-cli 1.0.2 → 1.2.0

package/README.ja.md

@@ -5,7 +5,7 @@
 <h1 align="center">oh-my-design</h1>
 
 <p align="center">
-  <strong>67 社の実在する企業デザインシステムから DESIGN.md を生成。</strong>インタラクティブウィザード。AI 呼び出しゼロ。
+  <strong>88 社の実在する企業デザインシステムから DESIGN.md を生成。</strong>インタラクティブウィザード。AI 呼び出しゼロ。
 </p>
 
 <p align="center">
@@ -17,7 +17,7 @@
   <a href="https://github.com/kwakseongjae/oh-my-design/stargazers"><img src="https://img.shields.io/github/stars/kwakseongjae/oh-my-design?style=social" alt="GitHub Stars" /></a>
   <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square" alt="PRs Welcome" />
   <img src="https://img.shields.io/badge/AI%20calls-zero-blue?style=flat-square" alt="Zero AI" />
-  <img src="https://img.shields.io/badge/references-67-7c5cfc?style=flat-square" alt="67 References" />
+  <img src="https://img.shields.io/badge/references-88-7c5cfc?style=flat-square" alt="88 References" />
 </p>
 
 <p align="center">
@@ -36,7 +36,7 @@
 
 1. **[仕様](spec/omd-v0.1.md)** — バージョン管理された Google Stitch 拡張、MIT ライセンス。
 2. **[Claude Code スキル](.claude/skills/omd/SKILL.md)** — 仕様をハード制約として自動適用。
-3. **[67 のリファレンス](references/)** — 実在企業の `DESIGN.md` をフォークし、ビルダーでカスタマイズしてそのまま導入。
+3. **[88 のリファレンス](references/)** — 実在企業の `DESIGN.md` をフォークし、ビルダーでカスタマイズしてそのまま導入。
 
 **API キー不要。AI 呼び出しゼロ。全てクライアントサイドで完結。**
 
@@ -61,10 +61,10 @@ Toss · Claude · Line · Stripe · Linear · Vercel · Notion · Airbnb · Appl
 ## 主な機能
 
 - **ビルダー** — リファレンスを選び、カラー / radius / ダークモードを調整し、コンポーネントを選択して Export。**Philosophy** フィルターで完全なブランド哲学を持つ 10 件に絞り込めます。
-- **デザインシステムディレクトリ** ([oh-my-design.kr/design-systems](https://oh-my-design.kr/design-systems)) — 67 リファレンス中 34 件は公式のデザインシステムまたはブランドガイドラインページを持っており、ディレクトリからライブサムネイル付きで直接アクセスできます。
-- **Personal Curation** ([oh-my-design.kr/curation](https://oh-my-design.kr/curation)) — MBTI 風の短いクイズであなたのデザイン傾向を 67 リファレンスのいずれかとマッチングし、そのリファレンスが事前選択されたビルダーへ直接移動します。
+- **デザインシステムディレクトリ** ([oh-my-design.kr/design-systems](https://oh-my-design.kr/design-systems)) — 88 リファレンス中 34 件は公式のデザインシステムまたはブランドガイドラインページを持っており、ディレクトリからライブサムネイル付きで直接アクセスできます。
+- **Personal Curation** ([oh-my-design.kr/curation](https://oh-my-design.kr/curation)) — MBTI 風の短いクイズであなたのデザイン傾向を 88 リファレンスのいずれかとマッチングし、そのリファレンスが事前選択されたビルダーへ直接移動します。
 
-## サポートされる 67 のリファレンス
+## サポートされる 88 のリファレンス
 
 | カテゴリ | 企業 |
 |----------|------|
@@ -112,7 +112,7 @@ Toss · Claude · Line · Stripe · Linear · Vercel · Notion · Airbnb · Appl
 oh-my-design/
   spec/              OmD v0.1 仕様 (正本)
   .claude/skills/omd/ Claude Code スキルバンドル
-  references/        67 社分の DESIGN.md ファイル
+  references/        88 社分の DESIGN.md ファイル
   src/               CLI コア (TypeScript)
   web/               Next.js ウェブビルダー
     src/app/         Landing + Builder + Directory ページ

package/README.ko.md

@@ -5,7 +5,7 @@
 <h1 align="center">oh-my-design</h1>
 
 <p align="center">
-  <strong>67개 기업 디자인 시스템 기반 DESIGN.md 생성기.</strong> 인터랙티브 위자드. AI 호출 없음.
+  <strong>88개 기업 디자인 시스템 기반 DESIGN.md 생성기.</strong> 인터랙티브 위자드. AI 호출 없음.
 </p>
 
 <p align="center">
@@ -17,7 +17,7 @@
   <a href="https://www.npmjs.com/package/oh-my-design-cli"><img src="https://img.shields.io/npm/dm/oh-my-design-cli?style=flat-square&color=cb3837" alt="npm downloads" /></a>
   <a href="LICENSE"><img src="https://img.shields.io/github/license/kwakseongjae/oh-my-design?style=flat-square" alt="License" /></a>
   <a href="https://github.com/kwakseongjae/oh-my-design/stargazers"><img src="https://img.shields.io/github/stars/kwakseongjae/oh-my-design?style=social" alt="GitHub Stars" /></a>
-  <img src="https://img.shields.io/badge/references-67-7c5cfc?style=flat-square" alt="67 References" />
+  <img src="https://img.shields.io/badge/references-88-7c5cfc?style=flat-square" alt="88 References" />
   <img src="https://img.shields.io/badge/AI%20calls-zero-blue?style=flat-square" alt="Zero AI" />
 </p>
 
@@ -37,7 +37,7 @@
 
 1. **[스펙](spec/omd-v0.1.md)** — 버전 관리되는 Google Stitch 확장, MIT 라이선스.
 2. **[Claude Code 스킬](.claude/skills/omd/SKILL.md)** — 스펙을 하드 제약으로 자동 적용.
-3. **[67개 레퍼런스](references/)** — 실제 기업의 `DESIGN.md` 파일들을 포크하고, 빌더로 커스터마이징해 바로 씁니다.
+3. **[88개 레퍼런스](references/)** — 실제 기업의 `DESIGN.md` 파일들을 포크하고, 빌더로 커스터마이징해 바로 씁니다.
 
 **API 키 불필요. AI 호출 없음. 모두 클라이언트 사이드.**
 
@@ -162,10 +162,10 @@ Toss · Claude · Line · Stripe · Linear · Vercel · Notion · Airbnb · Appl
 ## 주요 구성
 
 - **빌더** — 레퍼런스 선택 후 색상 / radius / 다크 모드를 조정하고, 컴포넌트를 고른 뒤 Export. **Philosophy** 필터로 완전한 브랜드 철학을 담은 10개만 볼 수 있어요.
-- **디자인 시스템 디렉토리** ([oh-my-design.kr/design-systems](https://oh-my-design.kr/design-systems)) — 67개 레퍼런스 중 34개는 공식 디자인 시스템 또는 브랜드 가이드라인 페이지가 있으며, 디렉토리에서 라이브 썸네일과 함께 바로 이동할 수 있습니다.
-- **Personal Curation** ([oh-my-design.kr/curation](https://oh-my-design.kr/curation)) — MBTI 스타일의 짧은 퀴즈로 당신의 디자인 성향을 67개 레퍼런스 중 하나와 매칭해, 해당 레퍼런스가 미리 선택된 빌더로 바로 이동시켜 줍니다.
+- **디자인 시스템 디렉토리** ([oh-my-design.kr/design-systems](https://oh-my-design.kr/design-systems)) — 88개 레퍼런스 중 34개는 공식 디자인 시스템 또는 브랜드 가이드라인 페이지가 있으며, 디렉토리에서 라이브 썸네일과 함께 바로 이동할 수 있습니다.
+- **Personal Curation** ([oh-my-design.kr/curation](https://oh-my-design.kr/curation)) — MBTI 스타일의 짧은 퀴즈로 당신의 디자인 성향을 88개 레퍼런스 중 하나와 매칭해, 해당 레퍼런스가 미리 선택된 빌더로 바로 이동시켜 줍니다.
 
-## 67개 지원 레퍼런스
+## 88개 지원 레퍼런스
 
 | 카테고리 | 기업 |
 |----------|------|
@@ -213,7 +213,7 @@ Toss · Claude · Line · Stripe · Linear · Vercel · Notion · Airbnb · Appl
 oh-my-design/
   spec/              OmD v0.1 스펙 (정본)
   .claude/skills/omd/ Claude Code 스킬 번들
-  references/        67개 기업 DESIGN.md 파일
+  references/        88개 기업 DESIGN.md 파일
   src/               CLI 코어 (TypeScript)
   web/               Next.js 웹 빌더
     src/app/         Landing + Builder + Directory 페이지

package/README.md

@@ -5,7 +5,7 @@
 <h1 align="center">oh-my-design</h1>
 
 <p align="center">
-  <strong>One-command bootstrap for skill-driven design with your AI coding agent.</strong> 67 real company design systems. Zero AI calls in the install. Then you just talk to your agent.
+  <strong>One-command bootstrap for skill-driven design with your AI coding agent.</strong> 88 real company design systems. Zero AI calls in the install. Then you just talk to your agent.
 </p>
 
 <p align="center">
@@ -13,24 +13,23 @@
   <a href="https://www.npmjs.com/package/oh-my-design-cli"><img src="https://img.shields.io/npm/dm/oh-my-design-cli?style=flat-square&color=cb3837" alt="npm downloads" /></a>
   <a href="LICENSE"><img src="https://img.shields.io/github/license/kwakseongjae/oh-my-design?style=flat-square" alt="License" /></a>
   <a href="https://github.com/kwakseongjae/oh-my-design/stargazers"><img src="https://img.shields.io/github/stars/kwakseongjae/oh-my-design?style=social" alt="GitHub Stars" /></a>
-  <img src="https://img.shields.io/badge/references-67-7c5cfc?style=flat-square" alt="67 References" />
+  <img src="https://img.shields.io/badge/references-88-7c5cfc?style=flat-square" alt="88 References" />
   <img src="https://img.shields.io/badge/CLI%20commands-1-blue?style=flat-square" alt="One CLI command" />
 </p>
 
 ---
 
-## What is this?
+## What is oh-my-design?
 
 **oh-my-design (OmD)** turns your AI coding agent (Claude Code / Codex / OpenCode / Cursor) into a senior product designer with a working memory of your brand. You install once. After that, you just describe what you want — components, screens, copy, assets, charts — and the agent applies your project's design system, picks the right asset medium, and ships.
 
-`DESIGN.md` is the brand spec ([Google Stitch](https://stitch.withgoogle.com/docs/design-md/overview/) tokens + the OmD v0.1 brand-philosophy layer: Voice / Narrative / Principles / Personas / States / Motion). 67 real-company DESIGN.md files ship in this package. Pick one, customize through conversation, ship.
+`DESIGN.md` is the brand spec ([Google Stitch](https://stitch.withgoogle.com/docs/design-md/overview/) tokens + the brand-philosophy layer: Voice / Narrative / Principles / Personas / States / Motion). 88 real-company DESIGN.md files ship in this package. Pick one, customize through conversation, ship.
 
 **No API keys. No external infra. Everything runs inside your existing CLI session.**
 
 ## Install
 
 ```bash
-cd my-project
 npx oh-my-design-cli install-skills
 ```
 
@@ -38,12 +37,12 @@ Then restart your agent (Cmd+Q in Claude Code, then relaunch) so the new skills
 
 That is the only CLI command you will run. Everything else is natural language to your agent.
 
-## How you use it
+## How to use omd with your AI
 
 Open Claude Code (or Codex / OpenCode) in your project. Just talk:
 
 > "Set up the design system for a calm B2B fintech dashboard."
-> Agent picks a reference from 67 (likely Linear or Stripe), proposes a hybrid DESIGN.md, asks for confirmation, writes the file plus shims.
+> Agent picks a reference from 88 (likely Linear or Stripe), proposes a hybrid DESIGN.md, asks for confirmation, writes the file plus shims.
 
 > "Make the empty-state for the search results page."
 > Agent reads DESIGN.md, builds the component with brand tokens, picks an inline SVG illustration matching the voice, drops in microcopy that follows the §10 voice rules.
@@ -60,7 +59,7 @@ Open Claude Code (or Codex / OpenCode) in your project. Just talk:
 > "We never use uppercase CTAs."
 > Agent silently appends to `.omd/preferences.md`. Next time anyone makes a CTA, that rule applies. Later you can say "fold preferences into DESIGN.md" and the agent merges by scope.
 
-## What gets installed
+## What's in the install
 
 | Path | Owner | Purpose |
 |---|---|---|
@@ -68,10 +67,10 @@ Open Claude Code (or Codex / OpenCode) in your project. Just talk:
 | `.codex/skills/omd-*/SKILL.md` | install-skills | Codex skill bundle |
 | `.opencode/agents/omd-*.md` | install-skills | OpenCode agent bundle |
 | `.claude/agents/omd-*.md` | install-skills | 11 canonical sub-agents (master + 10 specialists) |
-| `.claude/data/*` | install-skills | 67-reference fingerprints, vocabulary, opt-out corpus |
+| `.claude/data/*` | install-skills | 88-reference fingerprints, vocabulary, opt-out corpus |
 | `.claude/hooks/*.cjs` | install-skills | UserPromptSubmit / SessionStart / PostToolUse hooks |
 | `.claude/skills/skill-rules.json` | install-skills | Skill activation rules |
-| `references/*/DESIGN.md` | bundled | 67 real design systems |
+| `references/*/DESIGN.md` | bundled | 88 real design systems |
 | `DESIGN.md` | your agent (after init flow) | Your project's authoritative brand spec |
 | `CLAUDE.md` / `AGENTS.md` / `.cursor/rules/omd-design.mdc` | omd-sync skill | Pointers so every agent reads DESIGN.md |
 | `.omd/preferences.md` | omd-remember skill | Append-only design correction log |
@@ -82,7 +81,7 @@ Open Claude Code (or Codex / OpenCode) in your project. Just talk:
 Skills (loaded into your agent's context based on prompt triggers):
 
 - **omd:apply** — DESIGN.md as authoritative context for every UI task. Routes complex requests (assets, charts, full screens, a11y audit) to specialized sub-agents.
-- **omd:init** — Bootstrap DESIGN.md from a reference + project description. 67 references, hybrid variation that preserves the reference voice while shifting only user-named axes.
+- **omd:init** — Bootstrap DESIGN.md from a reference + project description. 88 references, hybrid variation that preserves the reference voice while shifting only user-named axes.
 - **omd:harness** — `/omd-harness <task>` to run the 10-phase design pipeline with checkpoints. Spawns sub-agents in parallel.
 - **omd:remember** — Captures user corrections to `.omd/preferences.md` automatically when the agent detects them.
 - **omd:learn** — Folds pending corrections back into DESIGN.md by scope.
@@ -102,18 +101,16 @@ Sub-agents — 1 orchestrator + 10 specialists (invoked by the master or directl
 - **omd-persona-tester** — Adversarial 4-persona walkthrough (V/J/F/S). sonnet.
 - **omd-critic** — Root-cause analysis when the user iterates. opus.
 
-## What 1.0.0 is not
+## What it is not
 
 - It is not a collection of CLI commands. There is one bootstrap command. Everything else is skill prose.
-- It is not an SDK. The `dist/index.js` programmatic API is gone. If you need the matching algorithm or shim format, look at the skill markdown directly.
+- It is not an SDK. If you need the matching algorithm or shim format, look at the skill markdown directly.
 - It does not generate emojis as icons. Asset agent prefers inline SVG (Lucide-matched or custom).
 
-If you were on 0.1.x: see [MIGRATION.md](MIGRATION.md). All your old CLI commands are now spoken to your agent.
+## Changelog
 
-## Status
-
-`v1.0.0` — first skill-first release. Surface area collapsed by ~92% versus 0.1.x. Stable for the install bootstrap; the harness is improving every release as the agent prose tightens.
+See [CHANGELOG.md](CHANGELOG.md) for release history. Migrating from 0.1.x: see [MIGRATION.md](MIGRATION.md).
 
 ## License
 
-MIT. References belong to their respective companies — they are reproduced for educational reference.
+MIT — see [LICENSE](LICENSE). References belong to their respective companies; reproduced for educational reference.

package/README.zh-TW.md

@@ -5,7 +5,7 @@
 <h1 align="center">oh-my-design</h1>
 
 <p align="center">
-  <strong>從 67 家真實企業的設計系統生成 DESIGN.md。</strong>互動式精靈。零 AI 呼叫。
+  <strong>從 88 家真實企業的設計系統生成 DESIGN.md。</strong>互動式精靈。零 AI 呼叫。
 </p>
 
 <p align="center">
@@ -17,7 +17,7 @@
   <a href="https://github.com/kwakseongjae/oh-my-design/stargazers"><img src="https://img.shields.io/github/stars/kwakseongjae/oh-my-design?style=social" alt="GitHub Stars" /></a>
   <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square" alt="PRs Welcome" />
   <img src="https://img.shields.io/badge/AI%20calls-zero-blue?style=flat-square" alt="Zero AI" />
-  <img src="https://img.shields.io/badge/references-67-7c5cfc?style=flat-square" alt="67 References" />
+  <img src="https://img.shields.io/badge/references-88-7c5cfc?style=flat-square" alt="88 References" />
 </p>
 
 <p align="center">
@@ -36,7 +36,7 @@
 
 1. **[規範](spec/omd-v0.1.md)** — 版本化的 Google Stitch 擴充,MIT 授權。
 2. **[Claude Code skill](.claude/skills/omd/SKILL.md)** — 將規範作為硬性約束自動套用。
-3. **[67 個參考檔案](references/)** — 真實企業的 `DESIGN.md`,可以 fork、透過 builder 客製化後直接上線。
+3. **[88 個參考檔案](references/)** — 真實企業的 `DESIGN.md`,可以 fork、透過 builder 客製化後直接上線。
 
 **無須 API 金鑰。零 AI 呼叫。全部在客戶端執行。**
 
@@ -61,10 +61,10 @@ Toss · Claude · Line · Stripe · Linear · Vercel · Notion · Airbnb · Appl
 ## 主要功能
 
 - **Builder** — 選擇參考、調整色彩 / radius / 深色模式、挑選元件,然後按下 Export。透過 **Philosophy** 篩選可以只顯示具備完整品牌哲學的 10 個參考。
-- **Design Systems 目錄** ([oh-my-design.kr/design-systems](https://oh-my-design.kr/design-systems)) — 67 個參考中有 34 個擁有官方設計系統或品牌指南頁面,可從目錄配合即時縮圖直接前往。
-- **Personal Curation** ([oh-my-design.kr/curation](https://oh-my-design.kr/curation)) — 透過 MBTI 風格的簡短測驗,將你的設計偏好對應到 67 個參考之一,並直接帶你進入已預選該參考的 Builder。
+- **Design Systems 目錄** ([oh-my-design.kr/design-systems](https://oh-my-design.kr/design-systems)) — 88 個參考中有 34 個擁有官方設計系統或品牌指南頁面,可從目錄配合即時縮圖直接前往。
+- **Personal Curation** ([oh-my-design.kr/curation](https://oh-my-design.kr/curation)) — 透過 MBTI 風格的簡短測驗,將你的設計偏好對應到 88 個參考之一,並直接帶你進入已預選該參考的 Builder。
 
-## 67 個支援的參考
+## 88 個支援的參考
 
 | 類別 | 企業 |
 |------|------|
@@ -112,7 +112,7 @@ Toss · Claude · Line · Stripe · Linear · Vercel · Notion · Airbnb · Appl
 oh-my-design/
   spec/              OmD v0.1 規範 (正本)
   .claude/skills/omd/ Claude Code skill 包
-  references/        67 家企業的 DESIGN.md 檔案
+  references/        88 家企業的 DESIGN.md 檔案
   src/               CLI 核心 (TypeScript)
   web/               Next.js 網頁 builder
     src/app/         Landing + Builder + Directory 頁面

package/agents/omd-ux-writer.md

@@ -53,7 +53,7 @@ target이 wireframe markdown이면 `## Section` heading으로 분리.
 
 ### 4. Specificity
 - 광범위 단어 ("amazing", "powerful", "innovative") 카운트 — 3개 이상이면 fail
-- 측정 가능한 claim ("under 2 seconds", "67 references", "zero AI calls")가 있는가?
+- 측정 가능한 claim ("under 2 seconds", "실제 기업 references", "zero AI calls")가 있는가?
 - 모호한 형용사를 구체 수치로 대체 가능?
 
 ### 5. Verb strength (특히 CTA)

package/data/architecture-proposals/2026-05-13-thin-install-fresh-fetch.md

@@ -0,0 +1,189 @@
+# Thin install + fresh fetch (WebFetch + MCP)
+
+**Status**: proposed — not implemented
+**Author context**: 2026-05-13 conversation, after KR-10 batch
+**Motivation**: npm publish on every brand addition is high-friction and produces stale installs
+
+---
+
+## Problem statement
+
+Current `oh-my-design-cli` package bundles 88 brand DESIGN.md files (~12MB) and ships them via npm.
+
+**Pain points observed**:
+1. Every batch (10 brands) requires `npm publish` to reach end users
+2. Users installed at count N keep seeing N brands forever, even after we add more
+3. Skill descriptions historically baked the count (`"67개 ..."`) — required re-edit per batch, easy to forget (we forgot in the 78 release; observed again at 88)
+4. Bundle grows linearly; cold install time scales
+5. Single brand typo fix = minor version bump + publish
+
+**Decided 2026-05-13**: skill descriptions are now **count-agnostic** ("실제 기업 레퍼런스" without a number). Won't regress this kind of bug again. But the fundamental delivery model still needs reform.
+
+---
+
+## Proposed architecture
+
+Hybrid: **thin npm baseline + fresh fetch at runtime**.
+
+```
+npm package (thin, ~500KB)
+├─ skills/                       (routing logic, count-agnostic)
+├─ data/reference-fingerprints.json   (metadata only — id, category, primary, tone keywords)
+├─ data/snapshot-date.txt        ("baseline 2026-05-13")
+├─ hooks/, agents/, bin/         (unchanged)
+└─ (no DESIGN.md bundled — fetched at runtime)
+
+Runtime (skill execution in user's agent)
+1. Match brand via local fingerprints.json (offline-capable)
+2. Fetch full DESIGN.md from:
+   - Primary:  WebFetch  https://oh-my-design.kr/api/references/<id>/design-md
+   - MCP path: omd_get_designmd(id)        (if MCP server connected)
+   - Fallback: bundled (if shipped — optional Phase 3 decision)
+3. Apply, write to project DESIGN.md
+```
+
+**Outcome**:
+- New brand batch → `git push` web + git commit fingerprints; **no npm publish**
+- Users see new brands on next skill call (no reinstall)
+- npm publish frequency drops to "skill behavior changes" (<1/month)
+- Marketing copy (READMEs) still updates count per batch — that's intentional
+
+---
+
+## Implementation phases
+
+### Phase 1 — Backend HTTP endpoint (~1h)
+
+`web/src/app/api/references/[id]/design-md/route.ts`:
+```ts
+import { readFileSync } from 'fs';
+import { join } from 'path';
+import { NextRequest, NextResponse } from 'next/server';
+
+export async function GET(_req: NextRequest, { params }: { params: { id: string } }) {
+  try {
+    const md = readFileSync(join(process.cwd(), 'references', params.id, 'DESIGN.md'), 'utf-8');
+    return new NextResponse(md, {
+      headers: {
+        'Content-Type': 'text/markdown; charset=utf-8',
+        'Cache-Control': 'public, max-age=300, s-maxage=3600',
+        'Access-Control-Allow-Origin': '*',
+        'ETag': `"${md.length}-${md.slice(-32)}"`,
+      },
+    });
+  } catch {
+    return NextResponse.json({ error: 'not found' }, { status: 404 });
+  }
+}
+```
+
+Smoke test: `curl https://oh-my-design.kr/api/references/kakaopay/design-md | head -20`
+
+### Phase 2 — MCP server (~3h, parallel with Phase 1)
+
+New package `oh-my-design-mcp` (separate npm package).
+
+Tools exposed:
+| Tool | Args | Returns |
+|---|---|---|
+| `omd_search_references` | `{ query, top_k? }` | top-N brand fingerprints (id, score, why) |
+| `omd_get_designmd` | `{ id }` | full DESIGN.md markdown |
+| `omd_list_categories` | — | category → ids map |
+| `omd_get_snapshot_date` | — | "2026-05-13" (for staleness check) |
+
+Resources exposed (MCP resources, browsable):
+- `omd://references` — list all
+- `omd://references/<id>` — single DESIGN.md
+
+Server reads from same HTTP endpoint internally (single source of truth) OR direct disk if self-hosted.
+
+Distribution: `npx -y oh-my-design-mcp` in MCP config:
+```json
+{
+  "mcpServers": {
+    "oh-my-design": { "command": "npx", "args": ["-y", "oh-my-design-mcp"] }
+  }
+}
+```
+
+### Phase 3 — Skill updates (~1h)
+
+`skills/omd-init/SKILL.md`, `skills/omd-harness/SKILL.md`:
+
+```diff
+- Phase 4: fetch reference DESIGN.md from .claude/data/references/<id>/DESIGN.md
++ Phase 4: fetch reference DESIGN.md (priority order):
++   a) If MCP `oh-my-design` connected: call omd_get_designmd(id)
++   b) Else WebFetch https://oh-my-design.kr/api/references/<id>/design-md
++   c) Else (offline): bundled .claude/data/references/<id>/DESIGN.md if present
++   d) Else: report "id not in catalog, network unavailable, no bundle"
+```
+
+Skill must also surface the snapshot date to the user when fetching offline:
+> "오프라인 모드 — 2026-05-13 기준 카탈로그 사용 중. 최신 brand 보려면 인터넷 연결 후 재시도."
+
+### Phase 4 — Bundle diet (~30m, optional)
+
+`package.json`:
+```diff
+"files": [
+  "dist",
+  "skills/*",
+  "agents",
+  "data",
+- "web/references/*/DESIGN.md",
++ "data/snapshot-date.txt",
+  ".claude/hooks/*.cjs",
+  ".claude/settings.json"
+]
+```
+
+`scripts/postinstall.cjs`: stop copying DESIGN.md files into `.claude/data/references/`. Skills will fetch.
+
+**Trade-off**: completely offline-broken if API down. Mitigation: optional flag `--bundle-references` for users who want offline guarantee.
+
+### Phase 5 — `omd:batch-launch` SKILL update (~15m)
+
+Phase 3 SYNC:
+- Remove `npm publish` from suggested follow-ups
+- Add note: "After git push, brand reaches users automatically via API"
+- Marketing surfaces (README count, llms.txt count) still need batch sync since they're static
+
+---
+
+## Migration plan
+
+1. **Phase 1 first** (backend endpoint) — non-breaking, just adds capability
+2. **Phase 2 in parallel** (MCP) — non-breaking, separate package
+3. **Phase 3** (skill update) — backward-compat: tries MCP → WebFetch → bundle, so old installs still work
+4. **Phase 4 last** (bundle diet) — only after Phase 3 has shipped for 1-2 weeks and we confirm fetch reliability
+5. **Phase 5** (omd:batch-launch update) — final cleanup after migration is stable
+
+---
+
+## Open questions
+
+- **Authentication**: keep API public read? (Yes — DESIGN.md files are intended for public consumption, that's the product.)
+- **Rate limit**: needed? (Probably basic per-IP at edge — Vercel/Cloudflare. Not critical for v1.)
+- **Versioning of DESIGN.md content**: should the API return a `?version=YYYY-MM-DD` parameter so installs can pin? (Defer — KISS for v1.)
+- **Caching**: should the skill cache fetched DESIGN.md locally per session? (Yes — agent runtime should cache the parsed result for the session.)
+- **What about agent that has no WebFetch tool?** (Edge case. Codex CLI has it. Cursor has it via tool config. If a user's agent really has neither WebFetch nor MCP, they install the `--bundle-references` flag at install time.)
+
+---
+
+## When to do this
+
+**Trigger**: next time the user mentions "10개 더" or any brand addition. Pause Phase 2 build, ship the architecture first, then resume.
+
+**Or**: after 2 more batches (100, 110 brands), npm package bundle pain becomes hard to ignore — natural breakpoint.
+
+**Not now**: this conversation closed with count-agnostic skill descriptions as the immediate fix. Architecture is tracked but not implemented yet.
+
+---
+
+## Reading list / inspirations
+
+- Linear's hosted catalog approach (linear.app/docs API)
+- Tailwind v4 CDN-first delivery model
+- shadcn/ui's "components are not a package, they're snippets you copy" — opposite direction but instructive
+- MCP spec: `https://modelcontextprotocol.io/`

package/data/reference-audits/2026-05-13-kr10.md

@@ -0,0 +1,132 @@
+# Batch Audit — 2026-05-13 / KR-10
+
+**Theme**: Korean IT companies with publicly observable design system signal
+**Brands added**: 10 (78 → 88)
+**Skill**: `omd:batch-launch` (Phase 2 build pipeline = `omd:add-reference` CREATE)
+**Verification date**: 2026-05-13
+
+---
+
+## How the 10 were researched (pipeline applied to each)
+
+Every brand went through the standard `omd:add-reference` CREATE 3-tier pipeline. Each `omd-batch-launch` subagent was constrained to:
+
+1. **Tier 1 — Live inspect (required)**: playwright MCP `getComputedStyle` on hero CTA / nav / footer / input / cards across **≥1 surface** of the brand's production site. Where possible, also `curl` of the production CSS bundle (more authoritative than runtime sampling because it exposes the entire token system).
+2. **Tier 2 — Cross-check (both attempted)**: `getdesign.md/<id>` + `styles.refero.design/?q=<brand>` (also `?q=<한글명>`). Either source success = OK; both empty = explicitly logged in §4 footer.
+3. **Tier 3 — Reconcile + write**: 9 product sections (Stripe schema) + §10-15 philosophy (Toss §10-15 shape) + `_research.md` source map + `_promo.json` highlight + verified footer.
+
+Every brand also has:
+- `web/references/<id>/DESIGN.md` (the spec, frontmatter `omd: 0.1`)
+- `web/references/<id>/_research.md` (Tier-by-Tier source list + dates + confidence per section)
+- `web/references/<id>/_promo.json` (id, Korean name, logo URL, single "most striking" highlight for promo video)
+- §4 footer with `**Verified:** 2026-05-13` + Tier 1 sources + Tier 2 status + Conflicts unresolved
+
+---
+
+## Systemic finding
+
+**Tier 2 directories (`getdesign.md`, `styles.refero.design`) have weak Korean coverage**. All 10 brands returned **empty** on both 3rd-party indexes. This is not a brand-quality issue — it's a directory-bias issue (both are English-tooling-oriented). Documented per-brand in §4 footers.
+
+**But brand-published DS / design narrative resources DO exist for most of the 10** — they were just not in those 3rd-party indexes. 7/10 have public DS-related surfaces that were used in Tier 1 reconcile:
+
+| brand | brand-published DS surface | type | live (2026-05-13) |
+|---|---|---|---|
+| socar | `design.socar.kr` | docs hub | ✅ 200 |
+| wanted | `montage.wanted.co.kr` + `wanted.co.kr/brandcenter` | full DS | ✅ 200 |
+| remember | `dramancompany.github.io/remember-ui` | Storybook | ✅ 200 |
+| banksalad | `github.com/banksalad` (org + styleguide repos) | source | ✅ 200 |
+| zigzag | `brunch.co.kr/@zigzag/73` + `devblog.kakaostyle.com` | brand articles (ZDS) | ✅ 200 |
+| gangnamunni | `blog.gangnamunni.com/post/welchis/` | DS architecture post | ✅ 200 |
+| kakaopay | `story.kakaopay.com` | brand / design narrative | ✅ 200 |
+| 29cm | — | — | ❌ no public DS |
+| ably | — | — | ❌ no public DS |
+| zigbang | — | — | ❌ no public DS |
+
+→ For future Korean batches, weight Tier 1 (live inspect + **brand-owned tech blogs / brunch / medium / GitHub orgs**) more heavily. Tier 2 (3rd-party directories) is documentation discovery, not validation.
+
+→ The 7 brand-published DS URLs are also registered in `web/src/lib/design-systems.ts` so they surface as DS buttons in Browse modal and Builder Step 3 preview header. The 3 brands without a public DS correctly return null and the DS button stays hidden.
+
+---
+
+## Per-brand audit
+
+Confidence rubric:
+- **High** — ≥2 Tier 1 surfaces OR production CSS bundle captured; no unresolved hex; ≥3 supporting brand-owned sources (blog/medium/brunch); §10-15 sourced
+- **Medium** — 1 Tier 1 surface; some inferred values; brand-owned philosophy sources present
+- **Low** — Tier 1 partially blocked; key tokens marked `(unverified live)` or `(illustrative)`; needs UPDATE pass
+
+| # | id | confidence | Tier 1 depth | Tier 2 | Known gaps | Follow-up |
+|---|----|------------|--------------|--------|------------|-----------|
+| 1 | socar | **Medium** | 1 surface (home full); design.socar.kr partial (browser session contended) | empty (getdesign no record · refero no isolated set) | SOCAR Blue **exact hex unpublished** — brand-name-only reference. Brand fonts Sandoll Gothic Neo2 / Avenir (print) vs live Pretendard (web) — documented as intentional print-vs-web split. | UPDATE pass on `design.socar.kr` for canonical SOCAR Blue hex + Space Frame system tokens |
+| 2 | gangnamunni | **High** | 3 (home live + production CSS bundle `d246c5b2edcb00b6.css` with full Cell token map + blog.gangnamunni.com Cell+Welchis architecture post) | empty | none material | — |
+| 3 | kakaopay | **Medium** | 1 surface (home full live inspect); /payment/online second surface blocked by browser tab contention | empty (both verified empty) | none unresolved. KPDS = narrative-only on `story.kakaopay.com`, no public docs site. | UPDATE pass on /payment/online or /transfer for second surface verification |
+| 4 | zigzag | **High** | 4 (home live + production CSS bundle 184KB with full ZDS canonical tokens via `--zds-color-*` vars + devblog.kakaostyle.com ZDS rearchitecture + brunch.co.kr/@zigzag/73 brand-owned) | empty | Two-pink architecture (`#fa6ee3` brand-anchor vs `#f55dd6` interactive primary) — documented as intentional role split | — |
+| 5 | 29cm | **Medium** | 1 surface (home via isolated Playwright `browser_run_code_unsafe` workaround for session contention) | empty | PDP / checkout flows not inspected this pass | UPDATE pass on PDP + checkout (editorial product story modules) |
+| 6 | ably | **Low** | 1 navigation only — live `evaluate` calls blocked by Playwright session contention; §4 token hexes flagged `(unverified live)` in footer | empty / inconclusive (refero JS-rendered, capture blocked) | §4 token values need live re-capture. Brand disambiguation note added (Ably Corp KR commerce ≠ ably.com realtime API). | **Priority**: full Phase U2 live inspect re-run on a clean Playwright session |
+| 7 | banksalad | **High** | 5 (home live + 865KB production CSS bundle with `border-radius:2px` ×81 confirming system default + BPL tech blog + 2× GitHub orgs) | empty (both verified empty) | One nav exception documented (sign-in pill at 16px radius vs system 2px default) — already noted as exception, not conflict | — |
+| 8 | zigbang | **Medium** | 2 (home full + /home/apt/map partial — map-overlay listing card tokens inferred due to second-pass contention) | empty | (a) **brand-orange exact hex unpublished** — `~#FF6600` flagged illustrative in §2 + footer; (b) map-overlay listing-card / price-chip tokens inferred | UPDATE pass on /home/apt/map for canonical orange hex + listing-card token verification |
+| 9 | wanted | **High** | 8 sources (live DOM on `wdlist/518` 22 samples + brandcenter + Montage docs + wanted-sans GitHub + wanteddev org + wantedlab.com + WDS creation blog) | empty (refero blocked by session contention, getdesign verified empty) | none unresolved. `#14191E` (marketing) vs `#171719` (product) is documented two-surface split, not a conflict. | (optional) refero re-attempt on clean session |
+| 10 | remember | **High** | 5 (career page primary live inspect + `dramancompany.github.io/remember-ui/` Storybook root + corp x2 + redirect) | empty (3rd-party empty + GitHub UI repo 404 — source private/deleted, Storybook deploy still live) | (a) filter-chip **selected/active** state not observed (only default captured); (b) error/warning semantic tokens inferred from KR fintech convention | UPDATE pass capturing filter chip selected/active + error/warning states |
+
+---
+
+## Confidence distribution
+
+- **High** (5): gangnamunni, banksalad, wanted, zigzag, remember
+- **Medium** (3): socar, 29cm, kakaopay
+- **Low** (1): ably
+- *(zigbang was kept at Medium even though 2 surfaces inspected, because of 2 unresolved illustrative tokens — orange hex + map overlay)*
+
+**Aggregate**: 5/10 are publishable as-is. 3/10 are publishable with marked uncertainty. **2/10 (ably + zigbang) warrant a follow-up UPDATE pass before being cited in external blog posts or comparisons.**
+
+---
+
+## Known shared limitation — Playwright session contention
+
+The Phase 2 build ran 10 subagents in parallel, all sharing the host Playwright MCP browser. Several agents reported that `browser_evaluate` calls landed on *other agents' tabs* (kakaopay/zigzag/banksalad/29cm appear in multiple reports as "the tab that hijacked my session"). Mitigations applied per agent:
+
+- Fall back to direct `curl` of the production CSS bundle (banksalad, gangnamunni, zigzag) — actually higher signal than runtime sampling for these
+- Use `browser_run_code_unsafe` in isolated newPage context (29cm)
+- Document and explicitly flag affected surfaces in `_research.md` (ably, kakaopay, zigbang)
+
+**Process fix for next batch**: serialize Playwright sessions per brand (run 1-2 in parallel, not 10), OR isolate to `--user-data-dir` per agent if available. Cost: longer wall-clock. Benefit: no contention, clean §4 token values for every brand.
+
+---
+
+## Promo highlight selection (auditable)
+
+Each brand's `_promo.json` records a single "most striking" element — chosen by the build subagent and used in the promo MP4. Type distribution:
+
+- **palette** (7): socar, gangnamunni, zigzag, ably, banksalad, zigbang, wanted
+- **voice** (2): kakaopay, 29cm
+- **cta** (1): remember
+
+Justifications are written into each `_promo.json` (`label` field) and re-verified during Phase 4 composition build.
+
+---
+
+## Follow-up TODO (prioritized)
+
+1. **ably** — full Phase U2 live inspect re-run (clean session). §4 tokens currently `(unverified live)`.
+2. **zigbang** — UPDATE pass on `/home/apt/map` for canonical orange hex + map-overlay tokens.
+3. **socar** — UPDATE pass on `design.socar.kr` for canonical SOCAR Blue hex + Space Frame token system.
+4. **remember** — UPDATE pass capturing filter-chip selected/active + error/warning semantic tokens.
+5. **29cm** — UPDATE pass on PDP + checkout flows.
+6. **kakaopay** — UPDATE pass on a transactional second surface (e.g., /transfer).
+7. **reader UI**: long variant headings overlap preview area (observed on 29cm §5). Fix in `web/src/components/reference-preview.tsx` (or equivalent).
+8. **Process**: serialize Playwright sessions per build agent for future batches.
+
+---
+
+## Schema for this file (future batches use the same shape)
+
+Required top-level sections (so they're greppable across batches in `data/reference-audits/`):
+- `## How the 10 were researched`
+- `## Systemic finding`
+- `## Per-brand audit` (table with id, confidence, Tier 1 depth, Tier 2, Known gaps, Follow-up)
+- `## Confidence distribution`
+- `## Known shared limitation`
+- `## Promo highlight selection`
+- `## Follow-up TODO`
+
+Filename: `data/reference-audits/<YYYY-MM-DD>-<batch-slug>.md`