oh-my-design-cli 1.6.7 → 1.7.1

package/README.ko.md

@@ -50,24 +50,15 @@
 ```bash
 cd my-project
 
-# 1. 한 번만: 에이전트 스킬 설치 (.claude/skills, .codex/skills, .opencode/agents)
+# 한 번만: 에이전트 스킬 + 에이전트 설치 (.claude/skills, .codex/skills, .opencode/agents)
 npx oh-my-design-cli install-skills
+```
 
-# 2. 레퍼런스 + 프로젝트 description으로 DESIGN.md 부트스트랩
-#    (Claude Code/Codex/OpenCode 안에서 omd:init 스킬이 이 단계를 주도)
-npx oh-my-design-cli init recommend "warm approachable B2C marketplace"
-npx oh-my-design-cli init prepare --ref airbnb --description "warm approachable B2C marketplace"
-
-# 3. 4개 에이전트가 DESIGN.md를 읽도록 shim 파일 생성/갱신
-npx oh-my-design-cli sync
+설치가 끝나면 나머지는 전부 **에이전트에게 자연어로** 말하면 됩니다 — 별도의 CLI 서브커맨드가 아니라 스킬이 파일을 직접 Read/Write/Bash 하며 처리합니다.
 
-# 4. 작업 중 에이전트가 디자인 선택을 잘못하면 즉시 기록
-npx oh-my-design-cli remember "CTAs are never uppercase"
-
-# 5. 누적된 preference를 DESIGN.md에 일괄 반영
-npx oh-my-design-cli learn                            # pending 보기
-npx oh-my-design-cli learn --mark-applied <id>        # 반영 완료 표시
-```
+- **DESIGN.md 부트스트랩 + 레퍼런스 추천**: Claude Code/Codex/OpenCode 안에서 `omd:init` 스킬에게 요청하세요. 예: "warm approachable B2C marketplace로 DESIGN.md 만들어줘" → 스킬이 레퍼런스를 추천하고 프로젝트 description을 모아 DESIGN.md를 작성합니다.
+- **shim 파일 생성/갱신**: `omd:sync` 스킬이 4개 에이전트가 DESIGN.md를 읽도록 `CLAUDE.md` / `AGENTS.md` / `.cursor/rules` shim을 유지합니다 ("shim 동기화해줘").
+- **디자인 교정 기록 + 반영**: `omd:remember`로 preference를 append하고, `omd:learn`으로 누적된 preference를 DESIGN.md에 일괄 반영합니다.
 
 **또는 글로벌 설치 (짧은 커맨드):**
 
@@ -75,27 +66,25 @@ npx oh-my-design-cli learn --mark-applied <id>        # 반영 완료 표시
 npm install -g oh-my-design-cli
 # 이제 'oh-my-design' 또는 단축 별칭 'omd' 사용 가능
 omd install-skills
-omd sync
-omd remember "..."
 ```
 
-> **상태**: `v0.1.0`은 첫 ecosystem 릴리스. CLI 표면(sync / remember / learn / init prepare / install-skills)은 안정 + 단위 테스트 완료. 에이전트 측 Hybrid variation 품질은 호스트 LLM이 `omd:init` 스킬 프롬프트를 얼마나 잘 따르는지에 좌우됩니다 — 결과가 만족스럽지 않으면 archive와 함께 이슈로 보고 부탁드려요.
+> **상태**: 첫 ecosystem 릴리스. 안정적인 CLI 표면은 `install-skills` 하나뿐입니다 — 스킬·에이전트를 프로젝트에 설치/갱신하는 역할. 그 외 모든 동작(DESIGN.md 부트스트랩, 레퍼런스 추천, shim 동기화, preference 기록·반영)은 **스킬 주도**로, 에이전트가 파일을 직접 편집해 수행합니다. 에이전트 측 Hybrid variation 품질은 호스트 LLM이 `omd:init` 스킬 프롬프트를 얼마나 잘 따르는지에 좌우됩니다 — 결과가 만족스럽지 않으면 archive와 함께 이슈로 보고 부탁드려요.
 
 ### 설치되는 파일
 
 | 파일 | 관리 주체 | 용도 |
 |---|---|---|
 | `DESIGN.md` | 사용자 | 단일 진실 — 브랜드 & UI 명세 |
-| `CLAUDE.md` | `omd sync` | Claude Code 포인터 (`@./DESIGN.md`) |
-| `AGENTS.md` | `omd sync` | Codex CLI **+** OpenCode 공용 포인터 (한 파일이 둘 커버) |
-| `.cursor/rules/omd-design.mdc` | `omd sync` | Cursor가 UI 파일 편집 시 DESIGN.md 자동 attach |
+| `CLAUDE.md` | `omd:sync` 스킬 | Claude Code 포인터 (`@./DESIGN.md`) |
+| `AGENTS.md` | `omd:sync` 스킬 | Codex CLI **+** OpenCode 공용 포인터 (한 파일이 둘 커버) |
+| `.cursor/rules/omd-design.mdc` | `omd:sync` 스킬 | Cursor가 UI 파일 편집 시 DESIGN.md 자동 attach |
 | `.claude/skills/omd-*/SKILL.md` | `omd install-skills` | Claude Code 스킬 9종 |
 | `.codex/skills/omd-*/SKILL.md` | `omd install-skills` | Codex 스킬 9종 |
 | `.opencode/agents/omd-*.md` | `omd install-skills` | OpenCode 에이전트 9종 |
-| `.omd/preferences.md` | `omd remember` | append-only 디자인 교정 로그 |
-| `.omd/sync.lock.json` | `omd sync` | drift 감지 상태 |
+| `.omd/preferences.md` | `omd:remember` 스킬 | append-only 디자인 교정 로그 |
+| `.omd/sync.lock.json` | `omd:sync` 스킬 | drift 감지 상태 |
 
-shim과 스킬 파일은 `<!-- omd:start -->` 마커 블록을 사용해서, 마커 외부의 사용자 편집은 `omd sync` 재실행에도 보존됩니다.
+shim과 스킬 파일은 `<!-- omd:start -->` 마커 블록을 사용해서, 마커 외부의 사용자 편집은 `omd:sync` 스킬 재실행에도 보존됩니다.
 
 ### 9개 스킬
 
@@ -122,21 +111,13 @@ shim과 스킬 파일은 `<!-- omd:start -->` 마커 블록을 사용해서, 마
 
 ### CLI 명령어
 
+CLI가 노출하는 명령어는 `install-skills` 하나입니다 — 스킬·에이전트를 프로젝트에 설치/갱신합니다.
+
 ```
-omd init recommend <description>   # 태그+stem 매칭 레퍼런스 추천 (top-5)
-omd init prepare --ref <id> --description <text>
-                                   # .omd/init-context.json + delta_set 준비
 omd install-skills [--agent ...]   # skills/*를 .claude /.codex /.opencode로 복사
-omd reference list                 # 번들된 레퍼런스 id 목록
-omd reference show <id>            # 레퍼런스 DESIGN.md를 stdout으로 출력
-omd sync [--force | --check]       # shim 파일 작성 또는 감사
-omd remember <note> [--scope ...]  # preference entry append
-omd learn                          # pending 목록
-omd learn --mark-applied <id>      # DESIGN.md 반영 후 상태 변경
-omd learn --mark-rejected <id> --reason <text>
 ```
 
-`omd sync --check`는 CI 친화적: shim drift 또는 DESIGN.md 변경 + 미동기화 시 exit 1.
+레퍼런스 추천, DESIGN.md 생성, shim 동기화, preference 기록·반영은 별도 CLI 서브커맨드가 아니라 **스킬 주도**입니다 — 설치 후 에이전트(`omd:init` / `omd:sync` / `omd:remember` / `omd:learn`)에게 자연어로 요청하면 스킬이 파일을 직접 Read/Write/Bash 하며 처리합니다.
 
 ### 결정적 vs 에이전트 주도
 
@@ -150,7 +131,7 @@ omd learn --mark-rejected <id> --reason <text>
 
 ### 상태
 
-이 생태계는 **v0.1.0** — 첫 agent-integration 릴리스입니다. CLI 표면 (sync / remember / learn / init prepare / install-skills)은 안정 + 단위 테스트 완료 (505 테스트). 에이전트 측 Hybrid variation 품질은 호스트 LLM이 `omd:init` 스킬 프롬프트를 얼마나 잘 따르는지에 좌우됩니다 — 검증 맵은 [`test/scenarios/WORKFLOWS.md`](test/scenarios/WORKFLOWS.md) 참고. 실 세션 결과 환영 — `.omd/init-context.json`과 결과 `DESIGN.md`를 첨부해서 이슈로 보고 부탁드립니다.
+이 생태계는 첫 agent-integration 릴리스입니다. 안정적인 CLI 표면은 `install-skills` 하나뿐 — 스킬·에이전트를 프로젝트에 설치/갱신합니다. 그 외 모든 동작(레퍼런스 추천, DESIGN.md 생성, shim 동기화, preference 기록·반영)은 **스킬 주도**로, 에이전트가 파일을 직접 편집해 수행합니다. 에이전트 측 Hybrid variation 품질은 호스트 LLM이 `omd:init` 스킬 프롬프트를 얼마나 잘 따르는지에 좌우됩니다 — 검증 맵은 [`test/scenarios/WORKFLOWS.md`](test/scenarios/WORKFLOWS.md) 참고. 실 세션 결과 환영 — `.omd/init-context.json`과 결과 `DESIGN.md`를 첨부해서 이슈로 보고 부탁드립니다.
 
 ### 업그레이드
 

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> 100+ 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> 221 real company design systems. Zero AI calls in the install. Then you just talk to your agent.
 </p>
 
 <p align="center">
@@ -13,7 +13,7 @@
   <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-100%2B-7c5cfc?style=flat-square" alt="100+ References" />
+  <img src="https://img.shields.io/badge/references-221-7c5cfc?style=flat-square" alt="221 References" />
   <img src="https://img.shields.io/badge/CLI%20commands-1-blue?style=flat-square" alt="One CLI command" />
 </p>
 
@@ -23,7 +23,7 @@
 
 **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 brand-philosophy layer: Voice / Narrative / Principles / Personas / States / Motion). 100+ 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). 221 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.**
 
@@ -49,7 +49,7 @@ This is the whole point: one prompt turns into a `DESIGN.md` your agent remember
 
    > Set up our design system — Toss-style, for a family meal-tracking app.
 
-   Your agent runs **`omd:init`**: it recommends a reference from the 100+ real-company catalog, asks you to confirm, and writes **`DESIGN.md`** to your project root. (`omd:sync` then wires up the `CLAUDE.md` / `AGENTS.md` / Cursor shims so every agent reads it automatically.)
+   Your agent runs **`omd:init`**: it recommends a reference from the 221 real-company catalog, asks you to confirm, and writes **`DESIGN.md`** to your project root. (`omd:sync` then wires up the `CLAUDE.md` / `AGENTS.md` / Cursor shims so every agent reads it automatically.)
 
    **That `DESIGN.md` is your activation — your agent now remembers your brand.**
 
@@ -143,7 +143,7 @@ Open Claude Code (or Codex / OpenCode) in your project. Just talk:
 | `.claude/data/*` | install-skills | 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 | 100+ real design systems |
+| `references/*/DESIGN.md` | bundled | 221 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 |
@@ -155,7 +155,7 @@ Skills (loaded into your agent's context based on prompt triggers):
 
 **Core flow**
 - **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. 100+ references, hybrid variation that preserves the reference voice while shifting only user-named axes.
+- **omd:init** — Bootstrap DESIGN.md from a reference + project description. 221 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. **v1.6.0**: auto-triggers on natural-language requests ("그럴싸한 랜딩 만들어줘", "프로토타입 구색 갖춰") — no slash required. New **CTX-PRIME** pre-phase scans your repo (stack, brand color, voice, surface inventory) in ~20ms, then surfaces a single audience picker + batched Interview-lite so `omd-master` skips slot-gate and jumps straight to PROPOSE_PLAN. 7 hero archetypes (rule 9) match brand vibe to layout (center-text / carousel / split-screen / editorial / dashboard / quote-led / left-character). Reveal safety net (rule 10), wordmark-only logo (rule 5), container-inner consistency (rule 7), decomposed hero (rule 8).
 - **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.

package/agents/AGENT.md

@@ -16,9 +16,9 @@ A 60-line operational context card. Loaded into the project at install via `omd
 - `agents/` — canonical 11 sub-agent definitions (master + 10 specialists; source-of-truth, generates `.claude/agents/` and `.codex/agents/`)
 - `skills/omd-harness/` — entry skill that calls master orchestrator
 - `skills/omd-init/`, `skills/omd-apply/`, `skills/omd-remember/`, `skills/omd-learn/`, `skills/omd-sync/` — existing OmD skills
-- `data/reference-fingerprints.json` — 67-reference voice fingerprint manifest (skill-side semantic match)
+- `data/reference-fingerprints.json` — reference voice fingerprint manifest (skill-side semantic match)
 - `data/vocabulary.json`, `data/synonyms.json`, `data/reference-tags.md` — controlled vocab + tagging
-- `references/<id>/DESIGN.md` × 67 — bundled reference design systems
+- `references/<id>/DESIGN.md` — bundled reference design systems
 - `spec/omd-v0.1.md` — OmD spec (15-section DESIGN.md format)
 - `.omd/runs/run-<ts>-<slug>/` — every harness run; permanent archive
 - `skills/omd-lab-02-design-harness/runs/v<N>-...` — Lab #02 versioned experiments
@@ -41,7 +41,7 @@ A 60-line operational context card. Loaded into the project at install via `omd
 - 999 → never fabricate §11–13 facts
 - 9999 → never invent tokens absent from DESIGN.md
 - 99999 → never auto-skip user checkpoints
-- 999999 → never invent reference ids; 67-only catalog
+- 999999 → never invent reference ids — only ids present in `reference-fingerprints.json` (items[].id) are valid.
 - 9999999 → never claim success when output is empty; Read the file
 - 99999999 → never overwrite previous iteration; snapshot to `iteration-<N>/`
 

package/agents/omd-master.md

@@ -119,7 +119,7 @@ Each turn you are in one state. Determine current state from `.handoff.json` `st
 - **FIGMA_GUIDANCE**: User pasted Figma file URL.
   - Tell user: "Figma URL은 v4에서 직접 추출이 안 돼요. 두 가지 방법이 있어요:
     1. Tokens Studio 플러그인으로 JSON export → 그 path 알려주세요
-    2. 우리 67-catalog에서 가장 가까운 톤 골라서 시작 (catalog id로 답변)"
+    2. 우리 reference 카탈로그에서 가장 가까운 톤 골라서 시작 (catalog id로 답변)"
   - Wait for user. Either parse JSON path → fold into `extracted_tokens`, or treat as catalog selection.
 
 - **PRODUCTION_TRANSITION** (CRITICAL — re-engage when user says "프로덕션화" / "production" / "ship" / "deploy" / "실배포" mid-flight): User just shifted from prototyping to productionizing. **Don't fall back to plain coding.** **Don't extract DESIGN.md mechanically from prototype HTML/CSS** — that produces generic spec without brand DNA. Curate via reference matching instead.
@@ -132,14 +132,14 @@ Each turn you are in one state. Determine current state from `.handoff.json` `st
   - tone keywords from visible microcopy (e.g., "calm / encouraging / not-pushy" from "오늘 첫 잔으로 시작해요")
   - 5 short adjectives describing the *atmosphere* (NOT a full token dump)
 
-  ### Step 2 — Reference matching (67 catalog)
+  ### Step 2 — Reference matching (reference 카탈로그)
   Score against `data/reference-fingerprints.json` using the signal above + voice_fingerprint + tone_keywords. Identify top 2-3 closest references.
 
   ### Step 3 — Curation proposal (the wow point)
   Surface the matched references as a *curation question*, not a token dump:
 
   ```
-  prototype 한 번 보고 왔어요. 톤은 calm-blue + 응원하는 듯한 친근함 + 잔잔한 모션 — 67-catalog 중 toss + lovable이 가장 가깝게 보여요.
+  prototype 한 번 보고 왔어요. 톤은 calm-blue + 응원하는 듯한 친근함 + 잔잔한 모션 — reference 카탈로그 중 toss + lovable이 가장 가깝게 보여요.
    • toss — 차분한 calm-cerulean + 숫자 강조 + 한국 핀테크 절제미
    • lovable — parchment cream + 휴머니스트 + 응원하는 따뜻함
 
@@ -149,7 +149,7 @@ Each turn you are in one state. Determine current state from `.handoff.json` `st
    - go (toss base + drop delta) — 추천
    - lovable base + drop delta
    - 둘 다 섞기 (toss 60 / lovable 40)
-   - 다른 reference 골라볼게 (catalog 67 보여줘)
+   - 다른 reference 골라볼게 (reference 카탈로그 보여줘)
    - 그냥 prototype에서 바로 추출 (덜 추천 — generic해질 수 있음)
   ```
 
@@ -168,7 +168,7 @@ Each turn you are in one state. Determine current state from `.handoff.json` `st
   ```
   (Edit 툴로 첫 줄 prepend.)
 
-  **Step 4.2 — Reference DESIGN.md Read.** `Read references/<chosen_ref_id>/DESIGN.md` (예: `references/toss/DESIGN.md`). 67개 카탈로그 안의 모든 ref에 DESIGN.md 있음.
+  **Step 4.2 — Reference DESIGN.md Read.** `Read references/<chosen_ref_id>/DESIGN.md` (예: `references/toss/DESIGN.md`). reference 카탈로그 안의 모든 ref에 DESIGN.md 있음.
 
   **Step 4.3 — delta axes 추론.** 사용자 description + chosen ref base를 비교해서 다음 axes 중 사용자가 명시했거나 함의한 것만 shift 대상으로 표시:
   - `hue_deg` (색상 각도, 예: +30 = warmer rotation)
@@ -303,7 +303,7 @@ When user says "이 부분 좀 따뜻하게" / "더 세련되게" / "여기 좁
 **RULE 7.5 — Vague modifier disambiguator (don't guess).**
 When `signal-classifier` returns `vague_modifier !== null` (e.g., "좀 더 세련되게", "warmer", "여백 답답해"):
 1. Do NOT silently apply your guess — that's how you produce wrong work the user has to reject.
-2. Call `scoreCandidatesForModifier` (in `src/core/visual-anchor.ts`) with current reference + axis + direction + 67-catalog.
+2. Call `scoreCandidatesForModifier` (in `src/core/visual-anchor.ts`) with current reference + axis + direction + the full reference catalog.
 3. Get top 3-4 reference candidates that move in the requested direction.
 4. Build picker via `modifierDisambiguatorPicker` and present:
    ```
@@ -537,7 +537,7 @@ Audit trail. Persists across master spawns within a run.
 - **999.** Never fabricate §11–13 facts. Use `[FILL IN]` placeholder.
 - **9999.** Never introduce a token absent from DESIGN.md without going through Phase 5.
 - **99999.** Never auto-skip mandatory user gates (Phase 3, Phase 5, SHIP_GATE).
-- **999999.** Never invent reference ids — only the 67 in `reference-fingerprints.json` are valid.
+- **999999.** Never invent reference ids — only ids present in `reference-fingerprints.json` (items[].id) are valid.
 - **9999999.** Never claim sub-agent succeeded when output is missing/empty. Read the file.
 - **99999999.** Never overwrite previous iteration artifacts without snapshot.
 

package/agents/omd-microcopy.md

@@ -60,4 +60,4 @@ You write microcopy. Every word you write must be derivable from `DESIGN.md §10
 
 Write a single `components/microcopy.json` containing all slots. No prose response — just the JSON file written.
 
-If §10 is missing from DESIGN.md, halt and report to master: "DESIGN.md §10 missing — cannot write microcopy without voice spec. Run omd init Phase 4.5 to populate."
+If §10 is missing from DESIGN.md, halt and report to master: "DESIGN.md §10 missing — cannot write microcopy without voice spec. Ask omd-master to populate §10 (Voice) before microcopy can be written."

package/agents/omd-ux-researcher.md

@@ -1,6 +1,6 @@
 ---
 name: omd-ux-researcher
-description: Reads bundled oh-my-design references (67 companies), researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.
+description: Reads bundled oh-my-design references (the bundled reference catalog), researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.
 tools: Read, Glob, Grep, WebSearch, WebFetch, Bash, Write
 model: opus
 ---