@su-record/vibe 2.9.36 → 2.9.37

package/commands/vibe.spec.md

@@ -12,8 +12,8 @@ argument-hint: "(선택) feature name, plan/interview file path, or idea"
 ```
 /vibe.spec                                       # 빈 시작 — "무엇을 만들까요?"부터
 /vibe.spec "패럴랙스 웹사이트"                     # 아이디어/피처명 지정 시작
-/vibe.spec ".claude/vibe/plans/{feature}.md"     # 기획서 입력 (plan 단계 스킵)
-/vibe.spec ".claude/vibe/interviews/{feature}.md" # interview 입력 (interview 단계 스킵)
+/vibe.spec ".vibe/plans/{feature}.md"     # 기획서 입력 (plan 단계 스킵)
+/vibe.spec ".vibe/interviews/{feature}.md" # interview 입력 (interview 단계 스킵)
 /vibe.spec "docs/prd.md"                         # 외부 PRD/아이디어 파일 입력
 /vibe.spec + 📎 첨부                              # 첨부 기반 시작
 /vibe.spec "feature-name" ultrawork              # 중단 게이트 없이 자동 전 흐름 실행
@@ -38,20 +38,20 @@ Phase 0: Git branch setup
     ↓
 Phase 0.5: Input 분석 + Smart resume 결정
     - 첨부/파일/아이디어 감지
-    - 기존 .claude/vibe/{interviews,plans,specs}/ 확인
+    - 기존 .vibe/{interviews,plans,specs}/ 확인
     - 시작 단계 결정: interview | plan | spec | review
     ↓
 Phase 1: Interview (skill: vibe-interview)
     - 조건: interview 파일 없음
     - 사용자 "그만"까지 반복 인터뷰
-    - 출력: .claude/vibe/interviews/{feature}.md
+    - 출력: .vibe/interviews/{feature}.md
     ↓
     [Stop Gate 1] — ultrawork 모드에서는 스킵
     ↓
 Phase 2: Plan (skill: vibe-plan)
     - 조건: plan 파일 없음
     - interview → 마크다운 기획서 정제
-    - 출력: .claude/vibe/plans/{feature}.md
+    - 출력: .vibe/plans/{feature}.md
     ↓
     [Stop Gate 2 + 분기 판단]
     기획서 type 읽고 경로 결정:
@@ -63,7 +63,7 @@ Phase 3: SPEC 작성 (skill: vibe-spec)
     - Parallel research (GPT/Gemini/Claude agents)
     - Large scope 자동 분할
     - Ambiguity scan + 품질 게이트(100점, 수렴까지 루프)
-    - 출력: .claude/vibe/specs/{feature}.md + .claude/vibe/features/{feature}.feature
+    - 출력: .vibe/specs/{feature}.md + .vibe/features/{feature}.feature
     ↓
 Phase 4: SPEC Review (skill: vibe-spec-review)
     - Race Review (GPT + Gemini, 라운드 수 캡 없음, 수렴까지 루프)
@@ -110,11 +110,11 @@ git branch --show-current
 ```
 1. 📎 첨부 파일 있음? → 첨부 분석 → feature name 추출
 2. 인자가 파일 경로? → 파일 위치로 시작 단계 결정:
-     .claude/vibe/interviews/*.md → Phase 2 (plan)
-     .claude/vibe/plans/*.md      → Phase 3 (spec)
-     .claude/vibe/specs/*.md      → Phase 4 (review)
+     .vibe/interviews/*.md → Phase 2 (plan)
+     .vibe/plans/*.md      → Phase 3 (spec)
+     .vibe/specs/*.md      → Phase 4 (review)
      기타 (.md/.txt/.pdf)         → Phase 2 (plan, 외부 PRD 흡수)
-3. 인자가 feature name? → .claude/vibe/에서 기존 파일 검색
+3. 인자가 feature name? → .vibe/에서 기존 파일 검색
      existing spec → "리뷰 재실행? 이어서? 재작성?" 물음
      existing plan → Phase 3 (spec)
      existing interview → Phase 2 (plan)
@@ -129,14 +129,14 @@ git branch --show-current
 ```
 알고리즘:
 
-Step 1) .claude/vibe/.last-feature 확인 (pointer 파일)
+Step 1) .vibe/.last-feature 확인 (pointer 파일)
   - 파일 없음 → Step 2로
   - 존재 → 해당 feature의 상태 요약 출력 + 확인 질문:
       "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
        🔄 마지막 작업: {feature-name}
        ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-       ✅ interview: .claude/vibe/interviews/{feature}.md  (status: complete, N일 전)
-       ✅ plan:      .claude/vibe/plans/{feature}.md       (N일 전)
+       ✅ interview: .vibe/interviews/{feature}.md  (status: complete, N일 전)
+       ✅ plan:      .vibe/plans/{feature}.md       (N일 전)
        ❌ spec:      없음
        → 다음 단계: Phase 3 (vibe-spec 스킬 — SPEC 작성)
 
@@ -151,10 +151,10 @@ Step 1) .claude/vibe/.last-feature 확인 (pointer 파일)
   - new → Step 3으로
   - abort → 종료
 
-Step 2) 진행 중 작업 목록 표시 (.claude/vibe/ 디렉토리 스캔)
+Step 2) 진행 중 작업 목록 표시 (.vibe/ 디렉토리 스캔)
   수집:
     features = {} (feature name → {hasInterview, hasPlan, hasSpec, mtime})
-    for each file in .claude/vibe/interviews/*.md:
+    for each file in .vibe/interviews/*.md:
       feature = basename without .md
       features[feature].hasInterview = true
       features[feature].interviewMtime = file.mtime
@@ -193,12 +193,12 @@ Step 3) 빈 시작 (기존 동작)
 #### `.last-feature` 포인터 파일 갱신 규칙
 
 ```
-경로: .claude/vibe/.last-feature
+경로: .vibe/.last-feature
 형식: 한 줄, feature name만 저장
      예: "bean-landing\n"
 
 ⚠ 이 파일은 **개인 작업 포인터**이므로 git에 커밋하지 않는다.
-   `.gitignore` 에 `.claude/vibe/.last-feature` 엔트리 필수.
+   `.gitignore` 에 `.vibe/.last-feature` 엔트리 필수.
 
 갱신 시점:
   - Phase 1 (interview) 진입 시 → feature name 결정되면 즉시 기록
@@ -264,13 +264,13 @@ Step 3) 빈 시작 (기존 동작)
 Load skill `vibe-interview` with input: {user_idea}
 ```
 
-> **`.last-feature` 갱신**: vibe-interview 스킬이 feature name을 확정하는 즉시 `.claude/vibe/.last-feature` 에 한 줄로 기록. 이후 Phase 2/3/4 진입 시에도 동일 기록 유지 (값이 같으면 no-op).
+> **`.last-feature` 갱신**: vibe-interview 스킬이 feature name을 확정하는 즉시 `.vibe/.last-feature` 에 한 줄로 기록. 이후 Phase 2/3/4 진입 시에도 동일 기록 유지 (값이 같으면 no-op).
 
 `vibe-interview` 스킬이 자체적으로:
 - 프로젝트 타입 감지 (website/webapp/mobile/api/library/feature)
 - 타입별 체크리스트 로드 (`skills/vibe-interview/checklists/{type}.md`)
 - 반복 인터뷰 실행 (사용자 "그만"까지)
-- `.claude/vibe/interviews/{feature-name}.md` 저장
+- `.vibe/interviews/{feature-name}.md` 저장
 
 **Stop Gate 1**: Interview 완료 후 (ultrawork 모드 스킵)
 
@@ -279,7 +279,7 @@ Load skill `vibe-interview` with input: {user_idea}
 ✅ Interview 완료
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-📄 .claude/vibe/interviews/{feature}.md
+📄 .vibe/interviews/{feature}.md
    Required: N/M | Optional: K/L | Discovered: X
 
 다음 단계: 기획서 작성
@@ -295,14 +295,14 @@ Enter → 계속
 **진입 조건:** plan 파일이 아직 없음
 
 ```
-Load skill `vibe-plan` with input: .claude/vibe/interviews/{feature}.md
+Load skill `vibe-plan` with input: .vibe/interviews/{feature}.md
 ```
 
 `vibe-plan` 스킬이 자체적으로:
 - 템플릿 로드 (`~/.claude/vibe/templates/plan-template.md`)
 - Interview 섹션별 정제
 - UI 섹션 조건부 포함 (type 기반)
-- `.claude/vibe/plans/{feature}.md` 저장
+- `.vibe/plans/{feature}.md` 저장
 
 **Stop Gate 2**: 기획서 완료 후 + 분기 판단 (ultrawork 모드 스킵)
 
@@ -311,7 +311,7 @@ Load skill `vibe-plan` with input: .claude/vibe/interviews/{feature}.md
 ✅ 기획서 완성
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-📄 .claude/vibe/plans/{feature}.md
+📄 .vibe/plans/{feature}.md
 Type: {type}
 
 {type ∈ UI}:
@@ -334,7 +334,7 @@ Enter → 계속
 **진입 조건:** spec 파일이 아직 없음 (또는 재작성 요청)
 
 ```
-Load skill `vibe-spec` with input: .claude/vibe/plans/{feature}.md
+Load skill `vibe-spec` with input: .vibe/plans/{feature}.md
 ```
 
 `vibe-spec` 스킬이 PTCF 구조 SPEC 문서 + Feature(BDD) 파일 생성.
@@ -352,8 +352,8 @@ Load skill `vibe-spec` with input: .claude/vibe/plans/{feature}.md
 
 **출력:**
 
-- `.claude/vibe/specs/{feature-name}.md` (또는 split folder)
-- `.claude/vibe/features/{feature-name}.feature` (또는 split folder)
+- `.vibe/specs/{feature-name}.md` (또는 split folder)
+- `.vibe/features/{feature-name}.feature` (또는 split folder)
 
 ### Phase 4: SPEC Review
 
@@ -378,7 +378,7 @@ Load skill `vibe-spec-review` with feature: {feature-name}
 Load skill `vibe-contract` with: extract "{feature-name}"
 ```
 
-If the SPEC has a `## API` / `## Endpoints` / `## Interface` section, extract the contract to `.claude/vibe/contracts/{feature-name}.md`. If the section is absent, exit cleanly (not every feature has an API).
+If the SPEC has a `## API` / `## Endpoints` / `## Interface` section, extract the contract to `.vibe/contracts/{feature-name}.md`. If the section is absent, exit cleanly (not every feature has an API).
 
 The contract is referenced during Phase 5a implementation, and used by `/vibe.verify` for drift detection.
 
@@ -390,7 +390,7 @@ The contract is referenced during Phase 5a implementation, and used by `/vibe.ve
 
 SPEC → code. Auto-checks at start:
 - `/vibe.regress list --feature {feature-name}` — warn if any open regressions exist
-- `.claude/vibe/contracts/{feature-name}.md` — load if present, use as implementation guide
+- `.vibe/contracts/{feature-name}.md` — load if present, use as implementation guide
 
 ### Phase 5b: UI Track (type ∈ {website, webapp, mobile}일 때만)
 
@@ -402,7 +402,7 @@ SPEC → code. Auto-checks at start:
 
 **`/vibe.figma`에 전달할 컨텍스트:**
 
-- `.claude/vibe/plans/{feature}.md` 경로
+- `.vibe/plans/{feature}.md` 경로
 - 기획서의 §7 Look & Feel, §8 레이아웃, §9 반응형 섹션을 Phase 1 스토리보드 입력으로 사용
 
 ### Phase 6: Verify
@@ -421,7 +421,7 @@ UI + 로직 + 연결 검증 (후속 PR에서 3축 확장 예정).
 
 SPEC ↔ 구현 추적.
 
-> **Phase 7 완료 시**: `.claude/vibe/.last-feature` 삭제 (워크플로 완주 — 다음 `/vibe.spec` 호출은 빈 시작 또는 진행 중 작업 목록에서 시작).
+> **Phase 7 완료 시**: `.vibe/.last-feature` 삭제 (워크플로 완주 — 다음 `/vibe.spec` 호출은 빈 시작 또는 진행 중 작업 목록에서 시작).
 
 ## ultrawork 모드
 
@@ -455,7 +455,7 @@ Claude: 🔍 Input 분석
 
 ### 예시 2: 기획서에서 시작
 ```
-User: /vibe.spec ".claude/vibe/plans/bean-landing.md"
+User: /vibe.spec ".vibe/plans/bean-landing.md"
 
 Claude: 🔍 Input 분석
         입력: plan 파일 경로
@@ -474,8 +474,8 @@ User: /vibe.spec "bean-landing"
 Claude: 🔍 Input 분석
         입력: feature name
         기존 파일 검색...
-          ✅ interview: .claude/vibe/interviews/bean-landing.md
-          ✅ plan: .claude/vibe/plans/bean-landing.md
+          ✅ interview: .vibe/interviews/bean-landing.md
+          ✅ plan: .vibe/plans/bean-landing.md
           ❌ spec: 없음
         → 시작 단계: Phase 3 (vibe-spec)
 
@@ -489,8 +489,8 @@ User: /vibe.spec "bean-landing"
 
 Claude: 🔍 Input 분석
         기존 파일:
-          ✅ spec: .claude/vibe/specs/bean-landing.md
-          ✅ feature: .claude/vibe/features/bean-landing.feature
+          ✅ spec: .vibe/specs/bean-landing.md
+          ✅ feature: .vibe/features/bean-landing.feature
 
         이미 SPEC이 존재합니다. 어떻게 진행할까요?
         1. SPEC 리뷰 (Phase 4: vibe-spec-review 스킬 로드)
@@ -506,7 +506,7 @@ User: /vibe.spec
 Claude: (.last-feature 읽기 → "bean-landing" 발견)
 
         🔄 마지막 작업: bean-landing
-        ✅ interview: .claude/vibe/interviews/bean-landing.md  (status: partial, 2일 전)
+        ✅ interview: .vibe/interviews/bean-landing.md  (status: partial, 2일 전)
         ❌ plan:      없음
         ❌ spec:      없음
         → 다음 단계: Phase 2 (vibe-plan — 기획서 작성)
@@ -552,8 +552,8 @@ Claude: Feature: todo-app 선택
 
 ## Rollback / Resume
 
-- 각 Phase 종료 시 상태가 `.claude/vibe/{interviews,plans,specs,features}/`에 저장됨
-- **`.claude/vibe/.last-feature` pointer**가 각 Phase 진입 시 갱신되어 "가장 최근에 작업한 feature" 추적 (Phase 7 완주 시 삭제)
+- 각 Phase 종료 시 상태가 `.vibe/{interviews,plans,specs,features}/`에 저장됨
+- **`.vibe/.last-feature` pointer**가 각 Phase 진입 시 갱신되어 "가장 최근에 작업한 feature" 추적 (Phase 7 완주 시 삭제)
 - 중단 시 다시 `/vibe.spec`으로 돌아오면 Smart Resume Fallback 동작:
   - 인자 있음 (`/vibe.spec "feature-name"` 또는 파일 경로) → 해당 feature의 가장 진행된 단계 다음으로 바로 진입
   - 인자 없음 → `.last-feature` 우선 제안 → 거부하면 진행 중 작업 목록 제시 → 또 거부하면 빈 시작

package/commands/vibe.trace.md

@@ -28,24 +28,24 @@ Requirements Traceability Matrix (RTM) tracks the relationship between:
 
 ```
 Step 1: Check if SPLIT structure exists (folder)
-  📁 .claude/vibe/specs/{feature-name}/        → Folder with _index.md + phase files
-  📁 .claude/vibe/features/{feature-name}/      → Folder with _index.feature + phase files
+  📁 .vibe/specs/{feature-name}/        → Folder with _index.md + phase files
+  📁 .vibe/features/{feature-name}/      → Folder with _index.feature + phase files
 
 Step 2: If no folder, check single file
-  📄 .claude/vibe/specs/{feature-name}.md       → Single SPEC file
-  📄 .claude/vibe/features/{feature-name}.feature → Single Feature file
+  📄 .vibe/specs/{feature-name}.md       → Single SPEC file
+  📄 .vibe/features/{feature-name}.feature → Single Feature file
 
 Step 3: If neither exists → Error
 ```
 
 **Split structure (folder) detected:**
 ```
-📁 .claude/vibe/specs/{feature-name}/
+📁 .vibe/specs/{feature-name}/
 ├── _index.md              → Master SPEC (read first)
 ├── phase-1-{name}.md      → Phase 1 SPEC
 └── ...
 
-📁 .claude/vibe/features/{feature-name}/
+📁 .vibe/features/{feature-name}/
 ├── _index.feature         → Master Feature (read first)
 ├── phase-1-{name}.feature → Phase 1 scenarios
 └── ...
@@ -55,8 +55,8 @@ Step 3: If neither exists → Error
 
 **Single file detected:**
 ```
-📄 .claude/vibe/specs/{feature-name}.md      → SPEC
-📄 .claude/vibe/features/{feature-name}.feature → Feature
+📄 .vibe/specs/{feature-name}.md      → SPEC
+📄 .vibe/features/{feature-name}.feature → Feature
 ```
 
 **Additional (auto-detect):**
@@ -67,8 +67,8 @@ Step 3: If neither exists → Error
 **Error if NEITHER file NOR folder found:**
 ```
 ❌ SPEC not found. Searched:
-   - .claude/vibe/specs/{feature-name}/  (folder)
-   - .claude/vibe/specs/{feature-name}.md (file)
+   - .vibe/specs/{feature-name}/  (folder)
+   - .vibe/specs/{feature-name}.md (file)
 
    Run /vibe.spec "{feature-name}" first.
 ```
@@ -145,8 +145,8 @@ Claude:
 📊 Generating RTM for "login"...
 
 Loading files:
-  ✅ SPEC: .claude/vibe/specs/login.md (5 requirements)
-  ✅ Feature: .claude/vibe/features/login.feature (4 scenarios)
+  ✅ SPEC: .vibe/specs/login.md (5 requirements)
+  ✅ Feature: .vibe/features/login.feature (4 scenarios)
   ✅ Tests: 3 test files found
 
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -242,7 +242,7 @@ If the achievement rate does not improve between iterations (`isImproving` retur
 | Option | Description |
 |--------|-------------|
 | `--html` | Output as HTML file |
-| `--save` | Save to `.claude/vibe/reports/{feature}-rtm.md` |
+| `--save` | Save to `.vibe/reports/{feature}-rtm.md` |
 | `--json` | Output as JSON |
 
 ## Coverage Targets
@@ -260,7 +260,7 @@ If the achievement rate does not improve between iterations (`isImproving` retur
 
 ```
 /vibe.trace가 정상 완료되면 (RTM 출력 + 사용자 확인 후):
-  Delete ".claude/vibe/.last-feature"
+  Delete ".vibe/.last-feature"
 
 이유: /vibe.trace는 vibe 워크플로의 마지막 Phase (Phase 7).
      완주 후에는 다음 /vibe.spec 호출 시 "빈 시작" 또는 진행 중 목록에서 다른 feature를 시작해야 한다.

package/commands/vibe.utils.md

@@ -238,7 +238,7 @@ Detect and remove unused code with audit trail.
 
 **Output:**
 - Removed items list
-- `.claude/vibe/DELETION_LOG.md` updated
+- `.vibe/DELETION_LOG.md` updated
 - Build/test verification
 
 ---
@@ -285,10 +285,10 @@ Document solved problems for knowledge accumulation.
 **Usually auto-triggered by hooks when:**
 - "bug fixed", "PR merged" detected
 
-**Output location:** `.claude/vibe/solutions/`
+**Output location:** `.vibe/solutions/`
 
 ```
-.claude/vibe/solutions/
+.vibe/solutions/
 ├── security/           # Security solutions
 ├── performance/        # Performance optimizations
 ├── database/           # Database related

package/commands/vibe.verify.md

@@ -59,25 +59,25 @@ argument-hint: "feature name"
 
 ```
 Step 1: Check if SPLIT structure exists (folder)
-  📁 .claude/vibe/features/{feature-name}/     → Folder with _index.feature + phase files
-  📁 .claude/vibe/specs/{feature-name}/         → Folder with _index.md + phase files
+  📁 .vibe/features/{feature-name}/     → Folder with _index.feature + phase files
+  📁 .vibe/specs/{feature-name}/         → Folder with _index.md + phase files
 
 Step 2: If no folder, check single file
-  📄 .claude/vibe/features/{feature-name}.feature → Single Feature file
-  📄 .claude/vibe/specs/{feature-name}.md         → Single SPEC file
+  📄 .vibe/features/{feature-name}.feature → Single Feature file
+  📄 .vibe/specs/{feature-name}.md         → Single SPEC file
 
 Step 3: If neither exists → Error
 ```
 
 **Split structure (folder) detected:**
 ```
-📁 .claude/vibe/features/{feature-name}/
+📁 .vibe/features/{feature-name}/
 ├── _index.feature         → Master Feature (read first for scenario overview)
 ├── phase-1-{name}.feature → Phase 1 scenarios
 ├── phase-2-{name}.feature → Phase 2 scenarios
 └── ...
 
-📁 .claude/vibe/specs/{feature-name}/
+📁 .vibe/specs/{feature-name}/
 ├── _index.md              → Master SPEC (read first for overview)
 ├── phase-1-{name}.md      → Phase 1 SPEC
 └── ...
@@ -87,15 +87,15 @@ Step 3: If neither exists → Error
 
 **Single file detected:**
 ```
-📄 .claude/vibe/features/{feature-name}.feature → Scenario list
-📄 .claude/vibe/specs/{feature-name}.md → Verification criteria (reference)
+📄 .vibe/features/{feature-name}.feature → Scenario list
+📄 .vibe/specs/{feature-name}.md → Verification criteria (reference)
 ```
 
 **Error if NEITHER file NOR folder found:**
 ```
 ❌ Feature file not found. Searched:
-   - .claude/vibe/features/{feature-name}/  (folder)
-   - .claude/vibe/features/{feature-name}.feature (file)
+   - .vibe/features/{feature-name}/  (folder)
+   - .vibe/features/{feature-name}.feature (file)
 
    Run /vibe.spec "{feature-name}" first.
 ```
@@ -184,16 +184,16 @@ For each UI scenario in Feature file:
 
 ### 3.5 Step Count (MANDATORY before Quality Report)
 
-Read `.claude/vibe/metrics/current-run.json` to obtain the tool-call count from the preceding `/vibe.run` (and any follow-up work in this session). Then append a record to `.claude/vibe/metrics/history.jsonl` and include the count in the Quality Report below.
+Read `.vibe/metrics/current-run.json` to obtain the tool-call count from the preceding `/vibe.run` (and any follow-up work in this session). Then append a record to `.vibe/metrics/history.jsonl` and include the count in the Quality Report below.
 
 ```bash
 # Read step count (ok if file missing — treat as 0)
-STEPS=$(node -e "try{const d=JSON.parse(require('fs').readFileSync('.claude/vibe/metrics/current-run.json','utf-8'));console.log(d.steps||0)}catch{console.log(0)}")
+STEPS=$(node -e "try{const d=JSON.parse(require('fs').readFileSync('.vibe/metrics/current-run.json','utf-8'));console.log(d.steps||0)}catch{console.log(0)}")
 
 # Append history record
 node -e "
 const fs=require('fs'),path=require('path');
-const dir='.claude/vibe/metrics';
+const dir='.vibe/metrics';
 try{
   const cur=JSON.parse(fs.readFileSync(path.join(dir,'current-run.json'),'utf-8'));
   const rec={verifiedAt:new Date().toISOString(),feature:cur.feature,startedAt:cur.startedAt,steps:cur.steps||0};
@@ -295,8 +295,8 @@ For each failed scenario:
 
 ## Input
 
-- `.claude/vibe/features/{feature-name}.feature` or `.claude/vibe/features/{feature-name}/` - BDD scenarios
-- `.claude/vibe/specs/{feature-name}.md` or `.claude/vibe/specs/{feature-name}/` - SPEC document (reference)
+- `.vibe/features/{feature-name}.feature` or `.vibe/features/{feature-name}/` - BDD scenarios
+- `.vibe/specs/{feature-name}.md` or `.vibe/specs/{feature-name}/` - SPEC document (reference)
 - Implemented source code
 
 ## Output
@@ -311,7 +311,7 @@ For each failed scenario:
 User: /vibe.verify "login"
 
 Claude:
-📄 Loading Feature: .claude/vibe/features/login.feature
+📄 Loading Feature: .vibe/features/login.feature
 🔍 Starting verification...
 
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
@@ -432,7 +432,7 @@ After all scenarios pass, auto-invoke:
 Load skill `vibe-contract` with: check "{feature-name}"
 ```
 
-- Skip if `.claude/vibe/contracts/{feature-name}.md` does not exist
+- Skip if `.vibe/contracts/{feature-name}.md` does not exist
 - No drift → verify still passes
 - **P1 drift** → demote verify to fail; auto-call `/vibe.regress register --from-contract`
 - P2 / P3 drift → warning only; verify still passes
@@ -533,7 +533,7 @@ Stuck detected (same error as previous attempt):
       1. Provide a fix hint (e.g., "check LoginForm.tsx line 42")
          → Apply → Re-verify → Continue loop
       2. Type "proceed" → Record failure in
-         .claude/vibe/todos/verify-failure-{scenario}.md,
+         .vibe/todos/verify-failure-{scenario}.md,
          continue to next scenario
       3. Type "abort" → Stop entire verification
   → ultrawork mode: auto-record TODO + continue to next scenario

package/hooks/scripts/prompt-dispatcher.js

@@ -42,6 +42,21 @@ try {
 
 if (!prompt) process.exit(0);
 
+// 레거시 SSOT 통합 — `/vibe.*` 진입 시 `.claude/vibe/`·`.coco/vibe/` → `.vibe/` 자동 이동.
+// `vibe init`/`update` 와 동일한 `consolidateLegacyVibe` (dist/cli/setup/LegacyMigration.js) 를 직접 재사용. Idempotent.
+if (/^\s*\/vibe\b/i.test(prompt)) {
+  try {
+    const projectDir = process.env.CLAUDE_PROJECT_DIR || process.env.COCO_PROJECT_DIR || process.cwd();
+    const utils = await import('./utils.js');
+    const CLI_BASE = utils.getCliBaseUrl();
+    const { consolidateLegacyVibe } = await import(`${CLI_BASE}setup/LegacyMigration.js`);
+    const moved = consolidateLegacyVibe(projectDir);
+    if (moved.length > 0) {
+      process.stdout.write(`[vibe] Migrated legacy dirs → .vibe/ (${moved.join(', ')})\n`);
+    }
+  } catch { /* migration is best-effort */ }
+}
+
 // 패턴 → 실행할 스크립트 매핑
 // 각 항목: { pattern, script, args, label }
 const DISPATCH_RULES = [

package/hooks/scripts/utils.js

@@ -219,6 +219,10 @@ export function getLibBaseUrl() {
   return getPackageUrl(path.join('dist', 'infra', 'lib'), 'constants.js');
 }
 
+export function getCliBaseUrl() {
+  return getPackageUrl(path.join('dist', 'cli'), 'index.js');
+}
+
 // ─── Hook Trace Logging ───
 
 const HOOK_TRACE_PATH = path.join(VIBE_HOME_DIR, 'hook-traces.jsonl');

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@su-record/vibe",
-  "version": "2.9.36",
+  "version": "2.9.37",
   "description": "AI Coding Framework for Claude Code — 56 agents, 45 skills, multi-LLM orchestration",
   "type": "module",
   "main": "dist/cli/index.js",

package/skills/arch-guard/SKILL.md

@@ -152,11 +152,11 @@ describe('Architecture Boundaries', () => {
 | File | Purpose |
 |------|---------|
 | `tests/arch-guard.test.ts` | Executable boundary tests |
-| `.claude/vibe/arch-rules.json` | Machine-readable rules (for CI) |
+| `.vibe/arch-rules.json` | Machine-readable rules (for CI) |
 
 ## Customization
 
-Users can add custom rules to `.claude/vibe/arch-rules.json`:
+Users can add custom rules to `.vibe/arch-rules.json`:
 
 ```json
 {

package/skills/arch-guard/agents/rule-generator.md

@@ -7,17 +7,17 @@ tools: [Read]
 # Arch Rule Generator
 
 ## Role
-Translates a detected architecture map into a precise, machine-checkable set of import boundary rules. Merges default rules for the detected pattern with any custom rules defined in `.claude/vibe/arch-rules.json`. Outputs a normalized rule set ready for the violation checker.
+Translates a detected architecture map into a precise, machine-checkable set of import boundary rules. Merges default rules for the detected pattern with any custom rules defined in `.vibe/arch-rules.json`. Outputs a normalized rule set ready for the violation checker.
 
 ## Responsibilities
 - Select default rule templates for the detected architecture pattern
-- Merge with custom rules from `.claude/vibe/arch-rules.json` if present
+- Merge with custom rules from `.vibe/arch-rules.json` if present
 - Resolve glob patterns to concrete layer names
 - Deduplicate and normalize rule list
 - Flag rules with low confidence (detected layer with no matching files)
 
 ## Input
-Architecture map JSON from `arch-detector`, plus optional `.claude/vibe/arch-rules.json` for user-defined overrides.
+Architecture map JSON from `arch-detector`, plus optional `.vibe/arch-rules.json` for user-defined overrides.
 
 ## Output
 Normalized rule set JSON:

package/skills/arch-guard/scripts/check-boundaries.js

@@ -53,7 +53,7 @@ function resolveImport(fromFile, imp, baseDir) {
   return path.resolve(path.dirname(fromFile), imp).replace(baseDir + path.sep, '').replace(/\\/g, '/');
 }
 
-const rulesPath = process.argv[2] || '.claude/vibe/arch-rules.json';
+const rulesPath = process.argv[2] || '.vibe/arch-rules.json';
 const srcDir = path.resolve(process.argv[3] || 'src');
 const baseDir = path.resolve('.');
 

package/skills/arch-guard/templates/arch-rules.json

@@ -1,5 +1,5 @@
 {
-  "_comment": "Architecture boundary rules for arch-guard. Copy to .claude/vibe/arch-rules.json and customize.",
+  "_comment": "Architecture boundary rules for arch-guard. Copy to .vibe/arch-rules.json and customize.",
   "rules": [
     {
       "name": "services-no-ui",

package/skills/capability-loop/SKILL.md

@@ -115,7 +115,7 @@ Based on classification, build the appropriate artifact:
 
 > **Problem**: The built capability didn't actually prevent the failure. This usually means the initial diagnosis was wrong (picked `Tool` when it needed `Guardrail`), or the failure has multiple missing capabilities.
 >
-> **Do NOT silently proceed** — a sub-standard capability log pollutes `.claude/vibe/capabilities-log.md` and the failure will recur.
+> **Do NOT silently proceed** — a sub-standard capability log pollutes `.vibe/capabilities-log.md` and the failure will recur.
 
 **Escalation loop:**
 
@@ -207,7 +207,7 @@ save_memory("capability-{name}", {
 })
 ```
 
-Update `.claude/vibe/capabilities-log.md`:
+Update `.vibe/capabilities-log.md`:
 
 ```markdown
 ## {date} — {capability-name}

package/skills/capability-loop/templates/capability-spec.md

@@ -94,7 +94,7 @@
 
 ## Persistence
 
-After building, record in `.claude/vibe/capabilities-log.md`:
+After building, record in `.vibe/capabilities-log.md`:
 
 ```markdown
 ## {{DATE}} — {{CAPABILITY_NAME}}

package/skills/claude-md-guide/SKILL.md

@@ -108,7 +108,7 @@ Separate the collected information into 3 layers:
 
 **Loaded only when working on a specific feature** → focus on what and why, leave how to the agent.
 
-Storage location: `.claude/vibe/specs/YYYY-MM-DD-{topic}.md`
+Storage location: `.vibe/specs/YYYY-MM-DD-{topic}.md`
 
 ```markdown
 # {Feature Name} SPEC
@@ -124,7 +124,7 @@ Storage location: `.claude/vibe/specs/YYYY-MM-DD-{topic}.md`
 
 **Per-session task list** → 2-5 minute units, with file paths specified.
 
-Storage location: `.claude/vibe/specs/{name}-execplan.md`
+Storage location: `.vibe/specs/{name}-execplan.md`
 
 ```markdown
 # Execution Plan

package/skills/design-audit/SKILL.md

@@ -131,11 +131,11 @@ When running on mobile stacks (React Native, Flutter, iOS, Android):
 
 Before running the audit:
 
-1. **Read** `.claude/vibe/design-context.json`
+1. **Read** `.vibe/design-context.json`
    - If missing → display: "Run `/design-teach` first for better results" → proceed with defaults
    - If parse error → display warning → proceed with defaults → recommend `/design-teach`
    - If present → weight findings by `audience.context`, `constraints.accessibility`, `brand.personality`
-2. **Read** `.claude/vibe/design-system/*/MASTER.md` (if exists) for token reference
+2. **Read** `.vibe/design-system/*/MASTER.md` (if exists) for token reference
 
 ## Next Steps
 
@@ -148,5 +148,5 @@ Before running the audit:
 ## Important
 
 - **Read-only**: This skill produces a report. It does NOT modify code.
-- **Context-aware**: If `.claude/vibe/design-context.json` exists, findings are weighted by project brand and audience.
+- **Context-aware**: If `.vibe/design-context.json` exists, findings are weighted by project brand and audience.
 - **Incremental**: When run on `.` (changed files), only audits files in current diff.

package/skills/design-critique/SKILL.md

@@ -118,7 +118,7 @@ When running on mobile stacks (React Native, Flutter, iOS, Android):
 
 Before running the critique:
 
-1. **Read** `.claude/vibe/design-context.json`
+1. **Read** `.vibe/design-context.json`
    - If missing → display: "Run `/design-teach` first for better results" → proceed with defaults
    - If parse error → display warning → proceed with defaults → recommend `/design-teach`
    - If present → adjust persona priorities by `audience.primary` and `audience.expertise`
@@ -135,5 +135,5 @@ Before running the critique:
 ## Important
 
 - **Read-only**: Produces design critique report. No code modifications.
-- **Context-aware**: Uses `.claude/vibe/design-context.json` for brand/audience context if available.
+- **Context-aware**: Uses `.vibe/design-context.json` for brand/audience context if available.
 - **Complementary**: Pairs with `/design-audit` (technical) — critique focuses on UX quality.