@su-record/vibe 2.9.36 → 2.9.38

package/CLAUDE.md

@@ -69,7 +69,7 @@ Legacy: 기존 `.claude/vibe/`·`.coco/vibe/` 는 런타임에 자동 인식되
 
 ## Workflow
 
-`/vibe.spec` is the single entry point — orchestrates interview → plan → spec → review → `/vibe.run` → `/vibe.verify` → `/vibe.contract` → `/vibe.trace`. For UI types (website/webapp/mobile), `/vibe.figma` branches in parallel. Smart Resume detects existing `.claude/vibe/{interviews,plans,specs}/*.md` to skip phases.
+`/vibe.spec` is the single entry point — orchestrates interview → plan → spec → review → `/vibe.run` → `/vibe.verify` → `/vibe.contract` → `/vibe.trace`. For UI types (website/webapp/mobile), `/vibe.figma` branches in parallel. Smart Resume detects existing `.vibe/{interviews,plans,specs}/*.md` to skip phases.
 
 **Quality-loop commands** (bug → prevention):
 - `/vibe.regress` — Regression test auto-evolution. Auto-registers on `/vibe.verify` failure; `generate` produces preventive tests; `cluster` promotes recurring patterns.

package/README.en.md

@@ -27,7 +27,7 @@ One entry point. Everything else is automatic.
   Interview  ─── "Who's the audience?" "What sections?" "Dark mode?" ───
      |                     (loops until you say stop)
      v
-  Plan       ─── Structured planning document (.claude/vibe/plans/)
+  Plan       ─── Structured planning document (.vibe/plans/)
      |
      v
   SPEC       ─── PTCF spec + BDD features, GPT+Gemini parallel research

package/README.md

@@ -27,7 +27,7 @@ vibe init
   인터뷰    ─── "타깃은 누구?" "어떤 섹션?" "다크 모드?" ───
      |                   (사용자가 "그만"할 때까지 반복)
      v
-  기획서    ─── 구조화된 마크다운 기획서 (.claude/vibe/plans/)
+  기획서    ─── 구조화된 마크다운 기획서 (.vibe/plans/)
      |
      v
   SPEC     ─── PTCF 명세 + BDD 피처, GPT+Gemini 병렬 리서치

package/agents/compounder.md

@@ -75,7 +75,7 @@ Parallel agents analyze the solution:
 ### Phase 2: Category Classification
 
 ```
-.claude/vibe/solutions/
+.vibe/solutions/
 ├── security/           # Security related
 │   ├── sql-injection-prevention.md
 │   └── xss-sanitization.md
@@ -161,7 +161,7 @@ cache_key = f"user:{user_id}:v{updated_at.timestamp()}"
 
 ### Phase 4: Index Update
 
-Auto-update `.claude/vibe/solutions/index.md`:
+Auto-update `.vibe/solutions/index.md`:
 
 ```markdown
 # Solution Index
@@ -196,7 +196,7 @@ When similar problem detected:
 │  You're working on: "Cache not updating"                        │
 │                                                                 │
 │  Related solution (85% match):                                  │
-│  📄 .claude/vibe/solutions/performance/redis-cache-invalidation.md     │
+│  📄 .vibe/solutions/performance/redis-cache-invalidation.md     │
 │                                                                 │
 │  Key insight: Add version suffix to cache key                   │
 │                                                                 │
@@ -212,7 +212,7 @@ When similar problem detected:
 │  📚 SOLUTION DOCUMENTED                                          │
 ├─────────────────────────────────────────────────────────────────┤
 │                                                                 │
-│  ✅ Created: .claude/vibe/solutions/performance/redis-cache-invalid... │
+│  ✅ Created: .vibe/solutions/performance/redis-cache-invalid... │
 │                                                                 │
 │  📊 Knowledge Base Stats:                                        │
 │  ├── Total Solutions: 42                                        │
@@ -239,7 +239,7 @@ Auto-invoke `core_save_memory`:
   "category": "performance",
   "title": "Redis cache invalidation",
   "keywords": ["redis", "cache", "invalidation"],
-  "file": ".claude/vibe/solutions/performance/redis-cache-invalidation.md"
+  "file": ".vibe/solutions/performance/redis-cache-invalidation.md"
 }
 ```
 
@@ -249,7 +249,7 @@ Auto-invoke `core_save_memory`:
 /vibe.spec → /vibe.run → /vibe.verify → /vibe.compound
                                               │
                                               ▼
-                                    .claude/vibe/solutions/
+                                    .vibe/solutions/
                                               │
                                               ▼
                                     Future problem?

package/agents/diagrammer.md

@@ -159,7 +159,7 @@ erDiagram
 ```
 
 **Diagram save location:**
-  .claude/vibe/diagrams/erd-2025-11-17.md
+  .vibe/diagrams/erd-2025-11-17.md
 
 **Rendering options:**
   1. Push to GitHub (auto-renders)
@@ -171,7 +171,7 @@ erDiagram
 
 - Mermaid is supported in GitHub, GitLab, VSCode, etc.
 - Complex diagrams may need manual adjustments
-- Generated diagrams are saved in `.claude/vibe/diagrams/` folder
+- Generated diagrams are saved in `.vibe/diagrams/` folder
 
 ---
 

package/agents/e2e-tester.md

@@ -81,8 +81,8 @@ AI에게 필요한 건 후자다.
 
 ```
 Scenario Detection
-├── .claude/vibe/features/{feature}.feature → Extract BDD scenarios
-├── .claude/vibe/specs/{feature}.md → Check acceptance criteria
+├── .vibe/features/{feature}.feature → Extract BDD scenarios
+├── .vibe/specs/{feature}.md → Check acceptance criteria
 └── Analyze existing e2e/*.spec.ts
 ```
 
@@ -189,8 +189,8 @@ E2E scenario FAILED
 ```
 Comparing screenshots:
 ├── login-page.png
-│   ├── Baseline: .claude/vibe/e2e/baseline/login-page.png
-│   ├── Current:  .claude/vibe/e2e/current/login-page.png
+│   ├── Baseline: .vibe/e2e/baseline/login-page.png
+│   ├── Current:  .vibe/e2e/current/login-page.png
 │   └── Diff: 0.02% (threshold: 1%) → PASS
 ├── dashboard.png
 │   └── Diff: 5.3% (threshold: 1%) → FAIL → auto-fix loop
@@ -240,7 +240,7 @@ Token Usage: ~2,400 chars (vs ~96,000 with DOM-based approach)
 
 ## Configuration
 
-`.claude/vibe/e2e/config.json`:
+`.vibe/e2e/config.json`:
 
 ```json
 {

package/agents/qa/acceptance-tester.md

@@ -27,8 +27,8 @@
 This agent analyzes **SPEC and Feature documents**, NOT source code.
 
 Input files:
-- `.claude/vibe/specs/{feature-name}.md` - SPEC with `<acceptance>` section
-- `.claude/vibe/features/{feature-name}.feature` - Feature with Gherkin scenarios
+- `.vibe/specs/{feature-name}.md` - SPEC with `<acceptance>` section
+- `.vibe/features/{feature-name}.feature` - Feature with Gherkin scenarios
 
 ## Checklist
 

package/agents/refactor-cleaner.md

@@ -64,7 +64,7 @@ Task(model: "sonnet", prompt: "Find and remove dead code, maintain DELETION_LOG"
 
 ## DELETION_LOG Format
 
-Create/update `.claude/vibe/DELETION_LOG.md`:
+Create/update `.vibe/DELETION_LOG.md`:
 
 ```markdown
 # Deletion Log
@@ -112,7 +112,7 @@ Create/update `.claude/vibe/DELETION_LOG.md`:
 
 ### DELETION_LOG Updated
 - Added 18 entries
-- Location: .claude/vibe/DELETION_LOG.md
+- Location: .vibe/DELETION_LOG.md
 ```
 
 ## Anti-Patterns

package/agents/tester.md

@@ -22,7 +22,7 @@ Task(model: "haiku", prompt: "Write tests for the implemented code")
 
 ## Process
 
-1. Check `.claude/vibe/features/{feature-name}.feature`
+1. Check `.vibe/features/{feature-name}.feature`
 2. Analyze implemented code
 3. Write test cases
 4. Run tests

package/agents/ui/ui-antipattern-detector.md

@@ -24,7 +24,7 @@
 
 1. Receive list of changed UI files from git diff
 2. Read each changed file
-3. Load MASTER.md from `.claude/vibe/design-system/{project}/MASTER.md` if exists
+3. Load MASTER.md from `.vibe/design-system/{project}/MASTER.md` if exists
 4. Use `core_ui_search` for anti-pattern detection rules
 5. Compare implementation against design system tokens
 6. Return findings with anti-pattern name and suggested fix

package/agents/ui/ui-design-system-gen.md

@@ -24,7 +24,7 @@
 
 ## Process
 
-1. Read `.claude/vibe/design-system/{project}/analysis-result.json` from ①
+1. Read `.vibe/design-system/{project}/analysis-result.json` from ①
 2. Use `core_ui_search` to retrieve detailed style, color, typography data
 3. Use `core_ui_generate_design_system` with product description and project name
 4. Use `core_ui_persist_design_system` to write MASTER.md
@@ -32,8 +32,8 @@
 
 ## Output
 
-- **Primary**: `.claude/vibe/design-system/{project}/MASTER.md`
-- **Optional**: `.claude/vibe/design-system/{project}/pages/{page}.md`
+- **Primary**: `.vibe/design-system/{project}/MASTER.md`
+- **Optional**: `.vibe/design-system/{project}/pages/{page}.md`
 
 ## MASTER.md Structure
 

package/agents/ui/ui-industry-analyzer.md

@@ -27,7 +27,7 @@
 3. Use `core_ui_search` with domain `style` to determine style priority
 4. Use `core_ui_search` with domain `color` to determine color mood
 5. Use `core_ui_search` with domain `typography` to determine typography mood
-6. Save result to `.claude/vibe/design-system/{project}/analysis-result.json`
+6. Save result to `.vibe/design-system/{project}/analysis-result.json`
 
 ## Output Format
 

package/agents/ui/ui-layout-architect.md

@@ -22,7 +22,7 @@
 
 ## Process
 
-1. Read `.claude/vibe/design-system/{project}/analysis-result.json` from ①
+1. Read `.vibe/design-system/{project}/analysis-result.json` from ①
 2. Use `core_ui_search` with domain `landing` for page patterns
 3. Use `core_ui_search` with domain `product` for product-specific layouts
 4. Design section structure with component hierarchy

package/agents/ui/ui-stack-implementer.md

@@ -24,7 +24,7 @@
 ## Process
 
 1. Detect project tech stack from package.json or project files
-2. Load MASTER.md from `.claude/vibe/design-system/{project}/MASTER.md` if exists
+2. Load MASTER.md from `.vibe/design-system/{project}/MASTER.md` if exists
 3. Use `core_ui_stack_search` with detected stack for framework patterns
 4. Use `core_ui_search` with domain `react` for performance patterns (if React/Next.js)
 5. Generate implementation guidelines mapping design system to framework

package/commands/vibe.analyze.md

@@ -389,7 +389,7 @@ If `WebFetch` fails:
 
 ### Report
 
-Save to `.claude/vibe/reports/analysis-{date}.md`:
+Save to `.vibe/reports/analysis-{date}.md`:
 
 ```markdown
 # Project Analysis Report

package/commands/vibe.contract.md

@@ -12,7 +12,7 @@ argument-hint: "extract | check | diff [feature-name]"
 ## Usage
 
 ```
-/vibe.contract extract <feature>       # SPEC → contract record at .claude/vibe/contracts/<feature>.md
+/vibe.contract extract <feature>       # SPEC → contract record at .vibe/contracts/<feature>.md
 /vibe.contract check <feature>         # contract vs implementation, drift report
 /vibe.contract diff <feature>          # changed fields since last check
 ```
@@ -53,7 +53,7 @@ Load skill `vibe-contract` with subcommand: `$ARGUMENTS`
 ## Storage Format
 
 ```
-.claude/vibe/contracts/
+.vibe/contracts/
   <feature>.md           # extracted contract (SSOT)
   <feature>.snapshot.md  # implementation snapshot at last check (for diff)
 ```

package/commands/vibe.figma.md

@@ -64,7 +64,7 @@ Step 3) Create 모드 결정
 Step 4) 모순 검증 (즉시 reject — 진행 금지)
   isBranch3 AND hasNew                  → ❌ "--create-* 와 --new는 함께 사용할 수 없습니다."
   isBranch3 AND mdArg == null           → ❌ "--create-* 는 plan.md 경로가 필요합니다.
-                                              예: /vibe.figma .claude/vibe/plans/foo.md --create"
+                                              예: /vibe.figma .vibe/plans/foo.md --create"
   isBranch3 AND urlArgs.length > 0      → ❌ "--create-* 모드에서는 figma URL을 위치 인자로 받지 않습니다.
                                               target 파일은 Step B에서 질문합니다."
   NOT isBranch3 AND mdArg != null       → ⚠ "plan.md를 받았지만 --create-* 플래그가 없습니다.
@@ -130,7 +130,7 @@ AskUserQuestion 사용 시 절대 선택지(options) 제공 금지. 자유 텍
    ⛔ design-teach 스킬을 자동으로 로드하지 말 것 (인터랙티브라 흐름이 끊김)
 
    알고리즘:
-     - Read .claude/vibe/design-context.json
+     - Read .vibe/design-context.json
      - 존재 → 메모리에 binding 후 계속
      - 없음 → 다음 한 줄만 출력하고 계속:
          "💡 design-context.json 없음 — 기본값으로 진행합니다.
@@ -351,7 +351,7 @@ Load skill `design-audit`
    ✅ 피처명 결정: mdArg 파일명에서 .md 제거한 값을 {feature}로 사용
 
 2. Design context 로드 (non-interactive 기본)
-   - Read .claude/vibe/design-context.json
+   - Read .vibe/design-context.json
      · 존재 → 톤/팔레트 보강용으로 binding
      · 없음 → plan.md의 "## 7. Look & Feel" 값으로 임시 컨텍스트 구성
    - hasTeach == true 인 경우에만 Load skill `design-teach`로 인터랙티브 보강

package/commands/vibe.harness.md

@@ -35,10 +35,10 @@ Agent(subagent_type="explorer-low", model="haiku",
   prompt="Check project scaffolding: 1) Does docs/ exist with business documents? 2) Does .dev/ exist for AI logs? 3) Is src/ organized by role (not flat)? 4) Is tests/ separate from src/? 5) List top-level directory structure.")
 
 Agent(subagent_type="explorer-low", model="haiku",
-  prompt="Check project context and boundaries: 1) Does CLAUDE.md exist? How many lines? 2) Does .claude/rules/ or .claude/vibe/ exist? How many rule files? 3) Does .claude/settings.local.json exist with hooks? 4) Does .claude/vibe/config.json exist? 5) Are there any .claude/skills/ directories?")
+  prompt="Check project context and boundaries: 1) Does CLAUDE.md exist? How many lines? 2) Does .claude/rules/ or .vibe/ exist? How many rule files? 3) Does .claude/settings.local.json exist with hooks? 4) Does .vibe/config.json exist? 5) Are there any .claude/skills/ directories?")
 
 Agent(subagent_type="explorer-low", model="haiku",
-  prompt="Check project planning, execution, and verification: 1) Are there SPEC files in .claude/vibe/specs/? 2) Are there Feature (BDD) files in .claude/vibe/features/? 3) Are there test files? How many? 4) Is there CI config (.github/workflows, etc.)? 5) Are there .dev/learnings/ files?")
+  prompt="Check project planning, execution, and verification: 1) Are there SPEC files in .vibe/specs/? 2) Are there Feature (BDD) files in .vibe/features/? 3) Are there test files? How many? 4) Is there CI config (.github/workflows, etc.)? 5) Are there .dev/learnings/ files?")
 ```
 
 ### 2. Score Each Axis
@@ -147,7 +147,7 @@ Proceed with auto-fix? (y/n)
 
 ### 4. Save Report
 
-Save results to `.claude/vibe/reports/harness-{date}.md` for historical tracking.
+Save results to `.vibe/reports/harness-{date}.md` for historical tracking.
 
 ### 5. Self-Repair Chain
 

package/commands/vibe.regress.md

@@ -33,14 +33,14 @@ The `vibe-regress` skill performs registration, generation, and clustering.
 **Core steps** (see `skills/vibe-regress/SKILL.md` for details):
 
 1. Parse subcommand
-2. Read/write `.claude/vibe/regressions/<slug>.md` (frontmatter schema enforced)
+2. Read/write `.vibe/regressions/<slug>.md` (frontmatter schema enforced)
 3. On `generate`, detect the project's test stack → choose template (vitest / jest)
 4. On `cluster`, group by `root-cause-tag`; ≥3 entries → propose a shared test
 5. On `import`, parse `git log --grep='^fix:'`; skip duplicates by commit hash
 
 ## Output
 
-- `.claude/vibe/regressions/<slug>.md` — bug record (frontmatter + reproduction / root cause)
+- `.vibe/regressions/<slug>.md` — bug record (frontmatter + reproduction / root cause)
 - Project test dir — generated vitest file (`*.regression.test.ts`)
 - `list` prints a terminal table
 

package/commands/vibe.review.md

@@ -213,7 +213,7 @@ Read CLAUDE.md         -> Explicit tech stack declaration
 > When SPEC files exist, verify that code changes align with the SPEC
 
 ```
-1. Search .claude/vibe/specs/ for related SPEC files (based on git diff filenames)
+1. Search .vibe/specs/ for related SPEC files (based on git diff filenames)
 2. Compare SPEC REQ-* list against functionality in changed code
 3. If functionality added that's not in SPEC → P2 finding: "Feature added without SPEC"
 4. If implementation differs from SPEC → P1 finding: "SPEC ↔ code mismatch"
@@ -256,7 +256,7 @@ node -e "import('{{VIBE_PATH_URL}}/node_modules/@su-record/vibe/dist/infra/orche
 ### Phase 2.5: UI/UX Review Agents (Auto-triggered)
 
 > **활성화 조건**: 변경된 파일 중 UI 파일 존재 (`.tsx`, `.jsx`, `.vue`, `.svelte`, `.html`, `.css`, `.scss`)
-> **비활성화**: `.claude/vibe/config.json`에 `"uiUxAnalysis": false` 설정
+> **비활성화**: `.vibe/config.json`에 `"uiUxAnalysis": false` 설정
 
 **기존 12+ 리뷰 에이전트와 병렬 실행:**
 
@@ -279,7 +279,7 @@ Task(subagent_type="ui-a11y-auditor",
 
 # ⑧ 안티패턴 검출 (Haiku)
 Task(subagent_type="ui-antipattern-detector",
-  prompt="Detect UI anti-patterns in: {changed_ui_files}. Check against MASTER.md if exists at .claude/vibe/design-system/{project}/MASTER.md.")
+  prompt="Detect UI anti-patterns in: {changed_ui_files}. Check against MASTER.md if exists at .vibe/design-system/{project}/MASTER.md.")
 ```
 
 **findings 통합**: ⑥⑦⑧ findings를 기존 findings[]와 병합 → P1/P2/P3 통합 정렬
@@ -427,7 +427,7 @@ Codex 수정 완료 후 해당 리뷰 에이전트가 재검증.
 
 ### Phase 6: Todo File Creation (Items Requiring Manual Handling)
 
-Save **remaining** findings to `.claude/vibe/todos/`:
+Save **remaining** findings to `.vibe/todos/`:
 
 ```
 {priority}-{category}-{short-desc}.md

package/commands/vibe.run.md

@@ -37,7 +37,7 @@ Execute **Scenario-Driven Implementation** with automatic quality verification.
 > **📊 Step Counter Reset (MANDATORY at START)**: Run this Bash command once at the very start to reset the tool-call counter so `/vibe.verify` can report "how many steps to reach the goal":
 >
 > ```bash
-> mkdir -p .claude/vibe/metrics && printf '{"feature":"%s","startedAt":"%s","steps":0}\n' "{feature-name}" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" > .claude/vibe/metrics/current-run.json
+> mkdir -p .vibe/metrics && printf '{"feature":"%s","startedAt":"%s","steps":0}\n' "{feature-name}" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" > .vibe/metrics/current-run.json
 > ```
 
 ## File Reading Policy (Mandatory)
@@ -65,7 +65,7 @@ Load skill `vibe-regress` with: list --feature "{feature-name}"
   - ultrawork mode: auto-invoke `/vibe.regress generate <slug>` for each, then proceed
 - No open regressions → silently continue
 
-Also load `.claude/vibe/contracts/{feature-name}.md` if present — use it as the contract reference during implementation.
+Also load `.vibe/contracts/{feature-name}.md` if present — use it as the contract reference during implementation.
 
 ### Core Flow
 
@@ -172,7 +172,7 @@ After implementing each scenario, **automatic verification**:
 
 **활성화 조건:**
 - Feature 파일에 UI 관련 시나리오 존재 (form, button, page, navigate 등)
-- `.claude/vibe/e2e/config.json`의 `closedLoop.enabled: true` (기본값)
+- `.vibe/e2e/config.json`의 `closedLoop.enabled: true` (기본값)
 - dev server가 실행 중 (`baseURL` 접근 가능)
 
 ### Auto-Fix on Failure
@@ -402,7 +402,7 @@ Type Check: ✅ No errors
 
 ✅ RALPH VERIFIED COMPLETE!
 
-📄 RTM saved: .claude/vibe/rtm/login-rtm.md
+📄 RTM saved: .vibe/rtm/login-rtm.md
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
 
@@ -431,7 +431,7 @@ Claude:
 🚀 ULTRAWORK MODE ACTIVATED
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-📄 SPEC: .claude/vibe/specs/brick-game.md
+📄 SPEC: .vibe/specs/brick-game.md
 🎯 4 Phases detected
 ⚡ Boulder Loop: ENABLED (will continue until all phases complete)
 🔄 Auto-retry: ON (loop until 100% or stuck → auto-TODO)
@@ -757,7 +757,7 @@ Each agent has tier variants for cost optimization:
 
 ### External LLM Usage (When Enabled)
 
-When external LLMs are enabled in `.claude/vibe/config.json`:
+When external LLMs are enabled in `.vibe/config.json`:
 
 | Role | Method | Condition |
 |------|--------|-----------|
@@ -851,25 +851,25 @@ node -e "import('{{VIBE_PATH_URL}}/node_modules/@su-record/vibe/dist/tools/index
 
 ```
 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 for overview)
 ├── phase-1-{name}.md      → Phase 1 SPEC
 ├── phase-2-{name}.md      → Phase 2 SPEC
 └── ...
 
-📁 .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
@@ -881,15 +881,15 @@ Step 3: If neither exists → Error
 
 **Single file detected:**
 ```
-📄 .claude/vibe/specs/{feature-name}.md      → SPEC (structure, constraints, context)
-📄 .claude/vibe/features/{feature-name}.feature → Feature (scenario = implementation unit)
+📄 .vibe/specs/{feature-name}.md      → SPEC (structure, constraints, context)
+📄 .vibe/features/{feature-name}.feature → Feature (scenario = implementation unit)
 ```
 
 **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.
 ```
@@ -915,13 +915,13 @@ Step 3: If neither exists → Error
 │    3. Extract Phase N scope: files, scenarios, requirements      │
 │    4. Implement Phase N scenarios                                 │
 │    5. Verify Phase N                                             │
-│    6. Write Phase Checkpoint → .claude/vibe/checkpoints/         │
+│    6. Write Phase Checkpoint → .vibe/checkpoints/         │
 │    7. DISCARD Phase N details from working memory                │
 │  Step C: Next Phase — go to Step B                               │
 └─────────────────────────────────────────────────────────────────┘
 ```
 
-**Phase Checkpoint Format** (`.claude/vibe/checkpoints/{feature}-phase-{N}.md`):
+**Phase Checkpoint Format** (`.vibe/checkpoints/{feature}-phase-{N}.md`):
 
 ```markdown
 # Checkpoint: {feature} Phase {N}
@@ -996,7 +996,7 @@ Discovery during implementation: "An API endpoint not in SPEC is needed"
     │
     └─ Outside SPEC scope?
         YES → Record as TODO and exclude from current scope
-              .claude/vibe/todos/out-of-scope-{item}.md
+              .vibe/todos/out-of-scope-{item}.md
 ```
 
 **Required when changing SPEC:**
@@ -1245,7 +1245,7 @@ core ProjectCache (LRU) caches ts-morph parsing results. Parallel calls share th
 ### UI/UX Design Intelligence (Auto-triggered before Phase 1)
 
 > **조건**: SPEC 또는 Feature에 UI/UX 키워드 포함 시 자동 실행
-> **비활성화**: `.claude/vibe/config.json`에 `"uiUxAnalysis": false` 설정
+> **비활성화**: `.vibe/config.json`에 `"uiUxAnalysis": false` 설정
 
 **Phase 1 시작 전, 2개 에이전트 자동 실행:**
 
@@ -1267,7 +1267,7 @@ Task(subagent_type="ui-dataviz-advisor",
 ```
 
 **디자인 시스템 자동 참조:**
-- `.claude/vibe/design-system/{project}/MASTER.md` 존재 시 자동 로드
+- `.vibe/design-system/{project}/MASTER.md` 존재 시 자동 로드
 - 구현 에이전트가 CSS 변수, 폰트, 색상 팔레트를 직접 참조
 - 페이지별 오버라이드 `pages/{page}.md` 존재 시 우선 적용
 
@@ -1646,8 +1646,8 @@ Follow during implementation:
 
 ## Input
 
-- `.claude/vibe/specs/{feature-name}.md` (PTCF SPEC)
-- `.claude/vibe/features/{feature-name}.feature` (BDD)
+- `.vibe/specs/{feature-name}.md` (PTCF SPEC)
+- `.vibe/features/{feature-name}.feature` (BDD)
 - `CLAUDE.md` (project context)
 
 ## Output
@@ -1662,8 +1662,8 @@ Follow during implementation:
 User: /vibe.run "login"
 
 Claude:
-📄 Loading SPEC: .claude/vibe/specs/login.md
-📄 Loading Feature: .claude/vibe/features/login.feature
+📄 Loading SPEC: .vibe/specs/login.md
+📄 Loading Feature: .vibe/features/login.feature
 
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 📋 Scenarios to Implement
@@ -1799,7 +1799,7 @@ Then: Login success + JWT token returned
 User: /vibe.run "brick-game" --phase 2
 
 Claude:
-📄 Reading SPEC: .claude/vibe/specs/brick-game.md
+📄 Reading SPEC: .vibe/specs/brick-game.md
 🎯 Executing Phase 2 only.
 
 Phase 2: Game Logic
@@ -1923,7 +1923,7 @@ After ALL phases complete successfully, **automatically** perform a brief retros
 ### Execution Steps
 
 1. Generate retrospective based on the implementation session
-2. Save to `.claude/vibe/retros/{feature-name}.md`
+2. Save to `.vibe/retros/{feature-name}.md`
 3. Save key lessons via `core_save_memory` (for cross-session recall)
 4. Update `claude-progress.txt` with final status
 

package/commands/vibe.scaffold.md

@@ -26,7 +26,7 @@ Design and generate a project structure where AI works effectively on its own.
 
 1. Read `CLAUDE.md`, `package.json`, `pyproject.toml`, `pubspec.yaml`
 2. Scan existing folder structure via `Glob`
-3. Read `.claude/vibe/config.json` for detected stacks
+3. Read `.vibe/config.json` for detected stacks
 
 ### 2. Determine Project Type