@su-record/vibe 1.1.9 → 1.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -5,301 +5,510 @@ argument-hint: "feature name" or --phase N
5
5
 
6
6
  # /vibe.run
7
7
 
8
- SPEC을 기반으로 구현합니다 (Implementation Agent with Multi-Model Orchestration).
8
+ Execute implementation based on SPEC (Implementation Agent with Multi-Model Orchestration).
9
9
 
10
10
  ## Usage
11
11
 
12
12
  ```
13
- /vibe.run "기능명" # 전체 구현
14
- /vibe.run "기능명" --phase 1 # 특정 Phase
13
+ /vibe.run "feature-name" # Full implementation
14
+ /vibe.run "feature-name" --phase 1 # Specific Phase only
15
+ /vibe.run "feature-name" ultrawork # ULTRAWORK mode (recommended)
16
+ /vibe.run "feature-name" ulw # Short alias for ultrawork
15
17
  ```
16
18
 
19
+ ---
20
+
21
+ ## **ULTRAWORK Mode** (ulw)
22
+
23
+ > Include `ultrawork` or `ulw` in your command to activate **maximum performance mode**.
24
+
25
+ ### What ULTRAWORK Enables
26
+
27
+ When you include `ultrawork` (or `ulw`), ALL of these activate automatically:
28
+
29
+ | Feature | Description |
30
+ |---------|-------------|
31
+ | **Parallel Exploration** | 3+ Task(haiku) agents run simultaneously |
32
+ | **Boulder Loop** | Auto-continues until ALL phases complete |
33
+ | **Context Compression** | Aggressive auto-save at 70%+ context |
34
+ | **No Pause** | Doesn't wait for confirmation between phases |
35
+ | **External LLMs** | Auto-consults GPT/Gemini if enabled |
36
+ | **Error Recovery** | Auto-retries on failure (up to 3 times) |
37
+
38
+ ### Boulder Loop (Inspired by Sisyphus)
39
+
40
+ Like Sisyphus rolling the boulder, ULTRAWORK **keeps going until done**:
41
+
42
+ ```
43
+ ┌─────────────────────────────────────────────────────────────────┐
44
+ │ BOULDER LOOP (ultrawork) │
45
+ │ │
46
+ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
47
+ │ │ Phase 1 │───→│ Phase 2 │───→│ Phase 3 │───→│ Phase N │ │
48
+ │ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │
49
+ │ │ │ │ │ │
50
+ │ ↓ ↓ ↓ ↓ │
51
+ │ [Parallel] [Parallel] [Parallel] [Parallel] │
52
+ │ [Implement] [Implement] [Implement] [Implement] │
53
+ │ [Test] [Test] [Test] [Test] │
54
+ │ │ │ │ │ │
55
+ │ └───────────────┴───────────────┴───────────────┘ │
56
+ │ │ │
57
+ │ ↓ │
58
+ │ ┌──────────────┐ │
59
+ │ │ ALL DONE? │ │
60
+ │ └──────────────┘ │
61
+ │ │ │ │
62
+ │ NO YES │
63
+ │ │ │ │
64
+ │ ↓ ↓ │
65
+ │ [Continue] [🎉 Complete!] │
66
+ │ │
67
+ │ NO STOPPING until acceptance criteria met or error limit hit │
68
+ └─────────────────────────────────────────────────────────────────┘
69
+ ```
70
+
71
+ ### ULTRAWORK Example
72
+
73
+ ```
74
+ User: /vibe.run "brick-game" ultrawork
75
+
76
+ Claude:
77
+ 🚀 ULTRAWORK MODE ACTIVATED
78
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
79
+
80
+ 📄 SPEC: .vibe/specs/brick-game.md
81
+ 🎯 4 Phases detected
82
+ ⚡ Boulder Loop: ENABLED (will continue until all phases complete)
83
+ 🔄 Auto-retry: ON (max 3 per phase)
84
+ 💾 Context compression: AGGRESSIVE
85
+
86
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
87
+ 🏔️ BOULDER ROLLING... Phase 1/4
88
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
89
+
90
+ ⚡ [PARALLEL] Launching 3 exploration agents...
91
+ ✅ Exploration complete (7.2s)
92
+ 🔨 Implementing...
93
+ ✅ Phase 1 complete
94
+
95
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
96
+ 🏔️ BOULDER ROLLING... Phase 2/4
97
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
98
+
99
+ ⚡ [PARALLEL] Launching 3 exploration agents...
100
+ ✅ Exploration complete (6.8s)
101
+ 🔨 Implementing...
102
+ ❌ Test failed: collision detection
103
+ 🔄 Auto-retry 1/3...
104
+ 🔨 Fixing...
105
+ ✅ Phase 2 complete
106
+
107
+ [...continues automatically...]
108
+
109
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
110
+ 🎉 BOULDER REACHED THE TOP!
111
+ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
112
+
113
+ ✅ All 4 phases complete
114
+ ✅ All acceptance criteria passed
115
+ ✅ Build succeeded
116
+ ✅ Tests passed
117
+
118
+ ⏱️ Total: 8m 24s
119
+ 📊 Retries: 2
120
+ 💾 Context saved: 3 checkpoints
121
+ ```
122
+
123
+ ### Normal vs ULTRAWORK Comparison
124
+
125
+ | Aspect | Normal | ULTRAWORK |
126
+ |--------|--------|-----------|
127
+ | Phase transition | May pause | Auto-continues |
128
+ | On error | Reports and stops | Auto-retries (3x) |
129
+ | Context 70%+ | Warning only | Auto-compress + save |
130
+ | Exploration | Sequential possible | FORCED parallel |
131
+ | Completion | Phase-by-phase | Until ALL done |
132
+
133
+ ---
134
+
17
135
  ## Rules Reference
18
136
 
19
- **반드시 `.vibe/rules/` 규칙을 따릅니다:**
20
- - `core/development-philosophy.md` - 수술적 정밀도, 요청 범위만 수정
21
- - `core/quick-start.md` - 한국어, DRY, SRP, YAGNI
22
- - `standards/complexity-metrics.md` - 함수 ≤20줄, 중첩 ≤3단계
23
- - `quality/checklist.md` - 코드 품질 체크리스트
137
+ **Must follow `.vibe/rules/`:**
138
+ - `core/development-philosophy.md` - Surgical precision, modify only requested scope
139
+ - `core/quick-start.md` - Korean, DRY, SRP, YAGNI
140
+ - `standards/complexity-metrics.md` - Functions ≤20 lines, nesting ≤3 levels
141
+ - `quality/checklist.md` - Code quality checklist
24
142
 
25
143
  ## Description
26
144
 
27
- PTCF 구조의 SPEC 문서를 읽고 바로 구현을 실행합니다.
145
+ Read PTCF structured SPEC document and execute implementation immediately.
28
146
 
29
- > **PLAN, TASKS 문서 불필요** - SPEC 실행 가능한 프롬프트
147
+ > **PLAN, TASKS documents unnecessary** - SPEC is the executable prompt
30
148
 
31
- ## 모델 오케스트레이션
149
+ ## Model Orchestration
32
150
 
33
- 작업 유형에 따라 최적의 모델을 자동 선택합니다:
151
+ Automatically select optimal model based on task type:
34
152
 
35
153
  ```
36
154
  ┌─────────────────────────────────────────────────────────────┐
37
- │ Opus 4.5 (오케스트레이터) │
38
- │ - 전체 흐름 조율
39
- │ - 최종 결정/검토
155
+ │ Opus 4.5 (Orchestrator) │
156
+ │ - Coordinate overall flow
157
+ │ - Final decisions/review
40
158
  └─────────────────────────┬───────────────────────────────────┘
41
159
 
42
160
  ┌─────────────────────┼─────────────────────┐
43
161
  ↓ ↓ ↓
44
162
  ┌─────────┐ ┌─────────┐ ┌─────────┐
45
163
  │ Haiku │ │ Sonnet │ │ Haiku │
46
- (탐색) │ │ (구현) │ │(테스트)
164
+ │(Explore)│ │ (Impl) │ │ (Test)
47
165
  └─────────┘ └─────────┘ └─────────┘
48
166
  ```
49
167
 
50
- ### 역할별 Task 호출
168
+ ### Task Calls by Role
51
169
 
52
- | 작업 유형 | 모델 | Task 파라미터 |
53
- |----------|------|---------------|
54
- | 코드베이스 탐색 | Haiku 4.5 | `model: "haiku"` |
55
- | 핵심 구현 | Sonnet 4 | `model: "sonnet"` |
56
- | 테스트 작성 | Haiku 4.5 | `model: "haiku"` |
57
- | 아키텍처 결정 | Opus 4.5 | 메인 세션 |
58
- | 최종 검토 | Opus 4.5 | 메인 세션 |
170
+ | Task Type | Model | Task Parameter |
171
+ |-----------|-------|----------------|
172
+ | Codebase exploration | Haiku 4.5 | `model: "haiku"` |
173
+ | Core implementation | Sonnet 4 | `model: "sonnet"` |
174
+ | Test writing | Haiku 4.5 | `model: "haiku"` |
175
+ | Architecture decisions | Opus 4.5 | Main session |
176
+ | Final review | Opus 4.5 | Main session |
59
177
 
60
- ### 외부 LLM 활용 (활성화 )
178
+ ### External LLM Usage (When Enabled)
61
179
 
62
- `.vibe/config.json`에서 외부 LLM이 활성화된 경우:
180
+ When external LLMs are enabled in `.vibe/config.json`:
63
181
 
64
- | 역할 | 모델 | 조건 |
65
- |------|------|------|
66
- | 아키텍처/디버깅 | GPT 5.2 | `vibe gpt <key>` 실행 |
67
- | UI/UX 설계 | Gemini 3 | `vibe gemini <key>` 실행 |
182
+ | Role | Model | Condition |
183
+ |------|-------|-----------|
184
+ | Architecture/Debugging | GPT 5.2 | When `vibe gpt <key>` executed |
185
+ | UI/UX Design | Gemini 3 | When `vibe gemini <key>` executed |
68
186
 
69
- 외부 LLM 활성화 해당 역할은 MCP를 통해 자동 호출됩니다:
70
- - `mcp__vibe-gpt__chat` - GPT 5.2 아키텍처 자문
71
- - `mcp__vibe-gemini__chat` - Gemini 3 UI/UX 자문
187
+ When external LLM enabled, automatically called via MCP:
188
+ - `mcp__vibe-gpt__chat` - GPT 5.2 architecture consultation
189
+ - `mcp__vibe-gemini__chat` - Gemini 3 UI/UX consultation
72
190
 
73
- ## 시맨틱 코드 분석 (hi-ai MCP)
191
+ ## Semantic Code Analysis (hi-ai MCP)
74
192
 
75
- 구현 코드베이스를 정확히 파악하기 위해 hi-ai MCP의 시맨틱 도구를 활용합니다:
193
+ Use hi-ai MCP semantic tools to accurately understand codebase before implementation:
76
194
 
77
- | MCP 도구 | 용도 | 활용 시점 |
78
- |----------|------|----------|
79
- | `mcp__vibe__find_symbol` | 심볼 정의 찾기 | 클래스/함수 위치 파악 |
80
- | `mcp__vibe__find_references` | 참조 찾기 | 영향 범위 분석 |
81
- | `mcp__vibe__analyze_complexity` | 복잡도 분석 | 리팩토링 필요 여부 판단 |
82
- | `mcp__vibe__validate_code_quality` | 품질 검증 | 구현 품질 확인 |
195
+ | MCP Tool | Purpose | When Used |
196
+ |----------|---------|-----------|
197
+ | `mcp__vibe__find_symbol` | Find symbol definitions | Locate class/function |
198
+ | `mcp__vibe__find_references` | Find references | Analyze impact scope |
199
+ | `mcp__vibe__analyze_complexity` | Analyze complexity | Determine refactoring need |
200
+ | `mcp__vibe__validate_code_quality` | Validate quality | Verify post-implementation quality |
83
201
 
84
- ### 시맨틱 분석 흐름
202
+ ### Semantic Analysis Flow
85
203
 
86
204
  ```
87
- 구현 시작
205
+ Start Implementation
88
206
 
89
- ├─→ find_symbol: 수정할 함수/클래스 정확한 위치 파악
207
+ ├─→ find_symbol: Locate exact position of function/class to modify
90
208
 
91
- ├─→ find_references: 해당 심볼을 사용하는 모든 확인
209
+ ├─→ find_references: Check all places using that symbol
92
210
 
93
- ├─→ analyze_complexity: 기존 코드 복잡도 확인
211
+ ├─→ analyze_complexity: Check existing code complexity
94
212
 
95
213
 
96
- 구현 (영향 범위를 정확히 파악한 상태에서)
214
+ Implementation (with accurate understanding of impact scope)
97
215
 
98
216
 
99
- validate_code_quality: 구현 품질 검증
217
+ validate_code_quality: Verify quality after implementation
100
218
  ```
101
219
 
102
- ### 컨텍스트 관리 (세션 연속성)
220
+ ### Context Management (Session Continuity)
103
221
 
104
- | MCP 도구 | 용도 |
105
- |----------|------|
106
- | `mcp__vibe__start_session` | 세션 시작, 이전 컨텍스트 복원 |
107
- | `mcp__vibe__auto_save_context` | 현재 상태 자동 저장 |
108
- | `mcp__vibe__restore_session_context` | 이전 세션 컨텍스트 복원 |
109
- | `mcp__vibe__save_memory` | 중요 결정사항/패턴 저장 |
222
+ | MCP Tool | Purpose |
223
+ |----------|---------|
224
+ | `mcp__vibe__start_session` | Start session, restore previous context |
225
+ | `mcp__vibe__auto_save_context` | Auto-save current state |
226
+ | `mcp__vibe__restore_session_context` | Restore previous session context |
227
+ | `mcp__vibe__save_memory` | Save important decisions/patterns |
110
228
 
111
- **세션 시작 시**: `mcp__vibe__start_session`으로 이전 컨텍스트 자동 복원
112
- **세션 종료 시**: Hook `mcp__vibe__auto_save_context` 자동 실행
229
+ **On session start**: `mcp__vibe__start_session` auto-restores previous context
230
+ **On session end**: Hook auto-executes `mcp__vibe__auto_save_context`
113
231
 
114
232
  ## Process
115
233
 
116
- ### 1. SPEC 설정 읽기
234
+ ### 1. Read SPEC and Config
117
235
 
118
- `.vibe/specs/{기능명}.md` 파싱:
236
+ Parse `.vibe/specs/{feature-name}.md`:
119
237
 
120
- | 섹션 | 용도 |
121
- |------|------|
122
- | `<role>` | AI 역할 정의 |
123
- | `<context>` | 배경, 기술 스택, 관련 코드 |
124
- | `<task>` | Phase 작업 목록 |
125
- | `<constraints>` | 제약 조건 |
126
- | `<output_format>` | 생성/수정할 파일 |
127
- | `<acceptance>` | 검증 기준 |
238
+ | Section | Purpose |
239
+ |---------|---------|
240
+ | `<role>` | AI role definition |
241
+ | `<context>` | Background, tech stack, related code |
242
+ | `<task>` | Phase-by-phase task list |
243
+ | `<constraints>` | Constraints |
244
+ | `<output_format>` | Files to create/modify |
245
+ | `<acceptance>` | Verification criteria |
128
246
 
129
- `.vibe/config.json` 확인:
130
- - 외부 LLM 활성화 여부 (`models.gpt.enabled`, `models.gemini.enabled`)
247
+ Check `.vibe/config.json`:
248
+ - External LLM enablement (`models.gpt.enabled`, `models.gemini.enabled`)
131
249
 
132
- ### 2. Feature 파일 확인
250
+ ### 2. Check Feature File
133
251
 
134
- `.vibe/features/{기능명}.feature`:
135
- - BDD Scenarios 확인
136
- - 테스트 케이스로 활용
252
+ `.vibe/features/{feature-name}.feature`:
253
+ - Check BDD Scenarios
254
+ - Use as test cases
137
255
 
138
- ### 3. Phase 구현 (Task 병렬 호출)
256
+ ### 3. Phase-by-Phase Implementation
139
257
 
140
- `<task>` 섹션의 Phase 순서대로:
258
+ Follow `<task>` section Phase order.
259
+
260
+ ---
261
+
262
+ ## **CRITICAL: Parallel Sub-Agent Execution**
263
+
264
+ > **MUST USE PARALLEL TASK CALLS** - This is REQUIRED, not optional.
265
+ > Sequential execution when parallel is possible = VIOLATION of this workflow.
266
+
267
+ ### Mandatory Parallel Exploration (Phase Start)
268
+
269
+ **BEFORE any implementation, you MUST launch these Task calls IN PARALLEL (single message, multiple tool calls):**
141
270
 
142
271
  ```
143
- Phase 시작
144
-
145
- ├─→ Task(haiku): 코드베이스 분석
146
- "관련 파일과 패턴을 분석하세요"
272
+ ┌─────────────────────────────────────────────────────────────────┐
273
+ STEP 1: PARALLEL EXPLORATION (REQUIRED) │
274
+ │ │
275
+ Launch ALL of these in ONE message: │
276
+ │ │
277
+ │ Task(haiku) ─┬─→ "Analyze related files in <context>" │
278
+ │ │ │
279
+ │ Task(haiku) ─┼─→ "Check dependencies and imports" │
280
+ │ │ │
281
+ │ Task(haiku) ─┴─→ "Find existing patterns and conventions" │
282
+ │ │
283
+ │ [If GPT enabled] + MCP(vibe-gpt): Architecture review │
284
+ │ [If Gemini enabled] + MCP(vibe-gemini): UI/UX consultation │
285
+ └─────────────────────────────────────────────────────────────────┘
286
+
287
+ ↓ (wait for all to complete)
288
+ ┌─────────────────────────────────────────────────────────────────┐
289
+ │ STEP 2: SYNTHESIZE (Opus) │
290
+ │ - Review all exploration results │
291
+ │ - Decide implementation approach │
292
+ │ - Identify files to modify/create │
293
+ └─────────────────────────────────────────────────────────────────┘
294
+
295
+
296
+ ┌─────────────────────────────────────────────────────────────────┐
297
+ │ STEP 3: IMPLEMENT (Task sonnet) │
298
+ │ - Execute implementation with full context │
299
+ └─────────────────────────────────────────────────────────────────┘
300
+
301
+
302
+ ┌─────────────────────────────────────────────────────────────────┐
303
+ │ STEP 4: TEST (Task haiku) │
304
+ │ - Write tests for implemented code │
305
+ └─────────────────────────────────────────────────────────────────┘
306
+ ```
307
+
308
+ ### Parallel Task Call Pattern (MUST FOLLOW)
309
+
310
+ **Correct - Single message with multiple parallel Tasks:**
311
+ ```
312
+ <message>
313
+ Task(haiku, "Analyze src/components/ for existing patterns")
314
+ Task(haiku, "Check package.json dependencies")
315
+ Task(haiku, "Find usage of similar features in codebase")
316
+ </message>
317
+ → All 3 run simultaneously, ~3x faster
318
+ ```
319
+
320
+ **WRONG - Sequential calls (DO NOT DO THIS):**
321
+ ```
322
+ <message>Task(haiku, "Analyze...")</message>
323
+ <message>Task(haiku, "Check...")</message>
324
+ <message>Task(haiku, "Find...")</message>
325
+ → 3x slower, wastes time
326
+ ```
327
+
328
+ ### Why Parallel Matters
329
+
330
+ | Approach | Time | Cache Benefit |
331
+ |----------|------|---------------|
332
+ | Sequential (3 Tasks) | ~30s | Cache cold on each |
333
+ | **Parallel (3 Tasks)** | **~10s** | **Cache warmed once, shared** |
334
+
335
+ hi-ai ProjectCache (LRU) caches ts-morph parsing results. Parallel calls share the warmed cache.
336
+
337
+ ### Phase Execution Flow
338
+
339
+ ```
340
+ Phase N Start
147
341
 
148
- ├─→ [GPT 활성화 시] MCP(vibe-gpt): 아키텍처 검토
149
- "이 설계가 적절한지 검토해주세요"
342
+ ├─→ [PARALLEL] Task(haiku) × 2-3: Exploration
343
+ - Related code analysis
344
+ │ - Dependency check
345
+ │ - Pattern discovery
150
346
 
151
- ├─→ [Gemini 활성화 시] MCP(vibe-gemini): UI/UX 자문
152
- │ "UI 구현 방향을 제안해주세요"
347
+ (all complete)
153
348
 
154
-
155
- Opus: 분석 결과 종합, 구현 방향 결정
349
+ ├─→ Opus: Synthesize and decide
156
350
 
157
-
158
- Task(sonnet): 핵심 구현
159
- "SPEC에 따라 코드를 구현하세요"
351
+ ├─→ Task(sonnet): Implementation
160
352
 
161
-
162
- Task(haiku): 테스트 작성
163
- "구현된 코드의 테스트를 작성하세요"
353
+ ├─→ Task(haiku): Tests
164
354
 
165
355
 
166
- Opus: 최종 검토 다음 Phase
356
+ Phase N Complete Next Phase
167
357
  ```
168
358
 
169
- **병렬 실행 예시:**
170
- ```javascript
171
- // 독립적인 작업은 병렬로 Task 호출
172
- Task(haiku) - 코드 분석
173
- Task(haiku) - 의존성 확인
174
- // → 동시 실행
175
-
176
- // 순차적 작업
177
- Task(sonnet) - 구현 (분석 완료 후)
178
- Task(haiku) - 테스트 (구현 완료 후)
179
- ```
359
+ ---
180
360
 
181
- 1. **관련 코드 분석**: Task(haiku) `<context>`의 관련 코드 탐색
182
- 2. **파일 생성/수정**: Task(sonnet) `<output_format>` 기준 구현
183
- 3. **제약 조건 준수**: `<constraints>` 확인
184
- 4. **검증 실행**: 검증 명령어 실행
361
+ 1. **Related code analysis**: Task(haiku) explores `<context>` related code
362
+ 2. **File creation/modification**: Task(sonnet) implements per `<output_format>`
363
+ 3. **Constraint compliance**: Check `<constraints>`
364
+ 4. **Run verification**: Execute verification commands
185
365
 
186
- ### 4. Acceptance Criteria 검증
366
+ ### 4. Acceptance Criteria Verification
187
367
 
188
- `<acceptance>` 체크리스트 확인:
189
- - [ ] 기준 통과 여부
190
- - [ ] 테스트 통과
191
- - [ ] 빌드 성공
368
+ Check `<acceptance>` checklist:
369
+ - [ ] Each criterion pass status
370
+ - [ ] Tests pass
371
+ - [ ] Build succeeds
192
372
 
193
- ### 5. SPEC 업데이트
373
+ ### 5. Update SPEC
194
374
 
195
- 완료된 Task 체크:
375
+ Check completed Tasks:
196
376
  ```markdown
197
377
  ## Task
198
378
  <task>
199
379
  ### Phase 1: Backend
200
- 1. [x] DB 스키마 작성
201
- 2. [x] API 엔드포인트
380
+ 1. [x] Write DB schema
381
+ 2. [x] API endpoint
202
382
  ...
203
383
  </task>
204
384
  ```
205
385
 
206
- ## TRUST 5 원칙
386
+ ## TRUST 5 Principles
207
387
 
208
- 구현 준수:
388
+ Follow during implementation:
209
389
 
210
- | 원칙 | 설명 |
211
- |------|------|
212
- | **T**est-first | 테스트 먼저 작성 |
213
- | **R**eadable | 명확한 코드 |
214
- | **U**nified | 일관된 스타일 |
215
- | **S**ecured | 보안 고려 |
216
- | **T**rackable | 로깅, 모니터링 |
390
+ | Principle | Description |
391
+ |-----------|-------------|
392
+ | **T**est-first | Write tests first |
393
+ | **R**eadable | Clear code |
394
+ | **U**nified | Consistent style |
395
+ | **S**ecured | Consider security |
396
+ | **T**rackable | Logging, monitoring |
217
397
 
218
398
  ## Input
219
399
 
220
- - `.vibe/specs/{기능명}.md` (PTCF SPEC)
221
- - `.vibe/features/{기능명}.feature` (BDD)
222
- - `CLAUDE.md` (프로젝트 컨텍스트)
400
+ - `.vibe/specs/{feature-name}.md` (PTCF SPEC)
401
+ - `.vibe/features/{feature-name}.feature` (BDD)
402
+ - `CLAUDE.md` (project context)
223
403
 
224
404
  ## Output
225
405
 
226
- - 구현된 코드 파일
227
- - 테스트 파일
228
- - SPEC 문서 업데이트 (체크표시)
406
+ - Implemented code files
407
+ - Test files
408
+ - Updated SPEC document (checkmarks)
229
409
 
230
410
  ## Example
231
411
 
232
412
  ```
233
- User: /vibe.run "벽돌게임"
413
+ User: /vibe.run "brick-game"
234
414
 
235
415
  Claude:
236
- 📄 SPEC 읽는 중: .vibe/specs/brick-game.md
416
+ 📄 Reading SPEC: .vibe/specs/brick-game.md
417
+
418
+ <role> analysis:
419
+ - Web game senior developer
420
+ - Phaser.js expert
421
+
422
+ <context> analysis:
423
+ - Tech stack: Phaser.js, TypeScript
424
+ - New project
237
425
 
238
- <role> 분석:
239
- - 게임 시니어 개발자
240
- - Phaser.js 전문가
426
+ <task> analysis:
427
+ - Phase 1: Project setup (3 tasks)
428
+ - Phase 2: Game logic (5 tasks)
429
+ - Phase 3: UI/UX (3 tasks)
430
+ - Phase 4: Testing (2 tasks)
241
431
 
242
- <context> 분석:
243
- - 기술 스택: Phaser.js, TypeScript
244
- - 신규 프로젝트
432
+ 🚀 Starting Phase 1...
245
433
 
246
- <task> 분석:
247
- - Phase 1: 프로젝트 셋업 (3개 작업)
248
- - Phase 2: 게임 로직 (5개 작업)
249
- - Phase 3: UI/UX (3개 작업)
250
- - Phase 4: 테스트 (2개 작업)
434
+ Launching parallel exploration...
435
+ [Task(haiku) × 3 launched in parallel]
436
+ - Analyzing Phaser.js project patterns
437
+ - Checking TypeScript configuration standards
438
+ - Finding game loop conventions
251
439
 
252
- 🚀 Phase 1 시작...
440
+ Exploration complete (3 tasks, 8.2s)
441
+ 📋 Synthesizing results...
253
442
 
254
- Phase 1 완료
255
- - package.json 생성
256
- - TypeScript 설정
257
- - Phaser.js 설치
443
+ 🔨 Implementing Phase 1...
444
+ [Task(sonnet) - Project setup]
258
445
 
259
- 🚀 Phase 2 시작...
260
- [구현 계속...]
446
+ Phase 1 complete
447
+ - package.json created
448
+ - TypeScript configured
449
+ - Phaser.js installed
261
450
 
262
- 모든 Phase 완료!
263
- 📊 Acceptance Criteria 검증 중...
264
- ✅ 게임 시작/종료 동작
265
- ✅ 공-패들 충돌 처리
266
- ✅ 점수 표시
267
- ✅ npm run build 성공
451
+ 🚀 Starting Phase 2...
268
452
 
269
- 🎉 구현 완료!
453
+ Launching parallel exploration...
454
+ [Task(haiku) × 3 launched in parallel]
455
+ - Analyzing game scene structure
456
+ - Checking physics engine patterns
457
+ - Finding collision detection approaches
458
+
459
+ ✅ Exploration complete (3 tasks, 7.5s)
460
+
461
+ 🔨 Implementing Phase 2...
462
+ [Task(sonnet) - Game logic]
463
+
464
+ [Implementation continues...]
465
+
466
+ ✅ All Phases complete!
467
+ 📊 Verifying Acceptance Criteria...
468
+ ✅ Game start/end works
469
+ ✅ Ball-paddle collision handling
470
+ ✅ Score display
471
+ ✅ npm run build succeeds
472
+
473
+ 🎉 Implementation complete!
474
+
475
+ ⏱️ Total time: 4m 32s (vs ~12m sequential)
270
476
  ```
271
477
 
272
- ### Phase 지정 실행
478
+ ### Phase-specific Execution
273
479
 
274
480
  ```
275
- User: /vibe.run "벽돌게임" --phase 2
481
+ User: /vibe.run "brick-game" --phase 2
276
482
 
277
483
  Claude:
278
- 📄 SPEC 읽는 중: .vibe/specs/brick-game.md
279
- 🎯 Phase 2 실행합니다.
484
+ 📄 Reading SPEC: .vibe/specs/brick-game.md
485
+ 🎯 Executing Phase 2 only.
486
+
487
+ Phase 2: Game Logic
488
+ 1. [ ] Paddle movement implementation
489
+ 2. [ ] Ball physics engine
490
+ 3. [ ] Brick collision handling
491
+ 4. [ ] Score system
492
+ 5. [ ] Game over conditions
280
493
 
281
- Phase 2: 게임 로직
282
- 1. [ ] 패들 이동 구현
283
- 2. [ ] 공 물리엔진
284
- 3. [ ] 벽돌 충돌 처리
285
- 4. [ ] 점수 시스템
286
- 5. [ ] 게임 오버 조건
494
+ Launching parallel exploration...
495
+ [Task(haiku) × 3 launched in parallel]
287
496
 
288
- 🚀 구현 시작...
497
+ 🚀 Starting implementation...
289
498
  ```
290
499
 
291
500
  ## Error Handling
292
501
 
293
- 실패 시:
294
- 1. 에러 메시지 확인
295
- 2. `<constraints>` 재검토
296
- 3. 코드 수정 재시도
297
- 4. 계속 실패 사용자에게 보고
502
+ On failure:
503
+ 1. Check error message
504
+ 2. Review `<constraints>`
505
+ 3. Fix code and retry
506
+ 4. If continues to fail, report to user
298
507
 
299
508
  ## Next Step
300
509
 
301
510
  ```
302
- /vibe.verify "벽돌게임"
511
+ /vibe.verify "brick-game"
303
512
  ```
304
513
 
305
514
  ---