@su-record/vibe 2.5.12 → 2.5.14

package/CLAUDE.md

@@ -2,14 +2,6 @@
 
 SPEC-driven AI Coding Framework (Claude Code Exclusive)
 
-## Response Language
-
-**IMPORTANT: Always respond in English unless the user explicitly requests otherwise.**
-
-## Response Language
-
-**IMPORTANT: Always respond in Korean (한국어) unless the user explicitly requests otherwise.**
-
 ## Code Quality Standards (Mandatory)
 
 Follow these standards when writing code. See `~/.claude/vibe/rules/` (global) for detailed rules.
@@ -40,12 +32,12 @@ Follow these standards when writing code. See `~/.claude/vibe/rules/` (global) f
 - No `@ts-ignore` → fix type issues at root
 - Explicit return types on all functions
 
-### TypeScript Rules
-- No `any` type → use `unknown` + type guards
-- No `as any` casting → define proper interfaces
-- No `@ts-ignore` → fix type issues at root
-- Explicit return types on all functions
-
+### TypeScript Rules
+- No `any` type → use `unknown` + type guards
+- No `as any` casting → define proper interfaces
+- No `@ts-ignore` → fix type issues at root
+- Explicit return types on all functions
+
 ### Error Handling Required
 - try-catch or error state required
 - Loading state handling
@@ -452,240 +444,240 @@ flowchart TD
 | 3. `/vibe.run` | Implementation + Gemini review | Manual start |
 | 4. Agent Review | 13+ agent parallel review | ✅ Auto |
 | 5. Auto-Fix | P1/P2 issue auto-fix | ✅ Auto |
-
----
-name: my-skill
-model: sonnet
-triggers: [keyword1, keyword2]
----
-```
-
-### Trigger-Based Skill Injection
-
-Skills in `~/.claude/vibe/skills/` or `.claude/vibe/skills/` auto-inject on keyword match.
-
-### Multi-Line HUD
-
-```bash
-node hooks/scripts/hud-multiline.js multi    # Tree view
-node hooks/scripts/hud-multiline.js compact  # 2-line view
-node hooks/scripts/hud-multiline.js single   # 1-line view
-```
-
-### Parallel Code Review (/vibe.review)
-
-13+ specialized agents review code simultaneously:
-
-```
-┌─────────────────────────────────────────────────────────────────┐
-│  🚀 PARALLEL REVIEW AGENTS                                       │
-├─────────────────────────────────────────────────────────────────┤
-│  Security          │ security-reviewer, data-integrity-reviewer │
-│  Performance       │ performance-reviewer, complexity-reviewer  │
-│  Architecture      │ architecture-reviewer, simplicity-reviewer │
-│  Language-Specific │ python, typescript, rails, react reviewers │
-│  Context           │ git-history, test-coverage reviewers       │
-└─────────────────────────────────────────────────────────────────┘
-```
-
-**Priority System:**
-- 🔴 P1 (Critical): Blocks merge
-- 🟡 P2 (Important): Fix recommended
-- 🔵 P3 (Nice-to-have): Backlog
-
-### E2E Testing (/vibe.utils --e2e)
-
-Playwright-based automated testing:
-
-```bash
-/vibe.utils --e2e "login flow"   # Scenario test
-/vibe.utils --e2e --visual       # Visual regression test
-/vibe.utils --e2e --record       # Video recording
-```
-
-### Enhanced Research Agents
-
-4 parallel research agents run **after requirements confirmed** during `/vibe.spec`:
-
-```
-Q&A to confirm requirements → Parallel research → SPEC writing
-```
-
-| Agent | Role |
-|-------|------|
-| best-practices-agent | Best practices for confirmed feature+stack |
-| framework-docs-agent | Latest docs for confirmed stack (context7) |
-| codebase-patterns-agent | Analyze existing similar patterns |
-| security-advisory-agent | Security advisory for confirmed feature |
-
-**⚠️ Research runs after requirements confirmed** (VIBE principle: requirements first)
-
-## PTCF Structure
-
-SPEC documents are AI-executable prompt format:
-
-```
-<role>      AI role definition
-<context>   Background, tech stack, related code
-<task>      Phase-by-phase task list
-<constraints> Constraints
-<output_format> Files to create/modify
-<acceptance> Verification criteria
-```
-
-## Built-in Tools
-
-### Semantic Code Analysis
-| Tool | Purpose |
-|------|---------|
-| `vibe_find_symbol` | Find symbol definitions |
-| `vibe_find_references` | Find references |
-| `vibe_analyze_complexity` | Analyze complexity |
-| `vibe_validate_code_quality` | Validate quality |
-
-### Context Management
-| Tool | Purpose |
-|------|---------|
-| `vibe_start_session` | Start session (restore previous context) |
-| `vibe_auto_save_context` | Save current state |
-| `vibe_save_memory` | Save important decisions |
-
-## Agents
-
-### Review Agents (12)
-```
-.claude/agents/review/
-├── security-reviewer.md        # Security vulnerabilities
-├── performance-reviewer.md     # Performance bottlenecks
-├── architecture-reviewer.md    # Architecture violations
-├── complexity-reviewer.md      # Complexity exceeded
-├── simplicity-reviewer.md      # Over-abstraction
-├── data-integrity-reviewer.md  # Data integrity
-├── test-coverage-reviewer.md   # Missing tests
-├── git-history-reviewer.md     # Risk patterns
-├── python-reviewer.md          # Python specialist
-├── typescript-reviewer.md      # TypeScript specialist
-├── rails-reviewer.md           # Rails specialist
-└── react-reviewer.md           # React specialist
-```
-
-### Research Agents (4)
-```
-.claude/agents/research/
-├── best-practices-agent.md     # Best practices
-├── framework-docs-agent.md     # Framework docs
-├── codebase-patterns-agent.md  # Code pattern analysis
-└── security-advisory-agent.md  # Security advisory
-```
-
-## Skills
-
-### Git Worktree
-```bash
-# Isolated environment for PR review
-git worktree add ../review-123 origin/pr/123
-cd ../review-123 && npm test
-git worktree remove ../review-123
-```
-
-### Priority Todos
-```
-.claude/vibe/todos/
-├── P1-security-sql-injection.md   # 🔴 Blocks merge
-├── P2-perf-n1-query.md            # 🟡 Fix recommended
-└── P3-style-extract-helper.md     # 🔵 Backlog
-```
-
-## Context Management Strategy
-
-### Model Selection
-- **Exploration/Search**: Haiku (sub-agent default)
-- **Implementation/Debugging**: Sonnet
-- **Architecture/Complex logic**: Opus
-
-### At 70%+ Context (⚠️ Important)
-```
-❌ Don't use /compact (risk of information loss/distortion)
-✅ save_memory to store important decisions → /new for new session
-```
-
-vibe maintains context across sessions with its own memory system:
-1. `save_memory` - Explicitly save important decisions
-2. `/new` - Start new session
-3. `start_session` - Auto-restore previous session
-
-### Session Restore
-To continue previous work in a new session:
-```
-/vibe.utils --continue
-```
-This command calls `vibe_start_session` to restore previous context from project memory.
-
-### Other Commands
-- `/rewind` - Revert to previous point
-- `/context` - Check current usage
-
-### Using context7
-Use context7 plugin when you need latest library documentation:
-```
-"Search React 19 use() hook with context7"
-```
-
-## Documentation Guidelines
-
-### Diagrams/Structure Representation
-- Avoid ASCII boxes (┌─┐) → Alignment breaks with mixed-width characters
-- Use alternatives:
-  - Mermaid diagrams (GitHub/Notion supported)
-  - Markdown tables
-  - Indentation + separators
-
-### Preferred Formats
-| Purpose | Recommended |
-|---------|-------------|
-| Flowcharts | Mermaid flowchart |
-| Structure/Hierarchy | Indented lists |
-| Comparisons/Lists | Markdown tables |
-| Sequences | Mermaid sequenceDiagram |
-
-## Git Commit Rules
-
-**Must include:**
-- `.claude/vibe/specs/`, `.claude/vibe/features/`, `.claude/vibe/todos/` (project docs)
-- `.claude/vibe/config.json`, `.claude/vibe/constitution.md` (project config)
-- `CLAUDE.md`
-
-**Exclude (globally installed):**
-- `~/.claude/vibe/rules/`, `~/.claude/vibe/languages/`, `~/.claude/vibe/templates/` (global)
-- `~/.claude/commands/`, `~/.claude/agents/`, `~/.claude/skills/` (global)
-- `.claude/settings.local.json` (personal settings)
-
-## Getting Started
-
-```bash
-vibe init
-/vibe.spec "login feature"
-```
-
-## Full Workflow
-
-```mermaid
-flowchart TD
-    A["/vibe.spec"] --> B["(auto) SPEC review"]
-    B --> C["SPEC auto-enhancement"]
-    C --> D["/vibe.run ultrawork"]
-    D --> E["Gemini code review"]
-    E --> F["(auto) 13+ Agent Review"]
-    F --> G{"P1/P2 issues?"}
-    G -->|Yes| H["(auto) Auto-Fix"]
-    H --> I["✅ Done"]
-    G -->|No| I
-```
-
-| Step | Description | Automation |
-|------|-------------|------------|
-| 1. `/vibe.spec` | Collect requirements + Generate SPEC | Manual start |
-| 2. SPEC review | Gemini reviews SPEC + Auto-apply | ✅ Auto |
-| 3. `/vibe.run` | Implementation + Gemini review | Manual start |
-| 4. Agent Review | 13+ agent parallel review | ✅ Auto |
-| 5. Auto-Fix | P1/P2 issue auto-fix | ✅ Auto |
+
+---
+name: my-skill
+model: sonnet
+triggers: [keyword1, keyword2]
+---
+```
+
+### Trigger-Based Skill Injection
+
+Skills in `~/.claude/vibe/skills/` or `.claude/vibe/skills/` auto-inject on keyword match.
+
+### Multi-Line HUD
+
+```bash
+node hooks/scripts/hud-multiline.js multi    # Tree view
+node hooks/scripts/hud-multiline.js compact  # 2-line view
+node hooks/scripts/hud-multiline.js single   # 1-line view
+```
+
+### Parallel Code Review (/vibe.review)
+
+13+ specialized agents review code simultaneously:
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│  🚀 PARALLEL REVIEW AGENTS                                       │
+├─────────────────────────────────────────────────────────────────┤
+│  Security          │ security-reviewer, data-integrity-reviewer │
+│  Performance       │ performance-reviewer, complexity-reviewer  │
+│  Architecture      │ architecture-reviewer, simplicity-reviewer │
+│  Language-Specific │ python, typescript, rails, react reviewers │
+│  Context           │ git-history, test-coverage reviewers       │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+**Priority System:**
+- 🔴 P1 (Critical): Blocks merge
+- 🟡 P2 (Important): Fix recommended
+- 🔵 P3 (Nice-to-have): Backlog
+
+### E2E Testing (/vibe.utils --e2e)
+
+Playwright-based automated testing:
+
+```bash
+/vibe.utils --e2e "login flow"   # Scenario test
+/vibe.utils --e2e --visual       # Visual regression test
+/vibe.utils --e2e --record       # Video recording
+```
+
+### Enhanced Research Agents
+
+4 parallel research agents run **after requirements confirmed** during `/vibe.spec`:
+
+```
+Q&A to confirm requirements → Parallel research → SPEC writing
+```
+
+| Agent | Role |
+|-------|------|
+| best-practices-agent | Best practices for confirmed feature+stack |
+| framework-docs-agent | Latest docs for confirmed stack (context7) |
+| codebase-patterns-agent | Analyze existing similar patterns |
+| security-advisory-agent | Security advisory for confirmed feature |
+
+**⚠️ Research runs after requirements confirmed** (VIBE principle: requirements first)
+
+## PTCF Structure
+
+SPEC documents are AI-executable prompt format:
+
+```
+<role>      AI role definition
+<context>   Background, tech stack, related code
+<task>      Phase-by-phase task list
+<constraints> Constraints
+<output_format> Files to create/modify
+<acceptance> Verification criteria
+```
+
+## Built-in Tools
+
+### Semantic Code Analysis
+| Tool | Purpose |
+|------|---------|
+| `vibe_find_symbol` | Find symbol definitions |
+| `vibe_find_references` | Find references |
+| `vibe_analyze_complexity` | Analyze complexity |
+| `vibe_validate_code_quality` | Validate quality |
+
+### Context Management
+| Tool | Purpose |
+|------|---------|
+| `vibe_start_session` | Start session (restore previous context) |
+| `vibe_auto_save_context` | Save current state |
+| `vibe_save_memory` | Save important decisions |
+
+## Agents
+
+### Review Agents (12)
+```
+.claude/agents/review/
+├── security-reviewer.md        # Security vulnerabilities
+├── performance-reviewer.md     # Performance bottlenecks
+├── architecture-reviewer.md    # Architecture violations
+├── complexity-reviewer.md      # Complexity exceeded
+├── simplicity-reviewer.md      # Over-abstraction
+├── data-integrity-reviewer.md  # Data integrity
+├── test-coverage-reviewer.md   # Missing tests
+├── git-history-reviewer.md     # Risk patterns
+├── python-reviewer.md          # Python specialist
+├── typescript-reviewer.md      # TypeScript specialist
+├── rails-reviewer.md           # Rails specialist
+└── react-reviewer.md           # React specialist
+```
+
+### Research Agents (4)
+```
+.claude/agents/research/
+├── best-practices-agent.md     # Best practices
+├── framework-docs-agent.md     # Framework docs
+├── codebase-patterns-agent.md  # Code pattern analysis
+└── security-advisory-agent.md  # Security advisory
+```
+
+## Skills
+
+### Git Worktree
+```bash
+# Isolated environment for PR review
+git worktree add ../review-123 origin/pr/123
+cd ../review-123 && npm test
+git worktree remove ../review-123
+```
+
+### Priority Todos
+```
+.claude/vibe/todos/
+├── P1-security-sql-injection.md   # 🔴 Blocks merge
+├── P2-perf-n1-query.md            # 🟡 Fix recommended
+└── P3-style-extract-helper.md     # 🔵 Backlog
+```
+
+## Context Management Strategy
+
+### Model Selection
+- **Exploration/Search**: Haiku (sub-agent default)
+- **Implementation/Debugging**: Sonnet
+- **Architecture/Complex logic**: Opus
+
+### At 70%+ Context (⚠️ Important)
+```
+❌ Don't use /compact (risk of information loss/distortion)
+✅ save_memory to store important decisions → /new for new session
+```
+
+vibe maintains context across sessions with its own memory system:
+1. `save_memory` - Explicitly save important decisions
+2. `/new` - Start new session
+3. `start_session` - Auto-restore previous session
+
+### Session Restore
+To continue previous work in a new session:
+```
+/vibe.utils --continue
+```
+This command calls `vibe_start_session` to restore previous context from project memory.
+
+### Other Commands
+- `/rewind` - Revert to previous point
+- `/context` - Check current usage
+
+### Using context7
+Use context7 plugin when you need latest library documentation:
+```
+"Search React 19 use() hook with context7"
+```
+
+## Documentation Guidelines
+
+### Diagrams/Structure Representation
+- Avoid ASCII boxes (┌─┐) → Alignment breaks with mixed-width characters
+- Use alternatives:
+  - Mermaid diagrams (GitHub/Notion supported)
+  - Markdown tables
+  - Indentation + separators
+
+### Preferred Formats
+| Purpose | Recommended |
+|---------|-------------|
+| Flowcharts | Mermaid flowchart |
+| Structure/Hierarchy | Indented lists |
+| Comparisons/Lists | Markdown tables |
+| Sequences | Mermaid sequenceDiagram |
+
+## Git Commit Rules
+
+**Must include:**
+- `.claude/vibe/specs/`, `.claude/vibe/features/`, `.claude/vibe/todos/` (project docs)
+- `.claude/vibe/config.json`, `.claude/vibe/constitution.md` (project config)
+- `CLAUDE.md`
+
+**Exclude (globally installed):**
+- `~/.claude/vibe/rules/`, `~/.claude/vibe/languages/`, `~/.claude/vibe/templates/` (global)
+- `~/.claude/commands/`, `~/.claude/agents/`, `~/.claude/skills/` (global)
+- `.claude/settings.local.json` (personal settings)
+
+## Getting Started
+
+```bash
+vibe init
+/vibe.spec "login feature"
+```
+
+## Full Workflow
+
+```mermaid
+flowchart TD
+    A["/vibe.spec"] --> B["(auto) SPEC review"]
+    B --> C["SPEC auto-enhancement"]
+    C --> D["/vibe.run ultrawork"]
+    D --> E["Gemini code review"]
+    E --> F["(auto) 13+ Agent Review"]
+    F --> G{"P1/P2 issues?"}
+    G -->|Yes| H["(auto) Auto-Fix"]
+    H --> I["✅ Done"]
+    G -->|No| I
+```
+
+| Step | Description | Automation |
+|------|-------------|------------|
+| 1. `/vibe.spec` | Collect requirements + Generate SPEC | Manual start |
+| 2. SPEC review | Gemini reviews SPEC + Auto-apply | ✅ Auto |
+| 3. `/vibe.run` | Implementation + Gemini review | Manual start |
+| 4. Agent Review | 13+ agent parallel review | ✅ Auto |
+| 5. Auto-Fix | P1/P2 issue auto-fix | ✅ Auto |

package/commands/vibe.analyze.md

@@ -281,9 +281,9 @@ Score = Σ(checked items × weight) / 100
 
 Grades:
 - 95-100: ✅ EXCELLENT - Comprehensive analysis
-- 85-94:  ✅ GOOD - Ready for development
-- 70-84:  ⚠️ FAIR - Needs more exploration
-- 0-69:   ❌ POOR - Incomplete, re-analyze
+- 90-94:  ⚠️ GOOD - Additional exploration recommended
+- 80-89:  ⚠️ FAIR - Needs more exploration
+- 0-79:   ❌ POOR - Incomplete, re-analyze
 ```
 
 ### Analysis Depth Levels

package/commands/vibe.review.md

@@ -265,9 +265,9 @@ Score = 100 - (P1 × 20) - (P2 × 5) - (P3 × 1)
 
 Grades:
 - 95-100: ✅ EXCELLENT - Merge ready
-- 85-94:  ✅ GOOD - Minor fixes recommended
-- 70-84:  ⚠️ FAIR - Must fix P2 issues
-- 0-69:   ❌ POOR - Block merge, fix P1/P2
+- 90-94:  ⚠️ GOOD - Minor fixes required before merge
+- 80-89:  ⚠️ FAIR - Must fix P2 issues
+- 0-79:   ❌ POOR - Block merge, fix P1/P2
 ```
 
 ### Merge Decision Matrix

package/commands/vibe.run.md

@@ -643,7 +643,73 @@ Phase N+1 Start (IMMEDIATE - exploration already done!)
 3. **Constraint compliance**: Check `<constraints>`
 4. **Run verification**: Execute verification commands
 
-### 4. Gemini Code Review + Auto-Fix (NEW)
+### 4. Brand Assets Generation (Optional)
+
+When starting a **new project** with brand context in SPEC, auto-generate app icons and favicons:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+🎨 BRAND ASSETS GENERATION
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+[Check] Brand assets exist? → Skip if favicon.ico exists
+[Check] Gemini API configured? → Required for image generation
+[Check] SPEC has brand context? → Extract app name, colors, style
+
+[Generate] Creating app icon with Gemini Image API...
+  - Prompt: "App icon for [AppName], [style], [color]..."
+  - Generated: 512x512 master icon
+
+[Resize] Creating platform variants...
+  ✅ favicon.ico (16/32/48)
+  ✅ favicon-16x16.png
+  ✅ favicon-32x32.png
+  ✅ apple-touch-icon.png (180x180)
+  ✅ android-chrome-192x192.png
+  ✅ android-chrome-512x512.png
+  ✅ site.webmanifest
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+✅ Brand assets generated in public/
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+**SPEC Brand Context Example:**
+
+```xml
+<context>
+Brand:
+  - App Name: MyApp
+  - Primary Color: #2F6BFF
+  - Style: Modern, minimalist, flat design
+  - Icon Concept: Abstract geometric shape
+</context>
+```
+
+**Trigger Conditions:**
+- First `/vibe.run` execution (no existing icons)
+- SPEC contains brand/design context
+- Gemini API key configured (`vibe gemini auth`)
+
+**Manual Generation:**
+```bash
+node hooks/scripts/generate-brand-assets.js \
+  --spec ".claude/vibe/specs/my-feature.md" \
+  --output "./public"
+
+# Or with explicit values
+node hooks/scripts/generate-brand-assets.js \
+  --name "MyApp" \
+  --color "#2F6BFF" \
+  --style "modern minimal" \
+  --output "./public"
+```
+
+**Fallback:** If Gemini Image fails, generates text monogram icon (first letter + primary color).
+
+---
+
+### 5. Gemini Code Review + Auto-Fix
 
 After all scenarios are implemented, **Gemini reviews the code and auto-fixes based on feedback**:
 
@@ -722,7 +788,7 @@ node "$VIBE_SCRIPTS/llm-orchestrate.js" gemini orchestrate-json "Review this cod
 - Skip and proceed on fallback response
 - Must re-verify build/tests after fixes
 
-### 5. Quality Report (Auto-generated)
+### 6. Quality Report (Auto-generated)
 
 After all scenarios complete + Gemini review, **quality report is auto-generated**:
 
@@ -767,7 +833,7 @@ After all scenarios complete + Gemini review, **quality report is auto-generated
 
 **This alone is enough to trust quality.**
 
-### 6. Update Feature File
+### 7. Update Feature File
 
 Auto-update scenario status:
 
@@ -1004,18 +1070,18 @@ Score = Σ(checked items × weight) / 100
 
 Grades:
 - 95-100: ✅ EXCELLENT - Ready to merge
-- 85-94:  ✅ GOOD - Minor improvements recommended
-- 70-84:  ⚠️ FAIR - Improvements required before merge
-- 0-69:   ❌ POOR - Major fixes needed
+- 90-94:  ⚠️ GOOD - Minor improvements required before merge
+- 80-89:  ⚠️ FAIR - Significant improvements required
+- 0-79:   ❌ POOR - Major fixes needed
 ```
 
 ### Quality Gate Thresholds
 
 | Gate | Minimum Score | Condition |
 |------|---------------|-----------|
-| **Scenario Complete** | 85 | Each scenario must score ≥85 |
-| **Phase Complete** | 90 | Average of all scenarios ≥90 |
-| **Feature Complete** | 90 | All phases complete + Gemini review |
+| **Scenario Complete** | 95 | Each scenario must score ≥95 |
+| **Phase Complete** | 95 | Average of all scenarios ≥95 |
+| **Feature Complete** | 95 | All phases complete + Gemini review |
 
 ### Auto-Fix Triggers