ai-workflow-init 6.1.0 → 6.2.3

package/.claude/CLAUDE.md

@@ -55,12 +55,34 @@
 
 ---
 
-## Skill Reporting
+## Skill Reporting (MANDATORY)
 
-At response start, list skills being used:
+**CRITICAL REQUIREMENT - ALWAYS follow this:**
+
+At the START of EVERY response, BEFORE any other content, report skills:
 
 ```
 📚 Skills: skill-name-1, skill-name-2
 ```
 
-Skills are defined in `.claude/skills/`. Use `/skill:name` to request specific skills.
+**Rules:**
+- If skills were activated → List them
+- If NO skills activated → Write: `📚 Skills: none`
+- This line MUST appear in EVERY response, no exceptions
+- Place BEFORE greeting, explanation, or any other content
+
+**Example responses:**
+
+```
+📚 Skills: frontend-design-fundamentals, frontend-design-theme-factory
+
+I'll help you create a modern login page...
+```
+
+```
+📚 Skills: none
+
+Sure, I can help you fix that bug...
+```
+
+Skills are defined in `.claude/skills/`.

package/.claude/agents/review-plan.md

@@ -0,0 +1,168 @@
+---
+name: review-plan
+description: Senior Technical Architect reviews planning docs for clarity, completeness, logic, and AI-executability before implementation.
+tools: Read, Glob, Grep
+model: inherit
+---
+
+You are a **Senior Technical Architect and QA Lead** reviewing feature plans before implementation.
+
+Your role is NOT to check formatting - it's to ensure the plan is **clear, complete, logical, and executable** by an AI agent.
+
+## Context
+
+- Plans are created by `/create-plan` and executed by `/execute-plan`
+- The executing AI agent will read the plan and implement code based on it
+- Poor plans lead to wrong implementations, wasted effort, and bugs
+
+## When Invoked
+
+1. Read the provided planning doc carefully
+2. Read project context:
+   - `docs/ai/project/CODE_CONVENTIONS.md` - coding standards
+   - `docs/ai/project/PROJECT_STRUCTURE.md` - architecture patterns
+3. Evaluate against 5 critical criteria
+4. Output actionable review with clear verdict
+
+## 5 Critical Evaluation Criteria
+
+### 1. Clarity - Is the plan clear enough to implement?
+
+**Ask yourself:**
+- Can I understand exactly what needs to be built?
+- Are there ambiguous terms or vague descriptions?
+- Would two different developers interpret this the same way?
+- Are edge cases explicitly defined or left to assumption?
+
+**Red flags:**
+- "Handle errors appropriately" (what does appropriately mean?)
+- "Similar to existing feature" (which feature? how similar?)
+- "Should support various formats" (which formats exactly?)
+- Missing details on user flows, states, or interactions
+
+### 2. Completeness - Does the plan cover the full requirement?
+
+**Ask yourself:**
+- Are all user scenarios covered?
+- Are error states and edge cases addressed?
+- Is the happy path AND unhappy paths defined?
+- Are there missing pieces that will block implementation?
+
+**Red flags:**
+- Only happy path described
+- No mention of error handling
+- Missing validation rules
+- Unclear what happens in edge cases
+- Dependencies not identified
+
+### 3. Project Context Alignment - Does it follow project patterns?
+
+**Compare against:**
+- `CODE_CONVENTIONS.md` - naming, structure, patterns
+- `PROJECT_STRUCTURE.md` - where files should go, architecture
+
+**Ask yourself:**
+- Does the plan use existing patterns/components?
+- Are file paths consistent with project structure?
+- Does it follow established conventions?
+- Is it reinventing something that already exists?
+
+**Red flags:**
+- Creating new patterns when existing ones apply
+- File paths that don't match project structure
+- Ignoring existing utilities/components
+- Inconsistent naming with codebase
+
+### 4. Logic Soundness - Is the technical approach correct?
+
+**Ask yourself:**
+- Does the data flow make sense?
+- Are there circular dependencies?
+- Is the sequence of operations correct?
+- Are there race conditions or timing issues?
+- Does the architecture scale appropriately?
+
+**Red flags:**
+- Steps that depend on something not yet created
+- Missing state management considerations
+- API calls without error handling strategy
+- Database operations without transaction considerations
+- Security gaps (auth, validation, sanitization)
+
+### 5. AI Executability - Can an AI agent implement this correctly?
+
+**Ask yourself:**
+- Are instructions specific enough for AI to follow?
+- Is there room for misinterpretation?
+- Are pseudo-code blocks clear on logic flow?
+- Would AI know EXACTLY what code to write?
+
+**Red flags:**
+- "Implement similar to X" without specifying what aspects
+- Pseudo-code that's too abstract or hand-wavy
+- Missing input/output specifications
+- Unclear success criteria for each task
+- Tasks that require human judgment calls
+
+## Output Format
+
+```markdown
+## Plan Review: {feature-name}
+
+### Verdict
+**Status**: ✅ Ready to Execute | ⚠️ Needs Clarification | ❌ Not Ready
+
+**Confidence**: High / Medium / Low
+(How confident that AI agent will implement correctly)
+
+---
+
+### 1. Clarity Assessment
+**Score**: ✅ Clear | ⚠️ Some Ambiguity | ❌ Too Vague
+
+[Specific findings - what's clear, what's not]
+
+### 2. Completeness Assessment
+**Score**: ✅ Complete | ⚠️ Gaps Found | ❌ Major Missing Pieces
+
+[What's covered, what's missing]
+
+### 3. Project Context Alignment
+**Score**: ✅ Aligned | ⚠️ Minor Deviations | ❌ Misaligned
+
+[How well it follows conventions and structure]
+
+### 4. Logic Soundness
+**Score**: ✅ Sound | ⚠️ Minor Issues | ❌ Flawed Logic
+
+[Technical concerns, if any]
+
+### 5. AI Executability
+**Score**: ✅ Executable | ⚠️ Risky Areas | ❌ Likely Misimplementation
+
+[Areas where AI might go wrong]
+
+---
+
+### Critical Issues (Must Fix)
+1. [Issue] → [Suggested fix]
+
+### Warnings (Should Fix)
+1. [Issue] → [Suggested fix]
+
+### Suggestions (Nice to Have)
+1. [Improvement idea]
+
+---
+
+### Recommendation
+[Clear next action: proceed / revise specific sections / major rework needed]
+```
+
+## Review Mindset
+
+- Think like you're preventing bugs BEFORE they're written
+- Assume the AI agent is literal - it will do exactly what's written
+- Ambiguity = AI will guess = likely wrong implementation
+- Your review saves hours of debugging and rework
+- Be specific and actionable - vague feedback is useless

package/.claude/commands/create-plan.md

@@ -145,7 +145,7 @@ Generate a single planning doc at `docs/ai/planning/feature-{name}.md` using the
 
 **Trigger:** User mentions "figma", "design file", "mockup", or provides Figma URL (detected in Step 1).
 
-**Use `figma-design-extraction` skill to:**
+**Use `frontend-design-figma-extraction` skill to:**
 - Validate Figma MCP connection
 - Extract design tokens (colors, typography, spacing, shadows, border radius)
 - Extract component specs (states, variants, dimensions, hierarchies)
@@ -170,9 +170,9 @@ Generate a single planning doc at `docs/ai/planning/feature-{name}.md` using the
 **Trigger:** Step 4 skipped (no Figma) AND user has NOT provided detailed design description/screenshot.
 
 **Use design skills to guide design decisions:**
-- `design-fundamentals`: Core principles (spacing, typography, color, hierarchy)
-- `theme-factory`: Interactive theme selection based on brand personality
-- `design-responsive`: Mobile-first responsive patterns and breakpoints
+- `frontend-design-fundamentals`: Core principles (spacing, typography, color, hierarchy)
+- `frontend-design-theme-factory`: Interactive theme selection based on brand personality
+- `frontend-design-responsive`: Mobile-first responsive patterns and breakpoints
 
 **Expected workflow:**
 1. Ask about brand personality/preferences if needed

package/.claude/commands/sync-workflow.md

@@ -672,7 +672,7 @@ After writing, verify:
 #### OpenCode Skills (.opencode/skill/)
 - [x] figma-extraction/SKILL.md - CREATED
 - [x] quality-code-check/SKILL.md - CREATED
-- [x] design-fundamentals/SKILL.md - CREATED
+- [x] frontend-design-fundamentals/SKILL.md - CREATED
 - [x] ux-accessibility/SKILL.md - CREATED
 
 #### OpenCode Agents (.opencode/agent/)

package/.claude/settings.local.json

@@ -11,5 +11,80 @@
     ],
     "deny": [],
     "ask": []
+  },
+  "hooks": {
+    "SessionStart": [
+      {
+        "matcher": "startup|resume|clear",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "echo '⚠️ REMINDER: Start EVERY response with: 📚 Skills: [list] or 📚 Skills: none'"
+          }
+        ]
+      }
+    ],
+    "PostToolUse": [
+      {
+        "matcher": "Write",
+        "hooks": [
+          {
+            "type": "prompt",
+            "prompt": "If the file path contains 'docs/ai/planning/feature-' and ends with '.md', validate this planning document has all required sections: 1. Goal & Acceptance Criteria, 2. Risks & Assumptions, 3. Definition of Done, 4. Implementation Plan (with Summary and Phases), 5. Follow-ups. Return JSON: {\"valid\": true/false, \"missing\": [list of missing sections], \"message\": \"brief validation result\"}. If file path doesn't match, return {\"valid\": true, \"message\": \"skipped - not a planning doc\"}"
+          }
+        ]
+      },
+      {
+        "matcher": "Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "if echo \"$TOOL_INPUT\" | grep -q 'docs/ai/planning/feature-'; then echo \"[$(date '+%Y-%m-%d %H:%M:%S')] Task updated in planning doc\" >> .claude/feature-progress.log; fi"
+          }
+        ]
+      }
+    ],
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "prompt",
+            "prompt": "GIT SAFETY CHECK: If command contains 'git ' (git commands like git add, git commit, git push, git pull, git checkout, git branch, git merge, git rebase, git reset, git stash, etc.): Check the ORIGINAL USER PROMPT - did the user EXPLICITLY request git operations? Keywords indicating user wants git: 'commit', 'push', 'git', 'version control', 'save changes', 'create branch'. If user did NOT explicitly request git operations, BLOCK with message 'Git operations require explicit user request. Ask user first.' Return JSON: {\"allow\": true/false, \"reason\": \"explanation\"}. If command does not contain git, return {\"allow\": true, \"reason\": \"not a git command\"}"
+          }
+        ]
+      },
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "prompt",
+            "prompt": "SECURITY CHECK: If file path matches any sensitive pattern: '.env', '.env.*', 'credentials', 'secrets', 'api_key', 'apikey', 'password', 'private_key', 'token', '.pem', '.key', 'auth.json', 'config/prod': WARN user with message '⚠️ SENSITIVE FILE: [filename] - Are you sure you want to modify this file?'. Return JSON: {\"isSensitive\": true/false, \"warning\": \"message if sensitive\", \"allow\": true}. Always allow but warn for sensitive files."
+          }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "if command -v notify-send &>/dev/null; then notify-send -i dialog-information 'Claude Code' '✅ Task completed' 2>/dev/null; elif command -v powershell.exe &>/dev/null; then powershell.exe -Command \"[System.Reflection.Assembly]::LoadWithPartialName('System.Windows.Forms'); [System.Windows.Forms.MessageBox]::Show('Task completed', 'Claude Code', 'OK', 'Information')\" 2>/dev/null; elif command -v osascript &>/dev/null; then osascript -e 'display notification \"Task completed\" with title \"Claude Code\"' 2>/dev/null; fi; exit 0"
+          }
+        ]
+      }
+    ],
+    "Notification": [
+      {
+        "matcher": "permission_prompt",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "if command -v notify-send &>/dev/null; then notify-send -u critical -i dialog-warning 'Claude Code' '⚠️ Permission required - check terminal' 2>/dev/null; elif command -v powershell.exe &>/dev/null; then powershell.exe -Command \"[System.Reflection.Assembly]::LoadWithPartialName('System.Windows.Forms'); [System.Windows.Forms.MessageBox]::Show('Permission required - check terminal', 'Claude Code', 'OK', 'Warning')\" 2>/dev/null; fi; exit 0"
+          }
+        ]
+      }
+    ]
   }
 }

package/.claude/skills/README.md

@@ -12,19 +12,15 @@ Version: 2.0.0
 .claude/skills/
 ├── README.md (this file)
 │
-├── design/           # Visual design principles
-│   ├── fundamentals/
-│   ├── responsive/
-│   ├── animations/
-│   ├── figma-extraction/
-│   └── theme-factory/
+├── frontend-design-fundamentals/   # Core design principles
+├── frontend-design-responsive/     # Mobile-first, breakpoints
+├── frontend-design-figma-extraction/  # Extract Figma specs
+├── frontend-design-theme-factory/  # Generate themes
 │
-├── ux/               # User experience patterns
-│   ├── feedback-patterns/
-│   └── accessibility/
+├── ux-feedback-patterns/           # Loading, success, error states
+├── ux-accessibility/               # Keyboard, screen readers, WCAG
 │
-└── architecture/     # Code quality & patterns
-    └── quality-code-check/
+└── quality-code-check/             # Linting, type checking, builds
 ```
 
 ---
@@ -170,31 +166,32 @@ skill-name/
 
 ## 🎨 Current Skills
 
-| Skill | Category | Lines | Purpose |
-|-------|----------|-------|---------|
-| design-fundamentals | design | 277 | Spacing, typography, color, hierarchy |
-| design-responsive | design | 402 | Mobile-first, breakpoints, fluid layouts |
-| figma-design-extraction | design | 385 | Extract complete Figma specs |
-| theme-factory | design | 420 | Generate themes when no design |
-| ux-feedback-patterns | ux | 333 | Loading, success, error states |
-| ux-accessibility | ux | 411 | Keyboard, screen readers, WCAG |
-| quality-code-check | architecture | 268 | Linting, type checking, builds |
+| Skill | Purpose |
+|-------|---------|
+| frontend-design-fundamentals | Spacing, typography, color, visual hierarchy |
+| frontend-design-responsive | Mobile-first, breakpoints, fluid layouts |
+| frontend-design-figma-extraction | Extract complete Figma design specs |
+| frontend-design-theme-factory | Generate themes when no design provided |
+| ux-feedback-patterns | Loading, success, error states |
+| ux-accessibility | Keyboard, screen readers, WCAG |
+| quality-code-check | Linting, type checking, builds |
 
-**Total:** 2,496 lines across 7 skills
+**Total:** 7 skills
 
 ---
 
-## 🎮 Manual Skill Commands
+## 🎮 Manual Skill Invocation
+
+Skills auto-trigger based on keywords in your prompt. Manual invocation:
 
 ```bash
-/skill:design              # Load design-fundamentals
-/skill:responsive          # Load design-responsive
-/skill:figma               # Load figma-design-extraction
-/skill:theme               # Load theme-factory
-/skill:feedback            # Load ux-feedback-patterns
-/skill:accessibility       # Load ux-accessibility
-/skill:a11y                # Alias for accessibility
-/skill:quality             # Load quality-code-check
+/frontend-design-fundamentals    # Core design principles
+/frontend-design-responsive      # Mobile-first responsive
+/frontend-design-figma-extraction   # Extract from Figma
+/frontend-design-theme-factory   # Generate theme
+/ux-feedback-patterns            # Loading/error states
+/ux-accessibility                # WCAG, keyboard nav
+/quality-code-check              # Linting, type checks
 ```
 
 ---

package/.claude/skills/{design/figma-extraction → frontend-design-figma-extraction}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: figma-design-extraction
+name: frontend-design-figma-extraction
 description: |
   Complete Figma design extraction for pixel-perfect implementation.
   Extracts design tokens, component specs, layouts, and responsive behavior systematically.
@@ -19,6 +19,8 @@ description: |
   - Responsive: mobile/tablet/desktop differences explicitly documented
   - Assets: icons (names, sizes), images (dimensions, alt text), illustrations
 
+  Keywords: Figma, design file, mockup, extract, MCP, design system, specs
+
   Goal: Extract ONCE completely during planning phase. Implementation should never
   need to re-fetch from Figma MCP. Focus on exact values only - no approximations,
   no guessing. Completeness prevents re-work and design inconsistencies.

package/.claude/skills/{design/fundamentals → frontend-design-fundamentals}/SKILL.md

@@ -1,23 +1,39 @@
 ---
-name: design-fundamentals
+name: frontend-design-fundamentals
 description: |
-  Core design principles for creating distinctive, beautiful UIs with technical excellence.
-  Combines creative direction with practical foundation for memorable, accessible interfaces.
-
-  Use when building UI without specific design specs (Figma, screenshots, design files):
-  - Creating landing pages, home pages, marketing pages from scratch
-  - Building web apps, dashboards, admin panels without design
-  - Choosing design system: typography, colors, spacing, visual hierarchy
-  - Need to propose complete design (fonts, colors, layout, spacing)
-  - Building distinctive UIs that avoid generic AI aesthetics
-
-  Keywords: landing page, design system, typography, colors, spacing, visual hierarchy
-
-  Two-part approach:
-  1. Creative Direction: Choose aesthetic tone (minimal, bold, elegant, playful)
-  2. Technical Foundation: Spacing scales, typography specs, WCAG contrast, hierarchy
-
-  Goal: Create UIs that are BOTH beautiful (distinctive, memorable) AND correct (accessible, consistent, professional).
+  Core design principles for implementing beautiful, professional UIs.
+  Ensures consistent quality through spacing, typography, colors, and visual hierarchy.
+
+  ALWAYS load when implementing UI/frontend code:
+  - Creating or modifying components, pages, screens
+  - Building landing pages, dashboards, forms, cards, buttons
+  - Any frontend work: HTML, CSS, styling, layouts
+  - Adding new UI elements or updating existing ones
+  - Modern, stunning, elegant, sleek interfaces
+  - Animation, transition, hover effects, motion, interactive elements
+
+  Keywords: UI, frontend, component, page, styling, CSS, layout, button, form,
+            card, dashboard, animation, transition, hover, effect, motion,
+            modern, beautiful, stunning, elegant, sleek, professional,
+            interactive, visual, aesthetic, design, attractive, impressive
+
+  Purpose: Ensure ALL UI implementation follows design best practices for:
+  - Consistent spacing scale (not arbitrary values)
+  - Typography hierarchy (readable, professional)
+  - Color contrast (accessible, WCAG compliant)
+  - Visual hierarchy (clear, intentional)
+  - Avoiding generic AI aesthetics
+
+  Do NOT load for:
+  - Backend-only code (APIs, database, server logic)
+  - Pure logic/algorithm work without UI
+  - DevOps, infrastructure, CLI tools
+
+  Works with other skills:
+  - theme-factory: When user needs help CHOOSING colors/theme
+  - figma-design-extraction: When Figma file provided
+  - design-responsive: For mobile/tablet/responsive specifics
+  - ux-accessibility: For keyboard/screen reader specifics
 ---
 
 # Design Fundamentals

package/.claude/skills/{design/responsive → frontend-design-responsive}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: design-responsive
+name: frontend-design-responsive
 description: |
   Mobile-first responsive design for beautiful, multi-device UIs. Breakpoints, fluid layouts,
   touch optimization, and creative responsive patterns for distinctive experiences across screens.
@@ -13,6 +13,13 @@ description: |
 
   Keywords: responsive, mobile-first, mobile, tablet, desktop, breakpoints, touch, multi-device
 
+  Do NOT load for:
+  - Desktop-only applications without responsive needs
+  - Figma extraction (use figma-design-extraction)
+  - Accessibility-only questions (use ux-accessibility)
+  - Theme/color selection (use theme-factory)
+  - Code quality checks (use quality-code-check)
+
   Mobile-first approach: Design for mobile constraints first, enhance progressively.
   Integrates with design-fundamentals: Apply spacing, typography, color systems responsively.
 ---

package/.claude/skills/{design/theme-factory → frontend-design-theme-factory}/SKILL.md

@@ -1,21 +1,27 @@
 ---
-name: theme-factory
+name: frontend-design-theme-factory
 description: |
   Interactive UI theme generation when user needs help choosing colors/fonts.
   Generates cohesive themes based on brand personality using color harmony theory.
 
-  Use when user asks for theme/color help OR building UI without design:
+  Use ONLY when user is UNCERTAIN about colors/theme and asks for help:
   - "What theme should I use?" "Help me pick colors" "Generate theme"
   - "What colors work well together?" "Suggest color palette"
   - User uncertain about design direction, needs aesthetic suggestions
-  - Building UI/landing page with no design specs, needs complete theme
+  - Building UI with no design specs AND no color preference
 
-  Keywords: theme, color palette, colors, fonts, brand personality, color harmony
+  Keywords: theme, color palette, colors, fonts, brand personality, color harmony,
+            aesthetic, style, visual style, look and feel, beautiful, attractive
 
   Interactive workflow: Ask personality → Present options → Generate custom theme.
   References pre-defined themes in .claude/themes/.
 
-  Do NOT load for: User has clear aesthetic/colors, Figma/design file provided.
+  Do NOT load for:
+  - User already has clear colors/aesthetic in mind (use design-fundamentals)
+  - Figma/design file provided (use figma-design-extraction)
+  - User just needs to apply existing theme
+  - Responsive layout questions (use design-responsive)
+
   Integrates with design-fundamentals: Generates themes following design principles.
 ---
 

package/.claude/skills/{architecture/quality-code-check → quality-code-check}/SKILL.md

@@ -18,6 +18,14 @@ description: |
   - Java (Gradle, Maven)
 
   Focuses on detecting issues early through systematic automated checks.
+
+  Keywords: lint, linting, type check, typecheck, build, quality, validation, eslint, tsc
+
+  Do NOT load for:
+  - Visual design work (use frontend-design-fundamentals, frontend-design-responsive)
+  - UX patterns (use ux-feedback-patterns, ux-accessibility)
+  - Initial development before implementation is stable
+  - Figma extraction (use frontend-design-figma-extraction)
 ---
 
 # Quality Code Check

package/.claude/skills/{ux/accessibility → ux-accessibility}/SKILL.md

@@ -14,6 +14,13 @@ description: |
 
   Keywords: accessible, accessibility, WCAG, keyboard, screen reader, ARIA, contrast, a11y
 
+  Do NOT load for:
+  - Visual design/styling only (use frontend-design-fundamentals)
+  - Theme/color selection (use frontend-design-theme-factory)
+  - Responsive layout (use frontend-design-responsive)
+  - Figma extraction (use frontend-design-figma-extraction)
+  - Code quality checks (use quality-code-check)
+
   Focus on making UI usable via keyboard, screen readers, assistive technologies.
 ---
 

package/.claude/skills/{ux/feedback-patterns → ux-feedback-patterns}/SKILL.md

@@ -13,6 +13,13 @@ description: |
 
   Keywords: loading, success, error, form, validation, async, feedback, toast, empty state
 
+  Do NOT load for:
+  - Visual design/styling (use frontend-design-fundamentals)
+  - Responsive layout (use frontend-design-responsive)
+  - Figma extraction (use frontend-design-figma-extraction)
+  - Accessibility-only questions (use ux-accessibility)
+  - Code quality checks (use quality-code-check)
+
   Focus on WHEN to show feedback, WHAT type (toast/inline/modal), HOW LONG (timing).
 ---
 

package/cli.js

@@ -397,12 +397,100 @@ function installClaudeCode() {
     }
   }
 
-  // Download hooks.json (always overwrite to get latest)
-  step("🚚 Downloading Claude Code hooks (.claude/hooks.json)...");
-  try {
-    run(`curl -fsSL ${RAW_BASE}/.claude/hooks.json -o .claude/hooks.json`);
-  } catch (_) {
-    run(`wget -qO .claude/hooks.json ${RAW_BASE}/.claude/hooks.json`);
+  // Create settings.json with hooks (project-level, shareable with team)
+  step("🚚 Setting up Claude Code hooks (.claude/settings.json)...");
+  const claudeSettingsPath = ".claude/settings.json";
+  if (existsSync(claudeSettingsPath)) {
+    skip(`Skipping (already exists): ${claudeSettingsPath}`);
+  } else {
+    const claudeSettings = {
+      hooks: {
+        SessionStart: [
+          {
+            matcher: "startup|resume|clear",
+            hooks: [
+              {
+                type: "command",
+                command: "echo '⚠️ REMINDER: Start EVERY response with: 📚 Skills: [list] or 📚 Skills: none'"
+              }
+            ]
+          }
+        ],
+        PostToolUse: [
+          {
+            matcher: "Write",
+            hooks: [
+              {
+                type: "prompt",
+                prompt: "If the file path contains 'docs/ai/planning/feature-' and ends with '.md', validate this planning document has all required sections: 1. Goal & Acceptance Criteria, 2. Risks & Assumptions, 3. Definition of Done, 4. Implementation Plan (with Summary and Phases), 5. Follow-ups. Return JSON: {\"valid\": true/false, \"missing\": [list of missing sections], \"message\": \"brief validation result\"}. If file path doesn't match, return {\"valid\": true, \"message\": \"skipped - not a planning doc\"}"
+              }
+            ]
+          },
+          {
+            matcher: "Edit",
+            hooks: [
+              {
+                type: "command",
+                command: "if echo \"$TOOL_INPUT\" | grep -q 'docs/ai/planning/feature-'; then echo \"[$(date '+%Y-%m-%d %H:%M:%S')] Task updated in planning doc\" >> .claude/feature-progress.log; fi"
+              }
+            ]
+          }
+        ],
+        PreToolUse: [
+          {
+            matcher: "Edit",
+            hooks: [
+              {
+                type: "prompt",
+                prompt: "If the file path contains 'docs/ai/planning/feature-' and ends with '.md': Check if the agent is starting a new phase. If yes, verify all tasks in the previous phase are marked [x]. Return JSON: {\"canProceed\": true/false, \"message\": \"reason\"}. If file path doesn't match, return {\"canProceed\": true, \"message\": \"skipped - not a planning doc\"}"
+              }
+            ]
+          },
+          {
+            matcher: "Bash",
+            hooks: [
+              {
+                type: "prompt",
+                prompt: "GIT SAFETY CHECK: If command contains 'git ' (git commands like git add, git commit, git push, git pull, git checkout, git branch, git merge, git rebase, git reset, git stash, etc.): Check the ORIGINAL USER PROMPT - did the user EXPLICITLY request git operations? Keywords indicating user wants git: 'commit', 'push', 'git', 'version control', 'save changes', 'create branch'. If user did NOT explicitly request git operations, BLOCK with message 'Git operations require explicit user request. Ask user first.' Return JSON: {\"allow\": true/false, \"reason\": \"explanation\"}. If command does not contain git, return {\"allow\": true, \"reason\": \"not a git command\"}"
+              }
+            ]
+          },
+          {
+            matcher: "Write|Edit",
+            hooks: [
+              {
+                type: "prompt",
+                prompt: "SECURITY CHECK: If file path matches any sensitive pattern: '.env', '.env.*', 'credentials', 'secrets', 'api_key', 'apikey', 'password', 'private_key', 'token', '.pem', '.key', 'auth.json', 'config/prod': WARN user with message '⚠️ SENSITIVE FILE: [filename] - Are you sure you want to modify this file?'. Return JSON: {\"isSensitive\": true/false, \"warning\": \"message if sensitive\", \"allow\": true}. Always allow but warn for sensitive files."
+              }
+            ]
+          }
+        ],
+        Stop: [
+          {
+            matcher: "",
+            hooks: [
+              {
+                type: "command",
+                command: "if command -v notify-send &>/dev/null; then notify-send -i dialog-information 'Claude Code' '✅ Task completed' 2>/dev/null; elif command -v powershell.exe &>/dev/null; then powershell.exe -Command \"[System.Reflection.Assembly]::LoadWithPartialName('System.Windows.Forms'); [System.Windows.Forms.MessageBox]::Show('Task completed', 'Claude Code', 'OK', 'Information')\" 2>/dev/null; elif command -v osascript &>/dev/null; then osascript -e 'display notification \"Task completed\" with title \"Claude Code\"' 2>/dev/null; fi; exit 0"
+              }
+            ]
+          }
+        ],
+        Notification: [
+          {
+            matcher: "permission_prompt",
+            hooks: [
+              {
+                type: "command",
+                command: "if command -v notify-send &>/dev/null; then notify-send -u critical -i dialog-warning 'Claude Code' '⚠️ Permission required - check terminal' 2>/dev/null; elif command -v powershell.exe &>/dev/null; then powershell.exe -Command \"[System.Reflection.Assembly]::LoadWithPartialName('System.Windows.Forms'); [System.Windows.Forms.MessageBox]::Show('Permission required - check terminal', 'Claude Code', 'OK', 'Warning')\" 2>/dev/null; fi; exit 0"
+              }
+            ]
+          }
+        ]
+      }
+    };
+    writeFileSync(claudeSettingsPath, JSON.stringify(claudeSettings, null, 2));
+    success(`Created: ${claudeSettingsPath}`);
   }
 
   // Download skills folder (always overwrite to get latest)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-workflow-init",
-  "version": "6.1.0",
+  "version": "6.2.3",
   "description": "Initialize AI workflow docs & commands into any repo with one command",
   "bin": {
     "ai-workflow-init": "./cli.js"

package/.claude/hooks.json

@@ -1,34 +0,0 @@
-{
-  "hooks": [
-    {
-      "id": "validate-planning-doc",
-      "description": "Validate planning doc structure after creation",
-      "event": "PostToolUse",
-      "tools": ["Write"],
-      "matchPath": "docs/ai/planning/feature-*.md",
-      "type": "prompt",
-      "prompt": "Validate this planning document has all required sections: 1. Goal & Acceptance Criteria, 2. Risks & Assumptions, 3. Definition of Done, 4. Implementation Plan (with Summary and Phases), 5. Follow-ups. Return JSON: {\"valid\": true/false, \"missing\": [list of missing sections], \"message\": \"brief validation result\"}",
-      "blocking": false
-    },
-    {
-      "id": "validate-phase-completion",
-      "description": "Check if all tasks in a phase are completed before moving to next phase",
-      "event": "PreToolUse",
-      "tools": ["Edit"],
-      "matchPath": "docs/ai/planning/feature-*.md",
-      "type": "prompt",
-      "prompt": "Before editing this planning doc, check if the agent is starting a new phase. If yes, verify all tasks in the previous phase are marked [x]. Return JSON: {\"canProceed\": true/false, \"message\": \"reason\"}",
-      "blocking": false
-    },
-    {
-      "id": "log-feature-progress",
-      "description": "Log when tasks are completed in planning docs",
-      "event": "PostToolUse",
-      "tools": ["Edit"],
-      "matchPath": "docs/ai/planning/feature-*.md",
-      "type": "command",
-      "command": "echo \"[$(date '+%Y-%m-%d %H:%M:%S')] Task updated in $FILE\" >> .claude/feature-progress.log",
-      "blocking": false
-    }
-  ]
-}