feat(workflow): add project-level state management with intelligent initialization

Implement comprehensive project.json system for tracking project state, completed features, and architecture overview.

## New Features

### 1. /workflow:init Command (NEW)
- Independent project initialization command using cli-explore-agent
- Deep Scan mode analyzes: technology stack, architecture, key components, metrics
- Generates project.json with comprehensive overview field
- Supports --regenerate flag to update analysis while preserving features
- One-time initialization with intelligent project cognition

### 2. Enhanced session:start
- Added Step 0: Check project.json existence before session creation
- Auto-calls /workflow:init if project.json missing
- Separated project-level vs session-level initialization responsibilities

### 3. Enhanced session:complete
- Added Phase 3: Update Project Feature Registry
- Extracts feature metadata from IMPL_PLAN.md
- Records completed sessions as features in project.json
- Includes: title, description, tags, timeline, traceability (archive_path, commit_hash)
- Auto-generates feature IDs and tags from implementation plans

### 4. Enhanced status Command
- Added --project flag for project overview mode
- Displays: technology stack, architecture patterns, key components, metrics
- Shows completed features with full traceability
- Provides query commands for feature exploration

### 5. Enhanced context-gather
- Integrated project.json reading in context-search-agent workflow
- Phase 1: Load project.json overview as foundational context
- Phase 3: Populate context-package.json from project.json
- Prioritizes project.json context for architecture and tech stack
- Avoids redundant project analysis on every planning session

## Data Flow
project.json (init) → context-gather → context-package.json → task-generation
session-complete → project.json (features registry)

## Benefits
- Single source of truth for project state
- Efficient context reuse across sessions
- Complete feature traceability and history
- Consistent architectural baseline for all workflows

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.claude/commands/workflow/session/complete.md

@@ -127,6 +127,158 @@ bash(mv .workflow/WFS-session-name .workflow/.archives/WFS-session-name)
 Task(subagent_type="universal-executor", description="Complete session archival", prompt=`...`)
 ```
 
+### Phase 3: Update Project Feature Registry
+
+**Purpose**: Record completed session as a project feature in `.workflow/project.json`.
+
+**Execution**: After agent successfully completes archival, extract feature information and update project registry.
+
+#### Step 3.1: Check Project State Exists
+```bash
+bash(test -f .workflow/project.json && echo "EXISTS" || echo "SKIP")
+```
+
+**If SKIP**: Output warning and skip Phase 3
+```
+WARNING: No project.json found. Run /workflow:session:start to initialize.
+```
+
+#### Step 3.2: Extract Feature Information (Simple Text Processing)
+
+```bash
+# Read archived IMPL_PLAN.md
+bash(cat .workflow/.archives/WFS-session-name/IMPL_PLAN.md | head -20)
+```
+
+**Data Processing** (No agent needed):
+1. Extract feature title: First `#` heading line
+2. Extract description: First paragraph after heading (max 200 chars)
+3. Get session_id from archive path
+4. Get completion timestamp
+
+**Extraction Logic**:
+```javascript
+// Read IMPL_PLAN.md
+const planContent = Read(`${archivePath}/IMPL_PLAN.md`);
+
+// Extract title (first # heading)
+const titleMatch = planContent.match(/^#\s+(.+)$/m);
+const title = titleMatch ? titleMatch[1].trim() : sessionId.replace('WFS-', '');
+
+// Extract description (first paragraph, max 200 chars)
+const descMatch = planContent.match(/^#[^\n]+\n\n([^\n]+)/m);
+const description = descMatch ? descMatch[1].substring(0, 200).trim() : '';
+
+// Create feature ID (lowercase slug)
+const featureId = title.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 50);
+```
+
+#### Step 3.3: Update project.json
+
+```bash
+# Read current project state
+bash(cat .workflow/project.json)
+```
+
+**JSON Update Logic**:
+```javascript
+// Read existing project.json (created by /workflow:init)
+// Note: overview field is managed by /workflow:init, not modified here
+const projectMeta = JSON.parse(Read('.workflow/project.json'));
+const currentTimestamp = new Date().toISOString();
+const currentDate = currentTimestamp.split('T')[0]; // YYYY-MM-DD
+
+// Extract tags from IMPL_PLAN.md (simple keyword extraction)
+const tags = extractTags(planContent); // e.g., ["auth", "security"]
+
+// Build feature object with complete metadata
+const newFeature = {
+  id: featureId,
+  title: title,
+  description: description,
+  status: "completed",
+  tags: tags,
+  timeline: {
+    created_at: currentTimestamp,
+    implemented_at: currentDate,
+    updated_at: currentTimestamp
+  },
+  traceability: {
+    session_id: sessionId,
+    archive_path: archivePath, // e.g., ".workflow/.archives/WFS-auth-system"
+    commit_hash: getLatestCommitHash() || "" // Optional: git rev-parse HEAD
+  },
+  docs: [],      // Placeholder for future doc links
+  relations: []  // Placeholder for feature dependencies
+};
+
+// Add new feature to array
+projectMeta.features.push(newFeature);
+
+// Update statistics
+projectMeta.statistics.total_features = projectMeta.features.length;
+projectMeta.statistics.total_sessions += 1;
+projectMeta.statistics.last_updated = currentTimestamp;
+
+// Write back
+Write('.workflow/project.json', JSON.stringify(projectMeta, null, 2));
+```
+
+**Helper Functions**:
+```javascript
+// Extract tags from IMPL_PLAN.md content
+function extractTags(planContent) {
+  const tags = [];
+
+  // Look for common keywords
+  const keywords = {
+    'auth': /authentication|login|oauth|jwt/i,
+    'security': /security|encrypt|hash|token/i,
+    'api': /api|endpoint|rest|graphql/i,
+    'ui': /component|page|interface|frontend/i,
+    'database': /database|schema|migration|sql/i,
+    'test': /test|testing|spec|coverage/i
+  };
+
+  for (const [tag, pattern] of Object.entries(keywords)) {
+    if (pattern.test(planContent)) {
+      tags.push(tag);
+    }
+  }
+
+  return tags.slice(0, 5); // Max 5 tags
+}
+
+// Get latest git commit hash (optional)
+function getLatestCommitHash() {
+  try {
+    const result = Bash({
+      command: "git rev-parse --short HEAD 2>/dev/null",
+      description: "Get latest commit hash"
+    });
+    return result.trim();
+  } catch {
+    return "";
+  }
+}
+```
+
+#### Step 3.4: Output Confirmation
+
+```
+✓ Feature "${title}" added to project registry
+  ID: ${featureId}
+  Session: ${sessionId}
+  Location: .workflow/project.json
+```
+
+**Error Handling**:
+- If project.json malformed: Output error, skip update
+- If IMPL_PLAN.md missing: Use session_id as title
+- If extraction fails: Use minimal defaults
+
+**Phase 3 Total Commands**: 2 bash reads + JSON manipulation
+
 ## Archive Query Commands
 
 After archival, you can query the manifest:

.claude/commands/workflow/session/start.md

@@ -13,6 +13,35 @@ examples:
 ## Overview
 Manages workflow sessions with three operation modes: discovery (manual), auto (intelligent), and force-new.
 
+**Dual Responsibility**:
+1. **Project-level initialization** (first-time only): Creates `.workflow/project.json` for feature registry
+2. **Session-level initialization** (always): Creates session directory structure
+
+## Step 0: Initialize Project State (First-time Only)
+
+**Executed before all modes** - Ensures project-level state file exists by calling `/workflow:init`.
+
+### Check and Initialize
+```bash
+# Check if project state exists
+bash(test -f .workflow/project.json && echo "EXISTS" || echo "NOT_FOUND")
+```
+
+**If NOT_FOUND**, delegate to `/workflow:init`:
+```javascript
+// Call workflow:init for intelligent project analysis
+SlashCommand({command: "/workflow:init"});
+
+// Wait for init completion
+// project.json will be created with comprehensive project overview
+```
+
+**Output**:
+- If EXISTS: `PROJECT_STATE: initialized`
+- If NOT_FOUND: Calls `/workflow:init` → creates `.workflow/project.json` with full project analysis
+
+**Note**: `/workflow:init` uses cli-explore-agent to build comprehensive project understanding (technology stack, architecture, key components). This step runs once per project. Subsequent executions skip initialization.
+
 ## Mode 1: Discovery Mode (Default)
 
 ### Usage