claude-flow-novice 2.13.0 → 2.14.1

package/.claude/commands/cfn/context-query.md

@@ -1,65 +1,60 @@
 ---
-description: Query adaptive context bullets by category, tags, confidence
+description: Query adaptive context bullets by category, tags, confidence, or semantic similarity
 tags: [context, ace, query, search, retrieval]
 ---
 
 # Context Query Command
 
-Search the `adaptive_context` table to retrieve relevant bullets.
+Search the `adaptive_context` table to retrieve relevant bullets for task execution, agent spawning, or CLAUDE.md injection.
 
 **Usage:**
 ```bash
-/context-query [--category=<type>] [--tags=<tag>] [--min-confidence=<0.0-1.0>]
+/context-query [--category=<type>] [--tags=<tag1,tag2>] [--min-confidence=<0.0-1.0>]
 ```
 
-**Quick SQL Queries:**
+**What This Does:**
+1. Queries `adaptive_context` table with filters
+2. Ranks bullets by relevance (priority, confidence, usage_count)
+3. Optionally uses semantic similarity if embeddings available
+4. Returns formatted bullets ready for injection
+
+**Arguments:**
+- `--category=<type>`: Filter by category (strategy/pattern/edge_case/domain_insight/anti_pattern/optimization)
+- `--tags=<tag1,tag2>`: Filter by tags (comma-separated)
+- `--min-confidence=<0.0-1.0>`: Minimum confidence score (default: 0.6)
+- `--min-helpful=<count>`: Minimum helpful_count (default: 0)
+- `--max-harmful=<count>`: Maximum harmful_count (default: 2)
+- `--priority-min=<1-10>`: Minimum priority (default: 5)
+- `--limit=<N>`: Max results to return (default: 20)
+- `--sort-by=<field>`: Sort by confidence|helpful_count|priority|last_used_at (default: priority)
+- `--semantic-query=<text>`: Find bullets semantically similar to query text (requires embeddings)
+- `--related-to=<bullet-id>`: Find bullets related to specific bullet
+- `--swarm-id=<id>`: Filter by swarm context
+- `--project-id=<id>`: Filter by project context
+- `--output=<format>`: Output format (json|markdown|claude-md) (default: markdown)
+- `--inject`: Automatically inject results into CLAUDE.md
+
+**Query Examples:**
 
 ```bash
 # Get top strategy bullets
-sqlite3 ./.artifacts/database/swarm-memory.db "
-SELECT bullet_id, content, confidence_score, helpful_count
-FROM adaptive_context
-WHERE is_active = 1 AND category = 'strategy' AND confidence_score >= 0.8
-ORDER BY confidence_score DESC, helpful_count DESC
-LIMIT 10;
-"
+/context-query --category=strategy --min-confidence=0.8 --limit=10
 
 # Find CFN Loop coordination patterns
-sqlite3 ./.artifacts/database/swarm-memory.db "
-SELECT bullet_id, category, content, tags
-FROM adaptive_context
-WHERE is_active = 1
-  AND (tags LIKE '%cfn-loop%' OR tags LIKE '%coordination%')
-  AND helpful_count >= 3
-ORDER BY helpful_count DESC;
-"
-
-# Get high-priority optimization tips
-sqlite3 ./.artifacts/database/swarm-memory.db "
-SELECT bullet_id, content, confidence_score, priority
-FROM adaptive_context
-WHERE is_active = 1
-  AND category = 'optimization'
-  AND priority >= 7
-ORDER BY confidence_score DESC;
-"
-
-# Get all active bullets
-sqlite3 ./.artifacts/database/swarm-memory.db "
-SELECT bullet_id, category, content, confidence_score, helpful_count, harmful_count
-FROM adaptive_context
-WHERE is_active = 1
-ORDER BY helpful_count DESC, confidence_score DESC
-LIMIT 20;
-"
-```
+/context-query --tags=cfn-loop,coordination --min-helpful=3
 
-**Arguments:**
-- `--category=<type>`: strategy|pattern|edge_case|domain_insight|anti_pattern|optimization
-- `--tags=<tag>`: Filter by tag (single tag)
-- `--min-confidence=<0.0-1.0>`: Minimum confidence (default: 0.6)
-- `--min-helpful=<N>`: Minimum helpful_count (default: 0)
-- `--limit=<N>`: Max results (default: 20)
+# Get all high-priority optimization tips
+/context-query --category=optimization --priority-min=7 --sort-by=confidence
+
+# Semantic search for Redis patterns
+/context-query --semantic-query="Redis pub/sub coordination patterns"
+
+# Get bullets related to specific bullet
+/context-query --related-to=STRAT-001 --limit=5
+
+# Get project-specific domain insights
+/context-query --category=domain_insight --project-id=proj-auth --min-helpful=5
+```
 
 **Output Formats:**
 

package/.claude/commands/cfn/context-reflect.md

@@ -68,16 +68,20 @@ Spawn a `context-reflector` agent to analyze recent task execution traces and ex
 /context-reflect --reflection-type=optimization --swarm-id=swarm-perf
 ```
 
-**Implementation:**
+**Reflection Prompt Template:**
+The reflector agent will use this structured prompt:
 
-Spawn the `context-reflector` agent with task context:
+```
+You are a Context Reflector for the ACE (Adaptive Context Extension) system.
+
+**Task Execution Trace:**
+{execution_trace}
 
-```javascript
-Task("context-reflector", `
-You are a Context Reflector for the ACE system.
+**Feedback Signals:**
+{feedback_signals}
 
 **Your Mission:**
-Analyze recent task execution and extract 3-7 high-quality lessons. For each lesson:
+Extract 3-7 high-quality lessons (bullets) from this execution. For each lesson:
 
 1. **Identify the pattern/insight**: What worked? What failed? What was unexpected?
 2. **Classify the lesson**:
@@ -94,40 +98,38 @@ Analyze recent task execution and extract 3-7 high-quality lessons. For each les
    - Include context/conditions ("When X, do Y")
    - 1-3 sentences max
 
-4. Assess confidence (0.0-1.0)
-5. Add 2-5 relevant tags
-
-**Steps:**
-1. Read recent task execution logs/context
-2. Identify patterns, successes, failures, edge cases
-3. For each lesson, use store-reflection.sh:
-
-   \`\`\`bash
-   # Create lessons file
-   cat > /tmp/lessons.json << 'EOF'
-   [
-     {
-       "bullet_id": "STRAT-XXX",
-       "category": "strategy",
-       "content": "Lesson content here",
-       "confidence": 0.85,
-       "tags": ["tag1", "tag2"]
-     }
-   ]
-   EOF
-
-   # Store reflection
-   ./.claude/skills/cfn-ace-system/store-reflection.sh \\
-     --reflection-type success \\
-     --task-id \${TASK_ID} \\
-     --agent-id \${AGENT_ID} \\
-     --lessons-file /tmp/lessons.json
-   \`\`\`
-
-4. Report reflection ID and summary
-`, "context-reflector");
+4. **Assess confidence**: 0.0-1.0 based on:
+   - Strong evidence (tests pass, metrics improve) → 0.8-1.0
+   - Moderate evidence (code works, no tests) → 0.5-0.7
+   - Hypothesis/observation (needs validation) → 0.3-0.4
+
+5. **Tag appropriately**: Add 2-5 relevant tags for retrieval
+
+**Output Format (JSON):**
+{
+  "reflection_type": "success|failure|optimization|edge_case|pattern",
+  "summary": "Brief summary of what was learned",
+  "extracted_lessons": [
+    {
+      "bullet_id": "STRAT-XXX",  // Use next available ID
+      "category": "strategy|pattern|edge_case|domain_insight|anti_pattern|optimization",
+      "content": "Actionable lesson with context",
+      "confidence": 0.85,
+      "tags": ["tag1", "tag2"],
+      "reasoning": "Why this lesson is valuable"
+    }
+  ],
+  "helpful_existing_bullets": ["STRAT-001", "PATTERN-017"],  // Bullets that helped
+  "harmful_existing_bullets": []  // Bullets that led astray
+}
 ```
 
+**Storage:**
+- Reflections stored in `context_reflections` table
+- ACL Level 3 (Swarm) - visible to swarm members
+- 30-day retention for pending reflections
+- Processed reflections retained as audit trail
+
 **Post-Reflection:**
 1. If `--auto-curate` enabled: Trigger `/context-curate --reflection-id=<id>`
 2. Otherwise: Reflection queued for manual curation

package/.claude/commands/cfn/context-stats.md

@@ -5,52 +5,27 @@ tags: [context, ace, stats, analytics, health]
 
 # Context Statistics Command
 
-View statistics about adaptive context bullets in the database.
+View comprehensive statistics about the adaptive context system, including bullet health, usage patterns, confidence trends, and curation metrics.
 
 **Usage:**
 ```bash
-/context-stats [--query=<type>] [--limit=<N>]
+/context-stats [--category=<type>] [--period=<days>] [--format=<format>]
 ```
 
 **What This Does:**
-Queries the `adaptive_context` and related tables for statistics.
+1. Queries `adaptive_context`, `context_usage_log`, and `context_merge_log` tables
+2. Generates analytics and health metrics
+3. Identifies trends, anomalies, and optimization opportunities
+4. Provides actionable recommendations
 
 **Arguments:**
-- `--query=<type>`: Query type (reflections|insights|summary) (default: summary)
-- `--limit=<N>`: Maximum results (default: 100)
-- `--category=<type>`: Filter by bullet category
-- `--min-confidence=<0.0-1.0>`: Filter by minimum confidence
-
-**Implementation:**
-Execute the ACE stats script directly:
-
-```bash
-# Query summary
-./.claude/skills/cfn-ace-system/invoke-context-stats.sh --query summary
-
-# Query all bullets
-sqlite3 ./.artifacts/database/swarm-memory.db "
-SELECT
-  category,
-  COUNT(*) as count,
-  AVG(confidence_score) as avg_confidence,
-  SUM(helpful_count) as total_helpful,
-  SUM(harmful_count) as total_harmful
-FROM adaptive_context
-WHERE is_active = 1
-GROUP BY category
-ORDER BY count DESC;
-"
-
-# Get top bullets
-sqlite3 ./.artifacts/database/swarm-memory.db "
-SELECT bullet_id, category, confidence_score, helpful_count, harmful_count, content
-FROM adaptive_context
-WHERE is_active = 1
-ORDER BY helpful_count DESC, confidence_score DESC
-LIMIT 10;
-"
-```
+- `--category=<type>`: Filter by category (default: all)
+- `--period=<days>`: Analysis period in days (default: 30)
+- `--swarm-id=<id>`: Filter by swarm
+- `--project-id=<id>`: Filter by project
+- `--format=<format>`: Output format (text|json|chart) (default: text)
+- `--detail-level=<level>`: Summary|detailed|comprehensive (default: summary)
+- `--output=<path>`: Save report to file
 
 **Output Example:**
 

package/.claude/commands/cfn/launch-web-dashboard.md

@@ -1,295 +0,0 @@
-# Launch Web Dashboard - Start Web Portal Development Server
-
-Launch the claude-flow-novice web portal with hot-reload development servers for both client and server.
-
-## Command
-
-```bash
-/launch-web-dashboard [--port <port>] [--production]
-```
-
-## Execution Pattern
-
-### Default Development Mode
-
-```bash
-# Navigate to web portal package
-cd packages/web-portal
-
-# Kill any existing processes on ports 3001-3003 (client) and 3000-3002 (server)
-lsof -ti:3001,3002,3003,3000 | xargs -r kill -9
-
-# Start development servers with hot-reload
-npm run dev
-```
-
-This will:
-1. **Client (Vite)**: Start on port 3001 (or next available: 3002, 3003)
-2. **Server (tsx watch)**: Start on port 3000 (or next available: 3001, 3002)
-
-### Production Mode
-
-```bash
-# Build for production
-npm run build
-
-# Start production server
-npm run start
-```
-
-## Port Configuration
-
-### Default Ports
-- **Client (Vite)**: 3001
-- **Server (Express)**: 3000
-- **WebSocket**: Same as server port
-
-### Port Conflict Resolution
-If ports are in use, automatically tries next available port:
-- Client: 3001 → 3002 → 3003
-- Server: 3000 → 3001 → 3002
-
-## Output
-
-```
-🚀 Launching Web Portal...
-
-📦 Package: @claude-flow-novice/web-portal
-📂 Directory: packages/web-portal
-
-🔧 Cleaning up existing processes...
-✅ Ports cleared: 3001, 3002, 3000
-
-🎬 Starting development servers...
-
-[Client] VITE v7.1.9  ready in 951 ms
-[Client] ➜  Local:   http://localhost:3001/
-[Client] ➜  Network: use --host to expose
-
-[Server] 🚀 Server running on http://localhost:3000
-[Server] 📊 Metrics: http://localhost:3000/api/metrics
-[Server] 🔌 WebSocket: ws://localhost:3000
-
-✅ Web Dashboard Launched Successfully!
-
-📱 Access Points:
-   • Main UI: http://localhost:3001
-   • API Server: http://localhost:3000
-   • API Docs: http://localhost:3000/api-docs
-   • Health Check: http://localhost:3000/health
-
-🛠️  Available Features:
-   ✓ Agent Management & Monitoring
-   ✓ CFN Loop Execution & Visualization
-   ✓ Real-time Metrics Dashboard
-   ✓ WebSocket Live Updates
-   ✓ Hybrid Routing Control Panel
-   ✓ SQLite Memory Browser
-   ✓ Redis Coordination Monitor
-
-💡 Tips:
-   • Hot-reload enabled for instant updates
-   • Check console for detailed logs
-   • Press Ctrl+C to stop servers
-```
-
-## Flags
-
-### --port <port>
-Specify custom client port (server will use port-1)
-
-```bash
-/launch-web-dashboard --port 4000
-# Client: http://localhost:4000
-# Server: http://localhost:3999
-```
-
-### --production
-Build and run in production mode
-
-```bash
-/launch-web-dashboard --production
-# Optimized build with minification
-# No hot-reload, better performance
-```
-
-### --debug
-Enable verbose logging
-
-```bash
-/launch-web-dashboard --debug
-# Shows detailed startup logs
-# Includes dependency resolution
-# Displays all environment variables
-```
-
-### --kill-only
-Just kill existing processes without starting new ones
-
-```bash
-/launch-web-dashboard --kill-only
-# Cleanup only, useful for port conflicts
-```
-
-## Features Available in Dashboard
-
-### 1. Agent Management
-- View all active agents and their status
-- Monitor agent workload and performance
-- Inspect agent capabilities and roles
-- Track agent communication via Redis pub/sub
-
-### 2. CFN Loop Visualization
-- Real-time phase execution tracking
-- Loop 2/3/4 progress monitoring
-- Confidence score aggregation
-- Consensus validation status
-- Product Owner decisions
-
-### 3. Metrics Dashboard
-- Cost tracking (per provider)
-- Token usage analytics
-- API latency monitoring
-- Success/failure rates
-- Performance bottlenecks
-
-### 4. Hybrid Routing Control
-- Provider selection (Claude Max / z.ai)
-- Worker spawn monitoring
-- Coordinator intelligence tracking
-- Cost savings visualization
-
-### 5. Memory & State
-- SQLite memory browser with ACL levels
-- Redis key inspection
-- Audit trail viewer
-- Permission management
-
-### 6. Event Stream
-- Live WebSocket event feed
-- Filter by event type
-- Search historical events
-- Export event logs
-
-## Troubleshooting
-
-### Port Already in Use
-
-```bash
-# Automatic resolution
-/launch-web-dashboard
-# Will try ports 3001 → 3002 → 3003 automatically
-
-# Manual cleanup
-/launch-web-dashboard --kill-only
-# Then try again
-/launch-web-dashboard
-```
-
-### Build Errors
-
-```bash
-# Clean build cache
-cd packages/web-portal
-rm -rf node_modules .vite dist
-npm install
-npm run build
-
-# Then launch
-/launch-web-dashboard
-```
-
-### WebSocket Connection Issues
-
-Check that both client and server are running:
-```bash
-# Client should show: http://localhost:3001
-# Server should show: http://localhost:3000
-
-# WebSocket connects to server port
-# Ensure VITE_API_URL matches server URL
-```
-
-### Missing Dependencies
-
-```bash
-# Install all dependencies
-npm install
-
-# Web portal specific
-cd packages/web-portal
-npm install
-
-# Rebuild TypeScript
-npm run build
-```
-
-## Integration with Other Commands
-
-### With CFN Loop
-```bash
-# Launch dashboard first
-/launch-web-dashboard
-
-# In another terminal, run CFN Loop
-/cfn-loop "Task description" --mode=standard
-
-# Dashboard will show real-time progress
-```
-
-### With Hybrid Routing
-```bash
-# Start dashboard
-/launch-web-dashboard
-
-# Spawn workers (dashboard monitors them)
-npx claude-flow-spawn "Task" --max-agents 5
-```
-
-### With Swarm Coordination
-```bash
-# Launch dashboard
-/launch-web-dashboard
-
-# Initialize swarm
-node tests/manual/test-swarm-direct.js "Objective" --executor
-
-# Dashboard shows agent coordination
-```
-
-## Environment Variables
-
-The dashboard uses these environment variables (auto-configured):
-
-```bash
-# Client (.env in packages/web-portal)
-VITE_API_URL=http://localhost:3000
-VITE_WS_URL=ws://localhost:3000
-
-# Server
-PORT=3000
-NODE_ENV=development
-REDIS_URL=redis://localhost:6379
-SQLITE_DB_PATH=../../data/swarm-memory.db
-```
-
-## Security Note
-
-Development mode runs with:
-- CORS enabled for localhost
-- Authentication disabled
-- Verbose error messages
-
-For production deployment, use `--production` flag which enables:
-- CORS restrictions
-- Authentication requirements
-- Error sanitization
-- Rate limiting
-
-## Related Commands
-
-- `/cfn-loop` - Execute CFN Loop (visible in dashboard)
-- `/swarm` - Manage swarms (dashboard monitors)
-- `/github-commit` - Commit changes (shows in activity feed)
-- `/sqlite-memory` - Memory management (browsable in dashboard)
-- `/context-stats` - Context metrics (displayed in dashboard)

package/.claude/commands/cfn/list-agents-rebuild.md

@@ -1,6 +1,6 @@
 ---
 name: list-agents-rebuild
-description: "Regenerate available agents list from .claude/agents/cfn-dev-team/ folder discovery"
+description: "Regenerate available agents list from .claude/agents/ folder discovery"
 argument-hint: "[--output=path] [--format=markdown]"
 allowed-tools: ["Bash", "Read", "Write"]
 ---
@@ -11,12 +11,12 @@ Regenerate `src/cli/hybrid-routing/AVAILABLE-AGENTS.md` from live agent discover
 
 ## Architecture Clarification
 
-**Source of Truth**: `.claude/agents/cfn-dev-team/` folder (50+ agent .md files)
+**Source of Truth**: `.claude/agents/` folder (50+ agent .md files)
 **Live Discovery**: `HybridWorkerSpawner.loadAgentDefinitions()` method
 **Documentation Snapshot**: `src/cli/hybrid-routing/AVAILABLE-AGENTS.md` (generated file)
 
 **When coordinators spawn agents**:
-1. Load agents dynamically from `.claude/agents/cfn-dev-team/` folder
+1. Load agents dynamically from `.claude/agents/` folder
 2. Parse YAML frontmatter from each .md file
 3. Extract keywords, system prompts, categories
 4. In-memory cache for performance
@@ -26,7 +26,7 @@ Regenerate `src/cli/hybrid-routing/AVAILABLE-AGENTS.md` from live agent discover
 - Human-readable reference
 - Documentation for users/coordinators
 - Snapshot of available agents at generation time
-- **NOT** used by the spawning system (system reads .claude/agents/cfn-dev-team/ directly)
+- **NOT** used by the spawning system (system reads .claude/agents/ directly)
 
 ---
 
@@ -34,7 +34,7 @@ Regenerate `src/cli/hybrid-routing/AVAILABLE-AGENTS.md` from live agent discover
 
 ```bash
 # Regenerate agent list
-npx claude-flow-spawn --agents-by-category > src/cli/hybrid-routing/AVAILABLE-AGENTS.md.tmp
+node src/cli/hybrid-routing/spawn-workers.js --agents-by-category > src/cli/hybrid-routing/AVAILABLE-AGENTS.md.tmp
 
 # Parse and format into markdown document
 node << 'EOF'
@@ -52,12 +52,12 @@ let markdown = '';
 markdown += '# Available Specialized Agents\n\n';
 markdown += '**Hybrid Routing System - Dynamic Agent Discovery**\n\n';
 markdown += '**Generated**: ' + new Date().toISOString().split('T')[0] + '\n';
-markdown += '**Source**: `.claude/agents/cfn-dev-team/` folder (live discovery)\n';
-markdown += '**Purpose**: Documentation snapshot - coordinators read from `.claude/agents/cfn-dev-team/` directly\n\n';
+markdown += '**Source**: `.claude/agents/` folder (live discovery)\n';
+markdown += '**Purpose**: Documentation snapshot - coordinators read from `.claude/agents/` directly\n\n';
 
 // Add architecture note
 markdown += '## Architecture\n\n';
-markdown += '**Source of Truth**: `.claude/agents/cfn-dev-team/` folder\n';
+markdown += '**Source of Truth**: `.claude/agents/` folder\n';
 markdown += '- Coordinators use `HybridWorkerSpawner.loadAgentDefinitions()`\n';
 markdown += '- Recursive scanning with YAML frontmatter parsing\n';
 markdown += '- In-memory caching after first load\n';
@@ -72,7 +72,7 @@ const categoriesMatch = rawOutput.match(/(\d+) categories/);
 if (discoveredMatch && loadedMatch) {
   markdown += '## Discovery Statistics\n\n';
   markdown += '```\n';
-  markdown += `🔍 Discovered ${discoveredMatch[1]} agent files in .claude/agents/cfn-dev-team/\n`;
+  markdown += `🔍 Discovered ${discoveredMatch[1]} agent files in .claude/agents/\n`;
   markdown += `✅ Loaded ${loadedMatch[1]} agents (${skippedMatch ? skippedMatch[1] : '?'} skipped)\n`;
   markdown += `📋 ${categoriesMatch ? categoriesMatch[1] : '?'} categories\n`;
   markdown += '```\n\n';
@@ -126,9 +126,9 @@ markdown += '## Usage\n\n';
 markdown += '### CLI Commands\n\n';
 markdown += '```bash\n';
 markdown += '# List all agents (flat view)\n';
-markdown += 'npx claude-flow-spawn --list-agents\n\n';
+markdown += 'node src/cli/hybrid-routing/spawn-workers.js --list-agents\n\n';
 markdown += '# List agents by category\n';
-markdown += 'npx claude-flow-spawn --agents-by-category\n\n';
+markdown += 'node src/cli/hybrid-routing/spawn-workers.js --agents-by-category\n\n';
 markdown += '# Regenerate this documentation file\n';
 markdown += '/list-agents-rebuild\n';
 markdown += '```\n\n';
@@ -136,12 +136,12 @@ markdown += '```\n\n';
 markdown += '### Coordinator Usage\n\n';
 markdown += '```bash\n';
 markdown += '# Automatic selection (keyword-based)\n';
-markdown += 'npx claude-flow-spawn "Build auth" --max-agents=3\n\n';
+markdown += 'node src/cli/hybrid-routing/spawn-workers.js "Build auth" --max-agents=3\n\n';
 markdown += '# Coordinator override (manual agent types)\n';
-markdown += 'npx claude-flow-spawn "Task" \\\n';
+markdown += 'node src/cli/hybrid-routing/spawn-workers.js "Task" \\\n';
 markdown += '  --agents=architect,coder,tester\n\n';
 markdown += '# Full override (custom agents + subtasks)\n';
-markdown += 'npx claude-flow-spawn "Task" \\\n';
+markdown += 'node src/cli/hybrid-routing/spawn-workers.js "Task" \\\n';
 markdown += '  --agents=coder,security-specialist \\\n';
 markdown += '  --subtasks="Subtask 1|Subtask 2"\n';
 markdown += '```\n\n';
@@ -149,10 +149,10 @@ markdown += '```\n\n';
 // Add notes
 markdown += '---\n\n';
 markdown += '## Notes\n\n';
-markdown += '- **Live Discovery**: Coordinators read from `.claude/agents/cfn-dev-team/` folder directly\n';
+markdown += '- **Live Discovery**: Coordinators read from `.claude/agents/` folder directly\n';
 markdown += '- **This File**: Documentation snapshot for human reference\n';
 markdown += '- **Regenerate**: Run `/list-agents-rebuild` to update this documentation\n';
-markdown += '- **Agent Files**: Add/modify agents in `.claude/agents/cfn-dev-team/` folder (auto-discovered)\n';
+markdown += '- **Agent Files**: Add/modify agents in `.claude/agents/` folder (auto-discovered)\n';
 markdown += '- **Caching**: Agent definitions cached after first load (lazy loading)\n';
 markdown += '- **Missing Keywords**: Some agents without keywords can be used via coordinator override\n\n';
 
@@ -184,7 +184,7 @@ echo ""
 echo "📋 Agent list regenerated: src/cli/hybrid-routing/AVAILABLE-AGENTS.md"
 echo ""
 echo "Architecture:"
-echo "  • Source: .claude/agents/cfn-dev-team/ folder (50+ agent .md files)"
+echo "  • Source: .claude/agents/ folder (50+ agent .md files)"
 echo "  • Coordinators: Load agents dynamically via HybridWorkerSpawner"
 echo "  • This file: Documentation snapshot for human reference"
 ```
@@ -199,7 +199,7 @@ echo "  • This file: Documentation snapshot for human reference"
 📋 Agent list regenerated: src/cli/hybrid-routing/AVAILABLE-AGENTS.md
 
 Architecture:
-  • Source: .claude/agents/cfn-dev-team/ folder (50+ agent .md files)
+  • Source: .claude/agents/ folder (50+ agent .md files)
   • Coordinators: Load agents dynamically via HybridWorkerSpawner
   • This file: Documentation snapshot for human reference
 ```