@monoes/monomindcli 1.8.0 → 1.9.0

package/.claude/skills/agentdb-vector-search/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: "AgentDB Vector Search"
+name: agentdb-vector-search
 description: "Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases."
 ---
 
@@ -12,7 +12,7 @@ Implements vector-based semantic search using AgentDB's high-performance vector
 ## Prerequisites
 
 - Node.js 18+
-- AgentDB v1.0.7+ (via agentic-flow or standalone)
+- @monomind/memory package
 - OpenAI API key (for embeddings) or custom embedding model
 
 ## Quick Start with CLI
@@ -21,61 +21,61 @@ Implements vector-based semantic search using AgentDB's high-performance vector
 
 ```bash
 # Initialize with default dimensions (1536 for OpenAI ada-002)
-npx agentdb@latest init ./vectors.db
+npx monomind memory init ./vectors.db
 
 # Custom dimensions for different embedding models
-npx agentdb@latest init ./vectors.db --dimension 768  # sentence-transformers
-npx agentdb@latest init ./vectors.db --dimension 384  # all-MiniLM-L6-v2
+npx monomind memory init ./vectors.db --dimension 768  # sentence-transformers
+npx monomind memory init ./vectors.db --dimension 384  # all-MiniLM-L6-v2
 
 # Use preset configurations
-npx agentdb@latest init ./vectors.db --preset small   # <10K vectors
-npx agentdb@latest init ./vectors.db --preset medium  # 10K-100K vectors
-npx agentdb@latest init ./vectors.db --preset large   # >100K vectors
+npx monomind memory init ./vectors.db --preset small   # <10K vectors
+npx monomind memory init ./vectors.db --preset medium  # 10K-100K vectors
+npx monomind memory init ./vectors.db --preset large   # >100K vectors
 
 # In-memory database for testing
-npx agentdb@latest init ./vectors.db --in-memory
+npx monomind memory init ./vectors.db --in-memory
 ```
 
 ### Query Vector Database
 
 ```bash
 # Basic similarity search
-npx agentdb@latest query ./vectors.db "[0.1,0.2,0.3,...]"
+npx monomind memory query ./vectors.db "[0.1,0.2,0.3,...]"
 
 # Top-k results
-npx agentdb@latest query ./vectors.db "[0.1,0.2,0.3]" -k 10
+npx monomind memory query ./vectors.db "[0.1,0.2,0.3]" -k 10
 
 # With similarity threshold (cosine similarity)
-npx agentdb@latest query ./vectors.db "0.1 0.2 0.3" -t 0.75 -m cosine
+npx monomind memory query ./vectors.db "0.1 0.2 0.3" -t 0.75 -m cosine
 
 # Different distance metrics
-npx agentdb@latest query ./vectors.db "[...]" -m euclidean  # L2 distance
-npx agentdb@latest query ./vectors.db "[...]" -m dot        # Dot product
+npx monomind memory query ./vectors.db "[...]" -m euclidean  # L2 distance
+npx monomind memory query ./vectors.db "[...]" -m dot        # Dot product
 
 # JSON output for automation
-npx agentdb@latest query ./vectors.db "[...]" -f json -k 5
+npx monomind memory query ./vectors.db "[...]" -f json -k 5
 
 # Verbose output with distances
-npx agentdb@latest query ./vectors.db "[...]" -v
+npx monomind memory query ./vectors.db "[...]" -v
 ```
 
 ### Import/Export Vectors
 
 ```bash
 # Export vectors to JSON
-npx agentdb@latest export ./vectors.db ./backup.json
+npx monomind memory export ./vectors.db ./backup.json
 
 # Import vectors from JSON
-npx agentdb@latest import ./backup.json
+npx monomind memory import ./backup.json
 
 # Get database statistics
-npx agentdb@latest stats ./vectors.db
+npx monomind memory stats ./vectors.db
 ```
 
 ## Quick Start with API
 
 ```typescript
-import { createAgentDBAdapter, computeEmbedding } from 'agentic-flow/reasoningbank';
+import { createAgentDBAdapter, computeEmbedding } from '@monomind/memory';
 
 // Initialize with vector search optimizations
 const adapter = await createAgentDBAdapter({
@@ -182,11 +182,11 @@ await db.batchStore(documents.map(doc => ({
 ## MCP Server Integration
 
 ```bash
-# Start AgentDB MCP server for Claude Code
-npx agentdb@latest mcp
+# Start Monomind MCP server for Claude Code
+npx monomind mcp start
 
 # Add to Claude Code (one-time setup)
-claude mcp add agentdb npx agentdb@latest mcp
+claude mcp add monomind npx monomind@latest mcp start
 
 # Now use MCP tools in Claude Code:
 # - agentdb_query: Semantic vector search
@@ -198,13 +198,13 @@ claude mcp add agentdb npx agentdb@latest mcp
 
 ```bash
 # Run comprehensive benchmarks
-npx agentdb@latest benchmark
+npx monomind memory benchmark
 
 # Results:
-# ✅ Pattern Search: 150x faster (100µs vs 15ms)
-# ✅ Batch Insert: 500x faster (2ms vs 1s for 100 vectors)
-# ✅ Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)
-# ✅ Memory Efficiency: 4-32x reduction with quantization
+# Pattern Search: 150x faster (100µs vs 15ms)
+# Batch Insert: 500x faster (2ms vs 1s for 100 vectors)
+# Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)
+# Memory Efficiency: 4-32x reduction with quantization
 ```
 
 ## Quantization Options
@@ -236,13 +236,13 @@ const adapter = await createAgentDBAdapter({
 
 ```bash
 # Cosine similarity (default, best for most use cases)
-npx agentdb@latest query ./db.sqlite "[...]" -m cosine
+npx monomind memory query ./db.sqlite "[...]" -m cosine
 
 # Euclidean distance (L2 norm)
-npx agentdb@latest query ./db.sqlite "[...]" -m euclidean
+npx monomind memory query ./db.sqlite "[...]" -m euclidean
 
 # Dot product (for normalized vectors)
-npx agentdb@latest query ./db.sqlite "[...]" -m dot
+npx monomind memory query ./db.sqlite "[...]" -m dot
 ```
 
 ## Advanced Features
@@ -276,7 +276,7 @@ npx agentdb@latest query ./db.sqlite "[...]" -m dot
 ### Issue: Slow search performance
 ```bash
 # Check if HNSW indexing is enabled (automatic)
-npx agentdb@latest stats ./vectors.db
+npx monomind memory stats ./vectors.db
 
 # Expected: <100µs search time
 ```
@@ -290,7 +290,7 @@ npx agentdb@latest stats ./vectors.db
 ### Issue: Poor relevance
 ```bash
 # Adjust similarity threshold
-npx agentdb@latest query ./db.sqlite "[...]" -t 0.8  # Higher threshold
+npx monomind memory query ./db.sqlite "[...]" -t 0.8  # Higher threshold
 
 # Or use MMR for diverse results
 # Use in adapter: useMMR: true
@@ -303,14 +303,14 @@ npx agentdb@latest query ./db.sqlite "[...]" -t 0.8  # Higher threshold
 # - sentence-transformers: 768
 # - all-MiniLM-L6-v2: 384
 
-npx agentdb@latest init ./db.sqlite --dimension 768
+npx monomind memory init ./db.sqlite --dimension 768
 ```
 
 ## Database Statistics
 
 ```bash
 # Get comprehensive stats
-npx agentdb@latest stats ./vectors.db
+npx monomind memory stats ./vectors.db
 
 # Shows:
 # - Total patterns/vectors
@@ -331,9 +331,5 @@ npx agentdb@latest stats ./vectors.db
 
 ## Learn More
 
-- GitHub: https://github.com/nokhodian/agentic-flow/tree/main/packages/agentdb
-- Documentation: node_modules/agentic-flow/docs/AGENTDB_INTEGRATION.md
-- MCP Integration: `npx agentdb@latest mcp` for Claude Code
-- Website: https://agentdb.ruv.io
-- CLI Help: `npx agentdb@latest --help`
-- Command Help: `npx agentdb@latest help <command>`
+- GitHub: https://github.com/nokhodian/monomind
+- MCP Integration: `npx monomind mcp start`

package/.claude/skills/{v3-integration-deep → agentic-integration}/SKILL.md

@@ -1,19 +1,26 @@
 ---
-name: "v1 Deep Integration"
-description: "Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building monomind as specialized extension rather than parallel implementation."
+name: agentic-integration
+description: "Code deduplication architecture implementing ADR-001. Eliminates 10,000+ duplicate lines by consolidating overlapping coordination systems using SONA, Flash Attention, and AgentDB."
+triggers:
+  - reduce code duplication
+  - SONA integration
+  - Flash Attention integration
+  - ADR-001
+  - eliminate duplicate lines
+  - consolidate coordination systems
 ---
 
-# Deep Integration
+# Agentic Integration
 
 ## What This Skill Does
 
-Transforms monomind from parallel implementation to specialized extension of agentic-flow@alpha, eliminating massive code duplication while achieving performance improvements and feature parity.
+This skill is a reference guide for the code deduplication architecture defined in ADR-001. Monomind consolidates overlapping coordination systems, eliminating massive code duplication while achieving performance improvements and feature parity.
 
 ## Quick Start
 
 ```bash
 # Initialize deep integration
-Task("Integration architecture", "Design agentic-flow@alpha adapter layer", "v1-integration-architect")
+Task("Integration architecture", "Design adapter layer for deduplication ADR-001", "v1-integration-architect")
 
 # Feature integration (parallel)
 Task("SONA integration", "Integrate 5 SONA learning modes", "v1-integration-architect")
@@ -38,7 +45,7 @@ Task("AgentDB coordination", "Setup 150x-12,500x search", "v1-integration-archit
 TARGET: <5,000 lines (vs 15,000+ currently)
 ```
 
-## agentic-flow@alpha Feature Integration
+## Feature Integration
 
 ### SONA Learning Modes
 
@@ -196,7 +203,7 @@ const attentionBenchmark = {
   baseline: "current attention mechanism",
   target: "2.49x-7.47x improvement",
   memoryReduction: "50-75%",
-  implementation: "agentic-flow@alpha Flash Attention",
+  implementation: "monomind Flash Attention",
 };
 ```
 
@@ -206,7 +213,7 @@ const attentionBenchmark = {
 const searchBenchmark = {
   baseline: "linear search in current systems",
   target: "150x-12,500x via HNSW indexing",
-  implementation: "agentic-flow@alpha AgentDB",
+  implementation: "monomind AgentDB (@monomind/memory)",
 };
 ```
 
@@ -250,9 +257,9 @@ class BackwardCompatibility {
 - **SONA**: <0.05ms adaptation time
 - **Integration**: All 213 MCP tools + 19 hook types available
 
-## Related v1 Skills
+## Related Skills
 
-- `v1-memory-unification` - Memory system integration
-- `v1-performance-optimization` - Performance target validation
-- `v1-swarm-coordination` - Swarm system migration
-- `v1-security-overhaul` - Secure integration patterns
+- `memory-unification` - Memory system integration
+- `performance-optimization` - Performance target validation
+- `swarm-coordination` - Swarm system migration
+- `security-hardening` - Secure integration patterns

package/.claude/skills/agentic-jujutsu/SKILL.md

@@ -11,13 +11,13 @@ description: |
 ## When to Use This Skill
 
 Use **agentic-jujutsu** when you need:
-- ✅ Multiple AI agents modifying code simultaneously
-- ✅ Lock-free version control (23x faster than Git)
-- ✅ Self-learning AI that improves from experience
-- ✅ Quantum-resistant security for future-proof protection
-- ✅ Automatic conflict resolution (87% success rate)
-- ✅ Pattern recognition and intelligent suggestions
-- ✅ Multi-agent coordination without blocking
+- Multiple AI agents modifying code simultaneously
+- Lock-free version control (23x faster than Git)
+- Self-learning AI that improves from experience
+- Quantum-resistant security for future-proof protection
+- Automatic conflict resolution (87% success rate)
+- Pattern recognition and intelligent suggestions
+- Multi-agent coordination without blocking
 
 ## Quick Start
 
@@ -80,10 +80,10 @@ console.log('Expected Success:', (suggestion.expectedSuccessRate * 100).toFixed(
 ```
 
 **Validation (v2.3.1)**:
-- ✅ Tasks must be non-empty (max 10KB)
-- ✅ Success scores must be 0.0-1.0
-- ✅ Must have operations before finalizing
-- ✅ Contexts cannot be empty
+- Tasks must be non-empty (max 10KB)
+- Success scores must be 0.0-1.0
+- Must have operations before finalizing
+- Contexts cannot be empty
 
 ### 2. Pattern Discovery
 
@@ -498,21 +498,21 @@ try {
 ## Validation Rules (v2.3.1+)
 
 ### Task Description
-- ✅ Cannot be empty or whitespace-only
-- ✅ Maximum length: 10,000 bytes
-- ✅ Automatically trimmed
+- Cannot be empty or whitespace-only
+- Maximum length: 10,000 bytes
+- Automatically trimmed
 
 ### Success Score
-- ✅ Must be finite (not NaN or Infinity)
-- ✅ Must be between 0.0 and 1.0 (inclusive)
+- Must be finite (not NaN or Infinity)
+- Must be between 0.0 and 1.0 (inclusive)
 
 ### Operations
-- ✅ Must have at least one operation before finalizing
+- Must have at least one operation before finalizing
 
 ### Context
-- ✅ Cannot be empty
-- ✅ Keys cannot be empty or whitespace-only
-- ✅ Keys max 1,000 bytes, values max 10,000 bytes
+- Cannot be empty
+- Keys cannot be empty or whitespace-only
+- Keys max 1,000 bytes, values max 10,000 bytes
 
 ## Troubleshooting
 
@@ -625,7 +625,7 @@ async function agentSwarm(taskList) {
 ## Related Documentation
 
 - **NPM Package**: https://npmjs.com/package/agentic-jujutsu
-- **GitHub**: https://github.com/nokhodian/agentic-flow/tree/main/packages/agentic-jujutsu
+- **GitHub**: https://github.com/nokhodian/monomind
 - **Full README**: See package README.md
 - **Validation Guide**: docs/VALIDATION_FIXES_v2.3.1.md
 - **AgentDB Guide**: docs/AGENTDB_GUIDE.md
@@ -640,6 +640,6 @@ async function agentSwarm(taskList) {
 
 ---
 
-**Status**: ✅ Production Ready
+**Status**: Production Ready
 **License**: MIT
 **Maintained**: Active

package/.claude/skills/{v3-cli-modernization → cli-modernization}/SKILL.md

@@ -1,13 +1,22 @@
 ---
-name: "v1 CLI Modernization"
-description: "CLI modernization and hooks system enhancement for monomind v1. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation."
+name: cli-modernization
+description: "CLI modernization and hooks system enhancement for monomind. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation."
+triggers:
+  - modernize CLI
+  - CLI refactor
+  - interactive CLI
+  - add interactive prompts
+  - decompose index.ts
+  - command file too large
+  - CLI hooks integration
+  - CLI performance
 ---
 
 # CLI Modernization
 
 ## What This Skill Does
 
-Modernizes monomind v1 CLI with interactive prompts, intelligent command decomposition, enhanced hooks integration, performance optimization, and comprehensive workflow automation capabilities.
+Modernizes monomind CLI with interactive prompts, intelligent command decomposition, enhanced hooks integration, performance optimization, and comprehensive workflow automation capabilities.
 
 ## Quick Start
 
@@ -913,12 +922,12 @@ const cliImprovements = {
 };
 ```
 
-## Related v1 Skills
+## Related Skills
 
-- `v1-core-implementation` - Core domain integration
-- `v1-memory-unification` - Memory-backed command caching
-- `v1-swarm-coordination` - CLI swarm management integration
-- `v1-performance-optimization` - CLI performance monitoring
+- `core-implementation` - Core domain integration
+- `memory-unification` - Memory-backed command caching
+- `swarm-coordination` - CLI swarm management integration
+- `performance-optimization` - CLI performance monitoring
 
 ## Usage Examples
 

package/.claude/skills/{v3-core-implementation → core-implementation}/SKILL.md

@@ -1,13 +1,22 @@
 ---
-name: "v1 Core Implementation"
-description: "Core module implementation for monomind v1. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing."
+name: core-implementation
+description: "Core module implementation for monomind. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing."
+triggers:
+  - implement domain entity
+  - DDD implementation
+  - add repository
+  - create use case
+  - bounded context implementation
+  - domain model
+  - value object
+  - aggregate root
 ---
 
 # Core Implementation
 
 ## What This Skill Does
 
-Implements the core TypeScript modules for monomind v1 following Domain-Driven Design principles, clean architecture patterns, and modern TypeScript best practices with comprehensive test coverage.
+Implements the core TypeScript modules for monomind following Domain-Driven Design principles, clean architecture patterns, and modern TypeScript best practices with comprehensive test coverage.
 
 ## Quick Start
 
@@ -323,6 +332,14 @@ export class TaskStatus extends ValueObject<TaskStatusType> {
     return new TaskStatus("failed");
   }
 
+  static fromString(value: string): TaskStatus {
+    const valid: TaskStatusType[] = ["pending", "assigned", "in_progress", "completed", "failed"];
+    if (!valid.includes(value as TaskStatusType)) {
+      throw new Error(`Invalid TaskStatus value: "${value}"`);
+    }
+    return new TaskStatus(value as TaskStatusType);
+  }
+
   get value(): TaskStatusType {
     return this.props.value;
   }
@@ -365,6 +382,14 @@ export class Priority extends ValueObject<PriorityLevel> {
     return new Priority("critical");
   }
 
+  static fromString(value: string): Priority {
+    const valid: PriorityLevel[] = ["low", "medium", "high", "critical"];
+    if (!valid.includes(value as PriorityLevel)) {
+      throw new Error(`Invalid Priority value: "${value}"`);
+    }
+    return new Priority(value as PriorityLevel);
+  }
+
   get value(): PriorityLevel {
     return this.props.value;
   }
@@ -839,12 +864,12 @@ export class EntityCache<T extends Entity<any>> {
 - [ ] **Memory Efficiency**: <100MB heap usage for core domains
 - [ ] **Plugin Architecture**: Modular domain loading capability
 
-## Related v1 Skills
+## Related Skills
 
-- `v1-ddd-architecture` - DDD architectural design
-- `v1-mcp-optimization` - MCP server integration
-- `v1-memory-unification` - AgentDB repository integration
-- `v1-swarm-coordination` - Swarm domain implementation
+- `ddd-architecture` - DDD architectural design
+- `mcp-optimization` - MCP server integration
+- `memory-unification` - AgentDB repository integration
+- `swarm-coordination` - Swarm domain implementation
 
 ## Usage Examples
 

package/.claude/skills/{v3-ddd-architecture → ddd-architecture}/SKILL.md

@@ -1,6 +1,15 @@
 ---
-name: "v1 DDD Architecture"
-description: "Domain-Driven Design architecture for monomind v1. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern."
+name: ddd-architecture
+description: "Domain-Driven Design architecture for monomind. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern."
+triggers:
+  - god object
+  - decompose orchestrator
+  - DDD boundaries
+  - bounded context
+  - plugin architecture
+  - microkernel
+  - domain separation
+  - modular architecture
 ---
 
 # DDD Architecture
@@ -167,7 +176,7 @@ interface DomainPlugin {
 // Example: Swarm Coordination Plugin
 export class SwarmCoordinationPlugin implements DomainPlugin {
   name = "swarm-coordination";
-  version = "3.0.0";
+  version = process.env.npm_package_version ?? "1.0.0";
   dependencies = ["task-management", "session-management"];
 
   async initialize(kernel: MonomindKernel): Promise<void> {
@@ -330,23 +339,7 @@ export const taskManagementModule = {
 
 ### Phase 1: Extract Domain Services
 
-```typescript
-// Extract services from orchestrator.ts
-const extractionPlan = {
-  week1: [
-    "TaskManager → task-management domain",
-    "SessionManager → session-management domain",
-  ],
-  week2: [
-    "HealthMonitor → health-monitoring domain",
-    "LifecycleManager → lifecycle-management domain",
-  ],
-  week3: [
-    "EventCoordinator → event-coordination domain",
-    "Wire up domain events",
-  ],
-};
-```
+Start with the shared kernel (base entity, value object, aggregate root, domain event classes) before any bounded context. Then implement core domains in dependency order: task-management first (no cross-domain dependencies), followed by session-management and health-monitoring (which may subscribe to task events), and finally event-coordination as the integration layer that wires domain events across contexts.
 
 ### Phase 2: Implement Clean Interfaces
 
@@ -425,12 +418,12 @@ describe("Task Entity", () => {
 - [ ] **Event-Driven Communication**: Loose coupling between domains
 - [ ] **Test Coverage**: >90% domain logic coverage
 
-## Related v1 Skills
+## Related Skills
 
-- `v1-core-implementation` - Implementation of DDD domains
-- `v1-memory-unification` - AgentDB integration within bounded contexts
-- `v1-swarm-coordination` - Swarm coordination as domain plugin
-- `v1-performance-optimization` - Performance optimization across domains
+- `core-implementation` - Implementation of DDD domains
+- `memory-unification` - AgentDB integration within bounded contexts
+- `swarm-coordination` - Swarm coordination as domain plugin
+- `performance-optimization` - Performance optimization across domains
 
 ## Usage Examples