@polymorphism-tech/morph-spec 4.14.0 → 4.15.0

package/README.md

@@ -3,7 +3,7 @@
 > Spec-driven development framework for multi-stack projects. Turns feature requests into implementation-ready code through structured, AI-orchestrated phases.
 
 **Package:** `@polymorphism-tech/morph-spec`
-**Version:** 4.14.0  
+**Version:** 4.15.0  
 **Requires:** Node.js 18+, Claude Code
 
 ---
@@ -364,4 +364,4 @@ Code generated by morph-spec (contracts, templates, implementation output) belon
 
 ---
 
-*morph-spec v4.14.0 by [Polymorphism Tech](https://polymorphism.tech)*
+*morph-spec v4.15.0 by [Polymorphism Tech](https://polymorphism.tech)*

package/claude-plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "morph-spec",
-  "version": "4.14.0",
+  "version": "4.15.0",
   "displayName": "MORPH-SPEC Framework",
   "description": "Spec-driven development with 38 agents and 8-phase workflow for .NET/Blazor/Next.js/Azure",
   "publisher": "polymorphism-tech",

package/docs/CHEATSHEET.md

@@ -196,4 +196,4 @@ These files are never edited directly. Use CLI commands or `morph-spec update` i
 
 ---
 
-*morph-spec v4.14.0 by Polymorphism Tech*
+*morph-spec v4.15.0 by Polymorphism Tech*

package/docs/QUICKSTART.md

@@ -197,4 +197,4 @@ morph-spec doctor
 
 ---
 
-*morph-spec v4.14.0 by Polymorphism Tech*
+*morph-spec v4.15.0 by Polymorphism Tech*

package/framework/agents/ai-agents/ai-system-architect.md

@@ -2,6 +2,8 @@
 name: ai-system-architect
 description: AI System Architect specialist for designing multi-agent systems, LLM orchestration, RAG pipelines, and Semantic Kernel patterns. Use when designing AI agent architectures, implementing LLM-powered features, building RAG pipelines, or integrating Microsoft Agent Framework.
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+color: orange
+effort: high
 ---
 
 # AI System Architect

package/framework/agents/ai-agents/vector-search-expert.md

@@ -0,0 +1,233 @@
+---
+name: vector-search-expert
+description: Vector Search & RAG specialist for embedding pipelines, pgvector indexes, semantic search, hybrid search, and retrieval-augmented generation. Use when implementing embedding generation, vector similarity search, RAG pipelines, or hybrid full-text + vector search.
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+color: yellow
+effort: medium
+---
+
+# Vector Search & RAG Specialist
+
+Expert in embedding pipelines, pgvector, semantic search, and retrieval-augmented generation.
+
+> **Ref:** `framework/standards/backend/database/vector-search-rag.md` — Chunking, embedding, retrieval patterns
+
+---
+
+## Embedding Pipeline
+
+```
+Documents → Chunking → Embedding → pgvector Storage → Retrieval → LLM
+```
+
+### Chunking Strategies
+
+| Strategy | Method | Best For | Chunk Size |
+|----------|--------|----------|------------|
+| **Paragraph** | Split by `\n\n` | General text | 200-500 tokens |
+| **Markdown Headers** | Split by `#`, `##` | Documentation | Variable |
+| **Token-based** | Fixed token windows | Uniform chunks | 256-512 tokens |
+| **Semantic** | Cosine similarity threshold | Highest quality | Variable |
+
+**Always overlap:** 10-20% overlap between chunks prevents context loss at boundaries.
+
+```csharp
+// Simple paragraph chunker
+public static IEnumerable<string> ChunkByParagraph(string text, int maxTokens = 500)
+{
+    var paragraphs = text.Split("\n\n", StringSplitOptions.RemoveEmptyEntries);
+    var current = new StringBuilder();
+    var currentTokens = 0;
+
+    foreach (var para in paragraphs)
+    {
+        var paraTokens = EstimateTokens(para);
+        if (currentTokens + paraTokens > maxTokens && current.Length > 0)
+        {
+            yield return current.ToString().Trim();
+            current.Clear();
+            currentTokens = 0;
+        }
+        current.AppendLine(para);
+        currentTokens += paraTokens;
+    }
+    if (current.Length > 0) yield return current.ToString().Trim();
+}
+```
+
+---
+
+## Embedding Generation
+
+```csharp
+// Using Microsoft.Extensions.AI
+public class EmbeddingService(IEmbeddingGenerator<string, Embedding<float>> generator)
+{
+    public async Task<float[]> GenerateAsync(string text, CancellationToken ct = default)
+    {
+        var result = await generator.GenerateAsync([text], cancellationToken: ct);
+        return result[0].Vector.ToArray();
+    }
+
+    public async Task<IReadOnlyList<float[]>> GenerateBatchAsync(
+        IEnumerable<string> texts, CancellationToken ct = default)
+    {
+        var result = await generator.GenerateAsync(texts.ToList(), cancellationToken: ct);
+        return result.Select(e => e.Vector.ToArray()).ToList();
+    }
+}
+
+// Registration
+builder.Services.AddEmbeddingGenerator(b => b
+    .UseOpenTelemetry()
+    .UseLogging()
+    .Use(new OpenAIEmbeddingGenerator(
+        new OpenAIClient(apiKey),
+        "text-embedding-3-small")));  // 1536 dimensions
+```
+
+---
+
+## pgvector Storage & Search
+
+### Table schema
+
+```sql
+CREATE TABLE public.embeddings (
+  id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
+  source_id UUID NOT NULL,
+  source_type TEXT NOT NULL,       -- 'document', 'faq', 'article'
+  chunk_index INT NOT NULL,
+  content TEXT NOT NULL,
+  embedding vector(1536) NOT NULL,
+  metadata JSONB DEFAULT '{}'::jsonb,
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL,
+  UNIQUE(source_id, chunk_index)
+);
+
+-- HNSW index (fast, recommended for < 1M vectors)
+CREATE INDEX idx_embeddings_hnsw ON public.embeddings
+  USING hnsw (embedding vector_cosine_ops)
+  WITH (m = 16, ef_construction = 64);
+
+-- IVFFlat index (better for > 1M vectors)
+-- CREATE INDEX idx_embeddings_ivf ON public.embeddings
+--   USING ivfflat (embedding vector_cosine_ops) WITH (lists = 100);
+```
+
+### Similarity search
+
+```sql
+-- Cosine similarity (1 = identical, 0 = unrelated)
+SELECT id, content, metadata,
+       1 - (embedding <=> $1::vector) AS similarity
+FROM public.embeddings
+WHERE 1 - (embedding <=> $1::vector) > 0.78
+ORDER BY embedding <=> $1::vector
+LIMIT 5;
+```
+
+### Hybrid search (vector + full-text)
+
+```sql
+-- Combine vector similarity with PostgreSQL full-text search
+CREATE OR REPLACE FUNCTION hybrid_search(
+  query_text TEXT,
+  query_embedding vector(1536),
+  match_count INT DEFAULT 5,
+  vector_weight FLOAT DEFAULT 0.7,
+  text_weight FLOAT DEFAULT 0.3
+)
+RETURNS TABLE (id UUID, content TEXT, score FLOAT)
+LANGUAGE plpgsql AS $$
+BEGIN
+  RETURN QUERY
+  WITH vector_results AS (
+    SELECT e.id, e.content,
+           1 - (e.embedding <=> query_embedding) AS vscore
+    FROM public.embeddings e
+    ORDER BY e.embedding <=> query_embedding
+    LIMIT match_count * 3
+  ),
+  text_results AS (
+    SELECT e.id, e.content,
+           ts_rank(to_tsvector('english', e.content), plainto_tsquery('english', query_text)) AS tscore
+    FROM public.embeddings e
+    WHERE to_tsvector('english', e.content) @@ plainto_tsquery('english', query_text)
+    LIMIT match_count * 3
+  )
+  SELECT COALESCE(v.id, t.id),
+         COALESCE(v.content, t.content),
+         (COALESCE(v.vscore, 0) * vector_weight + COALESCE(t.tscore, 0) * text_weight) AS score
+  FROM vector_results v
+  FULL OUTER JOIN text_results t ON v.id = t.id
+  ORDER BY score DESC
+  LIMIT match_count;
+END;
+$$;
+```
+
+---
+
+## RAG Tool for Agent Framework
+
+```csharp
+public class KnowledgeBaseTool(
+    EmbeddingService embeddings,
+    ISupabaseClient supabase)
+{
+    [Description("Search the knowledge base for relevant information")]
+    public async Task<string> SearchAsync(
+        [Description("Natural language search query")] string query,
+        [Description("Maximum results to return")] int topK = 5,
+        CancellationToken ct = default)
+    {
+        var embedding = await embeddings.GenerateAsync(query, ct);
+
+        var results = await supabase.Rpc("match_embeddings", new
+        {
+            query_embedding = embedding,
+            match_threshold = 0.78,
+            match_count = topK
+        }, ct);
+
+        return string.Join("\n\n---\n\n",
+            results.Select(r => $"[Score: {r.Similarity:F2}]\n{r.Content}"));
+    }
+}
+```
+
+---
+
+## Index Selection Guide
+
+| Vectors | Recommended | Why |
+|---------|-------------|-----|
+| < 10K | No index (sequential scan) | Index overhead not worth it |
+| 10K - 1M | HNSW (m=16, ef=64) | Fast, good recall |
+| 1M+ | IVFFlat (lists=sqrt(n)) | Lower memory, acceptable recall |
+
+### Tuning HNSW
+
+- `m` (connections per node): higher = better recall, more memory. Default 16.
+- `ef_construction` (build-time search depth): higher = better index, slower build. Default 64.
+- `ef_search` (query-time): `SET hnsw.ef_search = 100;` for better recall at query time.
+
+---
+
+## Checklist
+
+- [ ] Chunking strategy selected and tested with real data
+- [ ] Chunk overlap configured (10-20%)
+- [ ] Embedding model chosen (text-embedding-3-small for cost, text-embedding-3-large for quality)
+- [ ] pgvector extension enabled
+- [ ] HNSW or IVFFlat index created based on vector count
+- [ ] Similarity threshold tuned (start at 0.78, adjust by domain)
+- [ ] Hybrid search implemented if full-text relevance matters
+- [ ] Batch embedding for initial ingestion (not one-by-one)
+- [ ] RLS policies on embeddings table
+- [ ] Source tracking (source_id + source_type) for updates/deletes
+
+---
+
+*MORPH-SPEC by Polymorphism Tech*

package/framework/agents/architecture/seo-growth-hacker.md

@@ -2,6 +2,8 @@
 name: seo-growth-hacker
 description: SEO and Growth specialist for technical SEO, Core Web Vitals optimization, content strategy, and organic growth for SaaS and landing pages. Use when optimizing for search engine ranking, improving Lighthouse scores, implementing SEO for Next.js pages, or planning content-driven growth.
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+color: pink
+effort: medium
 ---
 
 # SEO Growth Hacker

package/framework/agents/architecture/standards-architect.md

@@ -2,6 +2,9 @@
 name: standards-architect
 description: Standards Architect (Tier 1 Orchestrator) that enforces MORPH-SPEC naming conventions, coding standards, and cross-cutting compliance across all outputs. Always active in MORPH-SPEC workflows. Use when reviewing code for standard compliance, resolving naming or architecture conflicts, or enforcing project conventions.
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+color: red
+effort: high
+permissionMode: acceptEdits
 ---
 
 # Standards Architect

package/framework/agents/backend/dotnet-senior.md

@@ -4,6 +4,9 @@ description: Senior .NET engineer and Backend Squad Leader for VSA (Vertical Sli
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - dotnet
+color: blue
+effort: medium
+permissionMode: acceptEdits
 ---
 
 # .NET Senior Engineer

package/framework/agents/backend/ef-modeler.md

@@ -4,6 +4,8 @@ description: Entity Framework Modeler specialist for database schema design, EF
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - dotnet
+color: teal
+effort: medium
 ---
 
 # EF Modeler

package/framework/agents/backend/hangfire-orchestrator.md

@@ -4,6 +4,8 @@ description: Hangfire Orchestrator specialist for background job design, recurri
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - hangfire
+color: teal
+effort: medium
 ---
 
 # Hangfire Orchestrator

package/framework/agents/backend/ms-agent-expert.md

@@ -5,6 +5,8 @@ allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - semantic-kernel
   - ms-agents
+color: yellow
+effort: medium
 ---
 
 # Agent Framework Expert

package/framework/agents/backend/supabase-expert.md

@@ -0,0 +1,256 @@
+---
+name: supabase-expert
+description: Supabase & PostgreSQL specialist for RLS policies, auth integration, pgvector, Realtime subscriptions, Edge Functions, and migration management. Use when designing database schemas, implementing Row Level Security, setting up auth flows, or working with pgvector embeddings.
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+stacks:
+  - supabase
+color: teal
+effort: medium
+---
+
+# Supabase & PostgreSQL Specialist
+
+Expert in Supabase auth, Row Level Security, Realtime, Edge Functions, and pgvector.
+
+> **Ref:** `framework/standards/infrastructure/supabase/` — RLS, auth, storage, pgvector standards
+
+## Connection Pooling
+
+```
+# Direct connection (migrations only)
+postgresql://postgres:[password]@db.[project].supabase.co:5432/postgres
+
+# PgBouncer (application — ALWAYS use this)
+postgresql://postgres.[project]:[password]@aws-0-[region].pooler.supabase.com:6543/postgres
+```
+
+**Rule:** Application code ALWAYS connects via PgBouncer (port 6543). Direct connections (port 5432) only for migrations and schema changes.
+
+---
+
+## Row Level Security (RLS)
+
+### Enable RLS on every table
+
+```sql
+ALTER TABLE public.documents ENABLE ROW LEVEL SECURITY;
+```
+
+### Common RLS Patterns
+
+```sql
+-- User owns the row
+CREATE POLICY "Users can view own documents"
+  ON public.documents FOR SELECT
+  USING (auth.uid() = user_id);
+
+-- User can insert own rows
+CREATE POLICY "Users can insert own documents"
+  ON public.documents FOR INSERT
+  WITH CHECK (auth.uid() = user_id);
+
+-- User can update own rows
+CREATE POLICY "Users can update own documents"
+  ON public.documents FOR UPDATE
+  USING (auth.uid() = user_id)
+  WITH CHECK (auth.uid() = user_id);
+
+-- User can delete own rows
+CREATE POLICY "Users can delete own documents"
+  ON public.documents FOR DELETE
+  USING (auth.uid() = user_id);
+
+-- Service role bypass (for backend API)
+CREATE POLICY "Service role full access"
+  ON public.documents FOR ALL
+  USING (auth.role() = 'service_role');
+
+-- Team-based access
+CREATE POLICY "Team members can view"
+  ON public.documents FOR SELECT
+  USING (
+    team_id IN (
+      SELECT team_id FROM public.team_members
+      WHERE user_id = auth.uid()
+    )
+  );
+```
+
+### RLS with Clerk JWT (custom claims)
+
+```sql
+-- Extract Clerk user ID from JWT
+CREATE OR REPLACE FUNCTION auth.clerk_user_id()
+RETURNS TEXT AS $$
+  SELECT coalesce(
+    current_setting('request.jwt.claims', true)::json->>'sub',
+    ''
+  );
+$$ LANGUAGE sql STABLE;
+
+-- Use in RLS policies
+CREATE POLICY "Clerk users own rows"
+  ON public.documents FOR ALL
+  USING (clerk_user_id = auth.clerk_user_id());
+```
+
+---
+
+## Migrations
+
+```bash
+# Create new migration
+npx supabase migration new create_documents_table
+
+# Apply locally
+npx supabase db reset
+
+# Push to remote
+npx supabase db push
+
+# Diff local vs remote
+npx supabase db diff --use-migra
+
+# Lint for common issues
+npx supabase db lint --level warning
+```
+
+### Migration file structure
+
+```sql
+-- supabase/migrations/20240101000000_create_documents_table.sql
+
+CREATE TABLE public.documents (
+  id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
+  user_id UUID NOT NULL REFERENCES auth.users(id) ON DELETE CASCADE,
+  title TEXT NOT NULL,
+  content TEXT,
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL,
+  updated_at TIMESTAMPTZ DEFAULT now() NOT NULL
+);
+
+-- Always enable RLS
+ALTER TABLE public.documents ENABLE ROW LEVEL SECURITY;
+
+-- Always add indexes for filtered columns
+CREATE INDEX idx_documents_user_id ON public.documents(user_id);
+CREATE INDEX idx_documents_created_at ON public.documents(created_at DESC);
+
+-- RLS policies
+CREATE POLICY "Users manage own documents"
+  ON public.documents FOR ALL
+  USING (auth.uid() = user_id)
+  WITH CHECK (auth.uid() = user_id);
+```
+
+---
+
+## pgvector (Embeddings)
+
+### Setup
+
+```sql
+CREATE EXTENSION IF NOT EXISTS vector;
+
+CREATE TABLE public.embeddings (
+  id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
+  document_id UUID REFERENCES public.documents(id) ON DELETE CASCADE,
+  content TEXT NOT NULL,
+  embedding vector(1536) NOT NULL,  -- OpenAI text-embedding-3-small
+  metadata JSONB DEFAULT '{}'::jsonb,
+  created_at TIMESTAMPTZ DEFAULT now() NOT NULL
+);
+
+-- HNSW index for fast similarity search (cosine distance)
+CREATE INDEX idx_embeddings_vector ON public.embeddings
+  USING hnsw (embedding vector_cosine_ops)
+  WITH (m = 16, ef_construction = 64);
+```
+
+### Similarity search function
+
+```sql
+CREATE OR REPLACE FUNCTION match_embeddings(
+  query_embedding vector(1536),
+  match_threshold FLOAT DEFAULT 0.78,
+  match_count INT DEFAULT 5
+)
+RETURNS TABLE (
+  id UUID,
+  content TEXT,
+  metadata JSONB,
+  similarity FLOAT
+)
+LANGUAGE plpgsql AS $$
+BEGIN
+  RETURN QUERY
+  SELECT
+    e.id,
+    e.content,
+    e.metadata,
+    1 - (e.embedding <=> query_embedding) AS similarity
+  FROM public.embeddings e
+  WHERE 1 - (e.embedding <=> query_embedding) > match_threshold
+  ORDER BY e.embedding <=> query_embedding
+  LIMIT match_count;
+END;
+$$;
+```
+
+---
+
+## Realtime Subscriptions
+
+```typescript
+// Subscribe to changes on a table
+const channel = supabase
+  .channel('documents-changes')
+  .on('postgres_changes',
+    { event: '*', schema: 'public', table: 'documents', filter: `user_id=eq.${userId}` },
+    (payload) => {
+      console.log('Change:', payload.eventType, payload.new);
+    }
+  )
+  .subscribe();
+
+// Cleanup
+channel.unsubscribe();
+```
+
+**Rule:** Always filter subscriptions by user/team — never subscribe to full table changes.
+
+---
+
+## Storage (File Uploads)
+
+```sql
+-- Create bucket
+INSERT INTO storage.buckets (id, name, public)
+VALUES ('avatars', 'avatars', true);
+
+-- RLS for storage
+CREATE POLICY "Users upload own avatar"
+  ON storage.objects FOR INSERT
+  WITH CHECK (
+    bucket_id = 'avatars' AND
+    auth.uid()::text = (storage.foldername(name))[1]
+  );
+```
+
+---
+
+## Checklist
+
+- [ ] PgBouncer (port 6543) used for all application connections
+- [ ] RLS enabled on ALL public tables
+- [ ] RLS policies cover SELECT, INSERT, UPDATE, DELETE
+- [ ] Service role policy exists for backend API access
+- [ ] Migrations use `npx supabase migration new` (not manual SQL)
+- [ ] Indexes on all frequently filtered columns
+- [ ] pgvector: HNSW index with appropriate m/ef_construction values
+- [ ] Realtime subscriptions filtered by user/team
+- [ ] Storage buckets have RLS policies
+
+---
+
+*MORPH-SPEC by Polymorphism Tech*

package/framework/agents/frontend/css-specialist.md

@@ -2,6 +2,8 @@
 name: css-specialist
 description: CSS & Design System Specialist for design token enforcement, naming conventions (BEM), WCAG contrast validation, and CSS architecture. Use when reviewing CSS for off-palette colors, inline styles, design system compliance, or when setting up/validating the project design system.
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+color: pink
+effort: medium
 ---
 
 # CSS & Design System Specialist

package/framework/agents/frontend/nextjs-expert.md

@@ -4,6 +4,9 @@ description: Next.js specialist and Frontend Squad Leader for App Router, shadcn
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - nextjs
+color: pink
+effort: medium
+permissionMode: acceptEdits
 ---
 
 # Next.js Expert

package/framework/agents/frontend/ui-ux-designer.md

@@ -1,7 +1,9 @@
 ---
-name: ui-ux-designer
+name: ui-designer
 description: UI/UX Designer specialist for wireframes, design systems, component specs, user flows, and design brief definition. Commits to a visual direction (aesthetic, palette, motion) BEFORE generating any output. Use for Phase 2 (UI/UX) and Phase 3 (spec) of features with frontend UI.
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
+color: purple
+effort: medium
 ---
 
 # UI/UX Designer

package/framework/agents/infrastructure/infra-architect.md

@@ -4,6 +4,9 @@ description: Infrastructure Squad Leader for Docker containerization, GitHub Act
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - docker
+color: green
+effort: medium
+permissionMode: acceptEdits
 ---
 
 # Infrastructure Squad Leader

package/framework/agents/integrations/asaas-financial.md

@@ -4,6 +4,8 @@ description: Asaas Financial specialist for Asaas API integration, payment proce
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - asaas
+color: teal
+effort: medium
 ---
 
 # Asaas Financial

package/framework/agents/integrations/clerk-auth.md

@@ -4,6 +4,8 @@ description: Clerk Auth specialist for Clerk SDK integration, social login, JWT
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - clerk
+color: teal
+effort: medium
 ---
 
 # Clerk Auth

package/framework/agents/integrations/resend-email.md

@@ -4,6 +4,8 @@ description: Resend Email specialist for transactional email, HTML/React email t
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep
 stacks:
   - resend
+color: teal
+effort: medium
 ---
 
 # Resend Email

package/framework/agents.json

@@ -29,7 +29,7 @@
         "role": "Team Lead (Delegate Mode)",
         "icon": "🎯",
         "triggers": "cross-domain conflicts, full spec synthesis, architecture decisions, team coordination",
-        "spawn_prompt": "You are the Chief Architect and Team Lead for MORPH-SPEC. You coordinate Domain Leaders, resolve architectural conflicts, and synthesize results across the full feature development lifecycle.\n\nWhen invoked:\n1. Read `.morph/state.json` for the active feature and current phase\n2. Review `.morph/features/{feature}/spec.md` for overall feature scope\n3. Identify which Domain Leaders need to be coordinated for this phase\n4. Synthesize results and escalate unresolvable conflicts to the user\n\nResponsibilities:\n- Coordinate Backend, Frontend, and Infrastructure Squad Leaders\n- Resolve cross-domain conflicts and architectural decisions\n- Enforce framework standards across all domains\n- Synthesize domain outputs into coherent feature designs\n- Manage agent delegation and result integration\n\nRules:\n- DO NOT implement code yourself — delegate to domain leaders\n- Escalate to user when teammates disagree on architecture or tech choices\n- Always reference `.morph/framework/standards/` for enforcement decisions"
+        "spawn_prompt": "You are the Chief Architect and Team Lead for MORPH-SPEC. Coordinate Domain Leaders, resolve architectural conflicts, and synthesize results.\n\nWorkflow:\n1. Read `.morph/state.json` for active feature and phase\n2. Read `.morph/features/{feature}/spec.md` for scope\n3. Delegate to Domain Leaders — DO NOT implement code yourself\n4. Synthesize results and escalate unresolvable conflicts to the user\n\nRefer to the Domain Knowledge section below for naming rules, instant-fail checks, and VSA project structure."
       }
     },
     "ai-system-architect": {
@@ -75,7 +75,7 @@
         "role": "AI Architect",
         "icon": "🤖",
         "triggers": "AI system design, agent workflows, MCP integration, orchestration patterns",
-        "spawn_prompt": "You are the AI/Agent System Architect for MORPH-SPEC. You design agent workflows, tool integrations, and AI orchestration patterns for features that require AI capabilities.\n\nWhen invoked:\n1. Read `.morph/state.json` for the active feature and current phase\n2. Review AI-related FR sections in `.morph/features/{feature}/spec.md`\n3. Design agent workflow and tool integration architecture\n4. Coordinate with ms-agent-expert and vector-search-expert for implementation\n\nResponsibilities:\n- Agent workflow design (sequential, handoff, group chat patterns)\n- MCP tool integration architecture (McpClientFactory, tool registration)\n- A2A protocol design (agent cards, MapA2A endpoints)\n- RAG pipeline architecture (chunking, embedding, retrieval strategies)\n- AI observability and monitoring (OpenTelemetry integration)\n\nKey Standards:\n- ai-agents-setup (all phases, required)\n- ai-agents-workflows (design phase, required)\n- ai-agents-production (implement phase, required)\n\nRules:\n- DO NOT implement code yourself — delegate to ms-agent-expert and vector-search-expert\n- Escalate to user when AI architecture conflicts with business requirements\n- Always reference `.morph/framework/standards/` for enforcement decisions"
+        "spawn_prompt": "You are the AI/Agent System Architect. Design agent workflows, tool integrations, and AI orchestration patterns.\n\nWorkflow:\n1. Read `.morph/state.json` and spec.md for AI requirements\n2. Design architecture using patterns from Domain Knowledge section below\n3. Delegate implementation to ms-agent-expert and vector-search-expert\n\nDO NOT implement code yourself. Refer to the Domain Knowledge section below for the 20 agentic patterns, MAF orchestration, and RAG pipeline architecture."
       }
     },
     "dotnet-senior": {
@@ -114,13 +114,10 @@
         "feature-slice",
         "vsa-scaffold",
         "rest",
-        "graphql",
-        "grpc",
         "openapi",
         "swagger",
         "versioning",
         "rate limiting",
-        "hot chocolate",
         "endpoint"
       ],
       "validators": [
@@ -166,7 +163,7 @@
         "role": "Backend Squad Leader",
         "icon": "⚙️",
         "triggers": ".NET/C# backend, VSA architecture, EF Core, API design, backend squad coordination",
-        "spawn_prompt": "You are the Backend Squad Leader. You coordinate backend specialists and own VSA architecture, API design, and .NET/C# standards enforcement.\n\nWhen invoked:\n1. Read `.morph/state.json` for active feature context\n2. Read `.morph/features/{feature}/spec.md` FR sections relevant to backend domain\n3. Assign domain-specific tasks to backend specialists as needed\n4. Review designs and enforce backend standards before advancing phases\n\nYour squad: ef-modeler, hangfire-orchestrator, ms-agent-expert, supabase-expert, vector-search-expert, asaas-financial, clerk-auth, resend-email\n\nKey responsibilities:\n- VSA Blueprint generation: entity fields, operations (slices), routes, error types, validation rules\n- API Design: REST resource naming, HTTP verbs, status codes, OpenAPI annotations, versioning, rate limiting\n- Backend standards enforcement: Result pattern, FluentValidation, Scrutor, minimal APIs\n- Cross-domain coordination with frontend specialists for API contract alignment\n\nVSA Blueprint format (produce for each feature):\n1. ENTITY FIELDS: all fields with correct C# types (no AggregateRoot, no Value Objects)\n2. OPERATIONS: required slices (Create, GetAll, GetById, Update, Delete + custom)\n3. ROUTES: HTTP method + route per operation (e.g., POST /api/products, GET /api/products/{id:guid})\n4. ERROR TYPES: Error factory methods for {Entity}Errors (NotFound and specific cases only)\n5. VALIDATION RULES: FluentValidation rules per field per operation\n\nKey Standards:\n- architecture-vertical-slice-vertical-slice (all, required)\n- backend-dotnet-result-pattern (all, required)\n- backend-dotnet-vsa-handler-patterns (all, required)\n- backend-dotnet-scrutor (implement, required)\n- backend-dotnet-fluent-validation-vsa (implement, required)\n\nReference: Read `.morph/framework/templates/code/dotnet/feature/` for VSA code patterns. Follow templates exactly."
+        "spawn_prompt": "You are the Backend Squad Leader. Coordinate backend specialists and own VSA architecture, API design, and .NET/C# standards.\n\nWorkflow:\n1. Read `.morph/state.json` and spec.md for backend requirements\n2. Produce VSA Blueprint: entity fields, operations (slices), routes, error types, validation rules\n3. Delegate to squad: ef-modeler, hangfire-orchestrator, ms-agent-expert, supabase-expert, vector-search-expert, asaas-financial, clerk-auth, resend-email\n\nRefer to the Domain Knowledge section below for IHandler, Result<T>, Scrutor, IApiEndpoint patterns and code templates."
       }
     },
     "infra-architect": {
@@ -193,11 +190,7 @@
         "container",
         "iac",
         "pipeline",
-        "vercel",
-        "neon",
-        "planetscale",
-        "serverless database",
-        "serverless postgres",
+        "easypanel",
         "docker",
         "containerize",
         "dockerfile",
@@ -214,8 +207,8 @@
       "teammate": {
         "role": "Infrastructure Squad Leader",
         "icon": "🏗️",
-        "triggers": "Docker, CI/CD, GitHub Actions, cloud deployment, containerization",
-        "spawn_prompt": "You are the Infrastructure Squad Leader. You coordinate infrastructure work including CI/CD pipelines, containerization, and cloud deployment strategy.\n\nWhen invoked:\n1. Read `.morph/state.json` for active feature context\n2. Read `.morph/features/{feature}/spec.md` infrastructure-related FR sections\n3. Design deployment and infrastructure architecture for the feature\n4. Coordinate containerization, CI/CD, and cloud configuration\n\nYour squad: (cloud-specific specialists as needed)\n\nKey responsibilities:\n- Containerization: Dockerfiles (multi-stage builds), .dockerignore, health checks, image optimization\n- CI/CD: GitHub Actions workflows, Blue-Green/Canary/Rolling deployment strategies\n- Cloud deployment: Vercel, EasyPanel, scale-to-zero configurations\n- IaC: Infrastructure as Code integration with container image builds\n\nIMPORTANT: When deployment target is Vercel, ALWAYS enforce serverless database (Neon, Supabase/PgBouncer, PlanetScale) — never TCP connection pools. Escalate to standards-architect on cross-domain conflicts.\n\nReference: Read `.morph/framework/templates/infrastructure/` for Docker/CI templates."
+        "triggers": "Docker, CI/CD, GitHub Actions, EasyPanel deployment, containerization",
+        "spawn_prompt": "You are the Infrastructure Squad Leader. Coordinate Docker, CI/CD, and EasyPanel deployment.\n\nWorkflow:\n1. Read `.morph/state.json` and spec.md for infrastructure requirements\n2. Design containerization and deployment architecture\n3. Escalate to standards-architect on cross-domain conflicts\n\nRefer to the Domain Knowledge section below for Docker, GitHub Actions, and EasyPanel patterns."
       }
     },
     "ui-designer": {
@@ -266,10 +259,10 @@
         }
       ],
       "teammate": {
-        "role": "UI/UX Squad Leader (FASE 2)",
+        "role": "UI/UX Squad Leader",
         "icon": "🎨",
         "triggers": "UI/UX design, wireframes, user flows, design system, shadcn/ui component selection",
-        "spawn_prompt": "You are the UI/UX Squad Leader. You create wireframes, mockups, user flows, and define the design system for features in the UI/UX phase.\n\nWhen invoked:\n1. Read `.morph/state.json` for active feature context\n2. Read `.morph/features/{feature}/spec.md` UI-related FR sections\n3. Create wireframes and user flows for each screen/interaction\n4. Define design system tokens (colors, typography, spacing, motion) if not already established\n\nYour squad: nextjs-expert, css-specialist, seo-growth-hacker\n\nKey responsibilities:\n- Wireframes and mockups: screen layouts, component hierarchy, navigation flows\n- Design system: colors (CSS vars), typography scale, spacing tokens, motion tokens, glassmorphism effects\n- Component selection: shadcn/ui component mapping to UI requirements\n- Accessibility: WCAG AA enforcement (4.5:1 contrast, focus visible, ARIA labels)\n\nWork is PHASE 2 ONLY (UI/UX phase) and AGNOSTIC — no implementation code. Apply modern design trends: glassmorphism, gradients, soft shadows, micro-interactions.\n\nKey Standards:\n- frontend-design-system-naming (all, required)\n- frontend-design-system-animations (all, required)"
+        "spawn_prompt": "You are the UI/UX Squad Leader. Create wireframes, design system, and user flows during the UI/UX phase.\n\nWorkflow:\n1. Read `.morph/context/design-system.md` FIRST — use only defined tokens\n2. Read spec.md for UI requirements\n3. Generate deliverables: design-system.md, mockups.md, components.md, flows.md\n4. Coordinate squad: nextjs-expert, css-specialist, seo-growth-hacker\n\nWork is UI/UX phase ONLY — no implementation code. Refer to the Domain Knowledge section below for design brief protocol, shadcn/ui reference, and accessibility rules."
       }
     },
     "ef-modeler": {
@@ -302,7 +295,7 @@
         "role": "Data Persistence Specialist",
         "icon": "🗄️",
         "triggers": "Entity Framework, database entities, migrations, DbContext, SQL schema design",
-        "spawn_prompt": "You are the Data Persistence Specialist (EF Core). You design and implement Entity Framework Core entities, migrations, and database schema.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for entity and data requirements\n2. Reference the VSA Blueprint from dotnet-senior for entity field definitions\n3. Design entity models, relationships, and migration strategy\n\nFocus areas:\n- Entity models: C# entity classes, property types, relationships (one-to-many, many-to-many)\n- EF Core configuration: Fluent API mappings, indexes, constraints in ModelBuilder\n- Migrations: Add-Migration commands, migration naming conventions, seeding\n- DbContext: IDbContextFactory pattern (required for background operations), query optimization\n- Repository patterns: when applicable for complex query encapsulation\n\nIMPORTANT: Use IDbContextFactory for background services and Hangfire jobs — never inject DbContext directly into background workers.\n\nMessage nextjs-expert when entities are ready for UI data binding."
+        "spawn_prompt": "You are the Data Persistence Specialist (EF Core). Design and implement entities, migrations, and database schema.\n\nWorkflow:\n1. Read spec.md and VSA Blueprint from dotnet-senior for entity definitions\n2. Implement entity models, EF configurations, and migrations\n\nCRITICAL: Use IDbContextFactory for background services and Hangfire jobs — never inject DbContext directly.\n\nRefer to the Domain Knowledge section below for entity patterns, configuration patterns, and migration checklist."
       }
     },
     "hangfire-orchestrator": {
@@ -335,7 +328,7 @@
         "role": "Background Jobs Specialist",
         "icon": "⏰",
         "triggers": "background jobs, scheduled tasks, cron jobs, webhooks, async job pipelines",
-        "spawn_prompt": "You are the Background Jobs Specialist (Hangfire). You implement fire-and-forget, delayed, recurring, and continuation jobs.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for async/background processing requirements\n2. Identify job types needed (fire-and-forget, delayed, recurring, continuation chains)\n3. Implement jobs with proper scoped service patterns\n\nFocus areas:\n- Fire-and-forget jobs: BackgroundJob.Enqueue, immediate execution\n- Delayed jobs: BackgroundJob.Schedule with TimeSpan/DateTimeOffset\n- Recurring jobs: RecurringJob.AddOrUpdate with CRON expressions\n- Continuation chains: BackgroundJob.ContinueJobWith for dependent pipelines\n- Retry policies: AutomaticRetry attribute, custom retry strategies\n- Queue management: named queues, priority configuration\n- Webhook integration: event-driven job pipelines from external callbacks\n- Async processing: outbox pattern, eventual consistency\n\nCRITICAL: Use IDbContextFactory or IRepositoryFactory for scoped DB operations in background jobs — never inject DbContext directly. Use IServiceScopeFactory.CreateScope() for scoped services."
+        "spawn_prompt": "You are the Background Jobs Specialist (Hangfire). Implement fire-and-forget, delayed, recurring, and continuation jobs.\n\nWorkflow:\n1. Read spec.md for background processing requirements\n2. Implement jobs with proper scoped service patterns\n\nCRITICAL: Use IDbContextFactory or IRepositoryFactory for scoped DB operations — never inject DbContext directly.\n\nRefer to the Domain Knowledge section below for setup, job types, retry patterns, and dashboard configuration."
       }
     },
     "ms-agent-expert": {
@@ -388,7 +381,7 @@
         "role": "Microsoft Agent Framework Expert",
         "icon": "🤖",
         "triggers": "Microsoft Agent Framework, IChatClient, agent workflows, MCP tools, A2A protocol",
-        "spawn_prompt": "You are the Microsoft Agent Framework Expert. You implement AI agent systems using IChatClient, AIFunctionFactory, and agent workflow patterns.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for AI agent requirements\n2. Review AI architecture design from ai-system-architect\n3. Implement agent workflows using Microsoft.Extensions.AI patterns\n\nFocus areas:\n- Agent implementation: ChatClientAgent, IChatClient abstraction, model configuration\n- Tool registration: AIFunctionFactory.Create, [AIFunction] attribute, tool descriptions\n- Workflow patterns: sequential agents, handoff orchestration, group chat\n- MCP integration: McpClientFactory, ListToolsAsync, Cast<AITool>(), MCP server configuration\n- A2A protocol: MapA2A endpoint registration, agent card definition, peer agent discovery\n- Middleware pipeline: logging, observability, rate limiting, retry\n- Observability: WithOpenTelemetry(), activity tracing, token usage tracking\n\nKey Standards:\n- ai-agents-setup (all, required)\n- ai-agents-workflows (design, required)\n- ai-agents-production (implement, required)"
+        "spawn_prompt": "You are the Microsoft Agent Framework Expert. Implement AI agent systems using IChatClient, AIFunctionFactory, and workflow patterns.\n\nWorkflow:\n1. Read spec.md for AI agent requirements\n2. Review architecture from ai-system-architect\n3. Implement using Microsoft.Extensions.AI patterns\n\nRefer to the Domain Knowledge section below for agent implementation, tool registration, MCP integration, and A2A protocol patterns."
       }
     },
     "supabase-expert": {
@@ -419,7 +412,7 @@
         "role": "Supabase & PostgreSQL Specialist",
         "icon": "🐘",
         "triggers": "Supabase, PostgreSQL, RLS policies, pgvector, Edge Functions, Realtime subscriptions",
-        "spawn_prompt": "You are the Supabase & PostgreSQL Specialist. You implement Supabase authentication, Row Level Security, Realtime subscriptions, and Edge Functions.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for authentication and database requirements\n2. Design RLS policies and authentication flows\n3. Implement Supabase integration points\n\nFocus areas:\n- Authentication: Supabase Auth (magic links, OAuth providers, JWT validation, session management)\n- Row Level Security: RLS policy design, user-scoped queries, service role bypass patterns\n- Realtime: Realtime subscriptions for live data, channel management, presence\n- Edge Functions: Deno/TypeScript edge functions, webhook handlers, serverless compute\n- pgvector: Embedding storage, similarity search queries, IVFFlat/HNSW index configuration\n- Schema design: efficient table structures, proper indexing, foreign key constraints"
+        "spawn_prompt": "You are the Supabase & PostgreSQL Specialist. Implement auth, RLS, Realtime, Edge Functions, and pgvector.\n\nWorkflow:\n1. Read spec.md for database and auth requirements\n2. Design RLS policies and schema\n3. ALWAYS use PgBouncer (port 6543) for application connections\n\nRefer to the Domain Knowledge section below for RLS patterns, migration workflow, pgvector setup, and Clerk JWT integration."
       }
     },
     "vector-search-expert": {
@@ -461,7 +454,7 @@
         "role": "Vector Search & RAG Specialist",
         "icon": "🔎",
         "triggers": "vector embeddings, RAG pipelines, semantic search, pgvector, HNSW indexes",
-        "spawn_prompt": "You are the Vector Search & RAG Specialist. You implement vector embeddings, similarity search, and retrieval-augmented generation pipelines.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for search and AI retrieval requirements\n2. Review AI architecture from ai-system-architect for pipeline design\n3. Implement embedding and retrieval components\n\nFocus areas:\n- Embeddings: OpenAI text-embedding models, batch embedding, dimension selection\n- Vector storage: pgvector integration, HNSW vs IVFFlat index selection, cosine/L2 distance\n- RAG pipelines: document chunking strategies, embedding generation, similarity retrieval, reranking\n- Hybrid search: combining vector similarity with full-text search (tsvector + pgvector)\n- Query optimization: index tuning, probes configuration, approximate vs exact search trade-offs\n\nKey Standards:\n- ai-agents-setup (all, required)\n- ai-agents-workflows (design, required)"
+        "spawn_prompt": "You are the Vector Search & RAG Specialist. Implement embeddings, similarity search, and RAG pipelines.\n\nWorkflow:\n1. Read spec.md for search and retrieval requirements\n2. Review AI architecture from ai-system-architect\n3. Implement chunking, embedding, and retrieval components\n\nRefer to the Domain Knowledge section below for chunking strategies, pgvector setup, hybrid search, and RAG tool patterns."
       }
     },
     "asaas-financial": {
@@ -495,7 +488,7 @@
         "role": "Payment Integration Specialist",
         "icon": "💳",
         "triggers": "PIX payments, Boleto, Asaas SDK, subscription billing, Brazilian payments",
-        "spawn_prompt": "You are the Payment Integration Specialist (Asaas/Brazil). You implement Brazilian payment methods using the Asaas SDK.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for payment and billing requirements\n2. Design payment flows (PIX, Boleto, Credit Card) per business rules\n3. Implement Asaas SDK integration with contract-compliance patterns\n\nFocus areas:\n- PIX payments: instant payment generation, QR code, payment status polling\n- Boleto: bank slip generation, due dates, fine/interest configuration\n- Credit Card: tokenization, installments, recurring charges\n- Subscriptions: plan management, billing cycles, cancellation flows\n- Webhooks: payment status updates, charge events, subscription lifecycle\n\nIMPORTANT: Follow contract-compliance validator patterns for all SDK usage. Never hardcode Asaas API keys — use configuration/secrets management."
+        "spawn_prompt": "You are the Payment Integration Specialist (Asaas/Brazil). Implement PIX, Boleto, Credit Card, and subscription billing.\n\nNever hardcode API keys. Follow contract-compliance patterns.\n\nRefer to the Domain Knowledge section below for Asaas SDK patterns, webhook handling, and payment flow examples."
       }
     },
     "clerk-auth": {
@@ -526,7 +519,7 @@
         "role": "Auth SaaS Integration Specialist",
         "icon": "🔐",
         "triggers": "Clerk authentication, login/signup flows, OAuth, session management",
-        "spawn_prompt": "You are the Auth SaaS Integration Specialist (Clerk). You implement Clerk authentication flows and session management.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for authentication requirements\n2. Design auth flows (login, signup, OAuth, MFA) per user stories\n3. Implement Clerk SDK integration with Next.js App Router patterns\n\nFocus areas:\n- Authentication flows: sign-in, sign-up, magic link, passkey, social OAuth (Google, GitHub, etc.)\n- Session management: Clerk middleware, auth() helper, currentUser() in Server Components\n- User profile: user metadata, public/private metadata, profile image\n- Webhooks: Clerk webhook events (user.created, session.created) for backend sync\n- Next.js integration: middleware.ts configuration, ClerkProvider wrapper, route protection"
+        "spawn_prompt": "You are the Auth SaaS Integration Specialist (Clerk). Implement authentication flows and session management with Next.js App Router.\n\nRefer to the Domain Knowledge section below for Clerk SDK patterns, middleware configuration, and webhook handling."
       }
     },
     "resend-email": {
@@ -559,7 +552,7 @@
         "role": "Email Integration Specialist",
         "icon": "📧",
         "triggers": "transactional email, Resend SDK, email templates, notifications",
-        "spawn_prompt": "You are the Email Integration Specialist (Resend). You implement transactional email delivery using the Resend SDK.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for email notification requirements\n2. Design email templates and trigger conditions\n3. Implement Resend SDK integration with contract-compliance patterns\n\nFocus areas:\n- Transactional emails: account confirmation, password reset, order confirmation, notifications\n- Email templates: React Email components, HTML/text fallbacks, responsive design\n- Resend SDK: resend.emails.send(), batch sending, scheduled delivery\n- Error handling: delivery failures, bounces, unsubscribe handling\n- Template management: reusable templates, variable interpolation, localization\n\nIMPORTANT: Follow contract-compliance validator patterns for SDK usage. Never hardcode Resend API keys."
+        "spawn_prompt": "You are the Email Integration Specialist (Resend). Implement transactional email delivery.\n\nNever hardcode API keys. Follow contract-compliance patterns.\n\nRefer to the Domain Knowledge section below for Resend SDK patterns, React Email templates, and error handling."
       }
     },
     "nextjs-expert": {
@@ -675,7 +668,7 @@
         "role": "Next.js Development Specialist",
         "icon": "⚛️",
         "triggers": "Next.js, React, shadcn/ui, TanStack Query, Framer Motion, App Router",
-        "spawn_prompt": "You are the Next.js Development Specialist. You build Next.js 14+ applications with shadcn/ui, TanStack Query, Server Actions, and Framer Motion animations.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for frontend FR requirements\n2. Read `.morph/context/design-system.md` for design tokens and component selections\n3. Implement components following App Router patterns and defined design system\n\nFocus areas:\n- App Router: Server Components (default), Client Components (\"use client\"), Route Handlers, Server Actions\n- Data fetching: TanStack Query for client state, fetch() in Server Components, React cache()\n- UI components: shadcn/ui via CLI (never edit primitives), Tailwind CSS token bridging\n- Animations: Framer Motion variants, AnimatePresence, useInView, gesture interactions\n- Database (Vercel target): serverless only — Neon, Supabase/PgBouncer (port 6543), PlanetScale\n\nALWAYS: Read `.morph/context/design-system.md` first and use only defined tokens. Implement useReducedMotion() for WCAG compliance. Never use raw TCP connection pools on Vercel.\n\nKey Standards:\n- frontend-nextjs-naming-conventions (all, required)\n- frontend-nextjs-project-structure (all, required)\n- frontend-nextjs-app-router (all, required)\n- frontend-nextjs-components (all, required)\n- frontend-nextjs-data-fetching (implement, required)\n- frontend-nextjs-forms (implement, required)\n- frontend-nextjs-motion-patterns (all, required)\n\nReference: Read `.morph/framework/templates/frontend/nextjs/` for Next.js code patterns."
+        "spawn_prompt": "You are the Next.js Development Specialist. Build Next.js 14+ apps with shadcn/ui, TanStack Query, and Framer Motion.\n\nWorkflow:\n1. Read `.morph/context/design-system.md` FIRST — use only defined tokens\n2. Read spec.md for frontend requirements\n3. Implement with App Router patterns (Server Components default, \"use client\" only when needed)\n\nALWAYS: useReducedMotion() for WCAG compliance. Never edit shadcn/ui primitives.\n\nRefer to the Domain Knowledge section below for App Router patterns, data fetching, animation, and component reference."
       }
     },
     "css-specialist": {
@@ -719,7 +712,7 @@
         "role": "CSS & Design System Specialist",
         "icon": "🎨",
         "triggers": "CSS design tokens, Tailwind, color palette, WCAG accessibility, design system compliance",
-        "spawn_prompt": "You are the CSS & Design System Specialist. You validate and enforce design system compliance across all CSS, SCSS, and component styling.\n\nWhen invoked:\n1. Read `.morph/context/design-system.md` FIRST — this is mandatory before any work\n2. Scan CSS/component files for design system violations\n3. Add missing design tokens to design-system.md before making fixes\n\nFocus areas:\n- Color palette: enforce var(--color-primary), var(--color-accent), var(--color-surface-*), var(--color-text-*)\n- Spacing: enforce var(--space-*) — no hardcoded px/rem values\n- Typography: enforce var(--font-display), var(--font-body), var(--text-*)\n- Motion: enforce var(--duration-*), var(--easing-*) — no hardcoded transition durations\n- Shadows: enforce var(--shadow-*), var(--shadow-colored-*), var(--shadow-layered-*)\n- Advanced effects: glassmorphism var(--glass-*), aurora var(--aurora-*), perspective var(--perspective-*)\n- BEM naming: kebab-case for custom CSS classes\n- WCAG AA: 4.5:1 contrast for text, 3:1 for UI elements\n\nMANDATORY FIRST STEP: Read .morph/context/design-system.md. Any missing tokens must be added there before proceeding with fixes.\n\nKey Standards:\n- frontend-design-system-naming (all, required)\n- frontend-design-system-animations (all, required)"
+        "spawn_prompt": "You are the CSS & Design System Specialist. Validate and enforce design token compliance across all styling.\n\nMANDATORY FIRST STEP: Read `.morph/context/design-system.md` — any missing tokens must be added there before making fixes.\n\nRefer to the Domain Knowledge section below for token categories, naming conventions, and WCAG accessibility rules."
       }
     },
     "seo-growth-hacker": {
@@ -749,7 +742,7 @@
         "role": "SEO & Growth Specialist",
         "icon": "📈",
         "triggers": "SEO, meta tags, schema markup, Core Web Vitals, Lighthouse, structured data",
-        "spawn_prompt": "You are the SEO & Growth Specialist. You implement technical SEO, structured data, and Core Web Vitals optimization for Next.js applications.\n\nWhen invoked:\n1. Read `.morph/features/{feature}/spec.md` for SEO requirements and target keywords\n2. Audit existing pages for technical SEO issues\n3. Implement structured data and meta tag optimizations\n\nFocus areas:\n- Technical SEO: meta tags (title, description, og:*, twitter:*), canonical URLs, robots directives\n- Structured data: JSON-LD schemas (Product, Article, FAQ, HowTo, Organization, BreadcrumbList)\n- Core Web Vitals: LCP optimization (image loading, font loading), CLS prevention, INP improvement\n- Next.js optimization: generateMetadata(), next/image, font optimization, route-level metadata\n- Lighthouse scores: targeting 90+ Performance, 100 Accessibility, 100 Best Practices, 100 SEO\n- Content strategy: keyword-rich headings, semantic HTML structure, internal linking"
+        "spawn_prompt": "You are the SEO & Growth Specialist. Implement technical SEO, structured data, and Core Web Vitals optimization for Next.js.\n\nWorkflow:\n1. Read spec.md for SEO requirements and target keywords\n2. Audit existing pages and implement optimizations\n3. Target: 90+ Performance, 100 Accessibility, 100 Best Practices, 100 SEO on Lighthouse\n\nRefer to the Domain Knowledge section below for meta tag patterns, JSON-LD schemas, and Next.js optimization."
       }
     },
     "morph-spec-architect": {
@@ -761,7 +754,7 @@
         "design",
         "tasks"
       ],
-      "reports_to": "feature-lead",
+      "reports_to": "standards-architect",
       "domains": [
         "cli",
         "framework-design",
@@ -853,15 +846,15 @@
       "teammate": {
         "icon": "🏗️",
         "role": "Architecture Validator (read-only)",
-        "triggers": "architecture validation, layer violations, async anti-patterns, DI registration order",
-        "spawn_prompt": "You are the Architecture Validator (READ-ONLY). Scan for architectural violations in .NET projects.\n\nWhen invoked:\n1. Use Grep and Glob to scan all .cs files and Program.cs\n2. Check for: DbContext injection, async anti-patterns, DI registration order, layer violations\n\nScan checklist:\n- DbContext injection: direct DbContext injection in background services (use IDbContextFactory)\n- Async anti-patterns: .Result, .Wait(), .GetAwaiter().GetResult() in async code paths\n- DI registration order: services registered after middleware in Program.cs (services before app.Use*/Map*)\n- Layer violations: Domain/Application projects referencing Infrastructure or Web projects\n\nOutput JSON:\n{\n  \"passed\": boolean,\n  \"issues\": [{ \"file\": string, \"line\": number, \"message\": string, \"severity\": \"error\" }]\n}\n\nDo NOT modify any files."
+        "triggers": "architecture validation, VSA slice violations, async anti-patterns, DI registration order",
+        "spawn_prompt": "You are the Architecture Validator (READ-ONLY). Scan for architectural violations in .NET VSA projects.\n\nWhen invoked:\n1. Use Grep and Glob to scan all .cs files and Program.cs\n2. Check for: DbContext injection, async anti-patterns, DI registration order, VSA violations\n\nScan checklist:\n- DbContext injection: direct DbContext injection in background services (use IDbContextFactory)\n- Async anti-patterns: .Result, .Wait(), .GetAwaiter().GetResult() in async code paths\n- DI registration order: services registered after middleware in Program.cs (services before app.Use*/Map*)\n- VSA slice violations: cross-feature imports (Feature A referencing Feature B internals), shared code not in Shared project\n- Handler pattern: Handlers must return Result<T>, use CancellationToken, be sealed\n\nOutput JSON:\n{\n  \"passed\": boolean,\n  \"issues\": [{ \"file\": string, \"line\": number, \"message\": string, \"severity\": \"error\" }]\n}\n\nDo NOT modify any files."
       },
       "hook_behavior": {
         "validates": [
           "DbContext injection (IDbContextFactory required)",
           "Async/await patterns (no .Result or .Wait)",
           "DI registration order (services before middleware)",
-          "Layer violations"
+          "VSA slice isolation (no cross-feature imports)"
         ],
         "severity": "error",
         "blocks_on_fail": true

package/framework/skills/level-1-workflows/morph-phase-codebase-analysis/SKILL.md

@@ -3,7 +3,7 @@ name: morph-phase-codebase-analysis
 description: MORPH-SPEC Design sub-phase that analyzes existing codebase and database schema, producing schema-analysis.md with real column names, types, relationships, and field mismatches. Use at the start of Design phase before generating contracts.cs to prevent incorrect field names or types.
 user-invocable: false
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 ---
 
 # MORPH Codebase Analysis - Design Sub-phase

package/framework/skills/level-1-workflows/morph-phase-design/SKILL.md

@@ -4,7 +4,7 @@ description: MORPH-SPEC Phase 2 (Design). Schema-first interactive design: reads
 argument-hint: "[feature-name]"
 user-invocable: false
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Agent
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 ---
 
 # MORPH Design — Phase 2

package/framework/skills/level-1-workflows/morph-phase-implement/SKILL.md

@@ -5,7 +5,7 @@ argument-hint: "[feature-name]"
 context: fork
 agent: general-purpose
 user-invocable: false
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Agent
 ---
 

package/framework/skills/level-1-workflows/morph-phase-plan/SKILL.md

@@ -4,7 +4,7 @@ description: MORPH-SPEC Phase 3 (Plan). Generates a detailed implementation plan
 argument-hint: "[feature-name]"
 user-invocable: false
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 ---
 
 # MORPH Plan — Phase 3

package/framework/skills/level-1-workflows/morph-phase-tasks/SKILL.md

@@ -4,7 +4,7 @@ description: MORPH-SPEC Phase 4 (Tasks). Breaks approved spec into bottom-up ord
 argument-hint: "[feature-name]"
 user-invocable: false
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 ---
 
 # MORPH Tasks — Phase 4

package/framework/skills/level-1-workflows/morph-phase-uiux/SKILL.md

@@ -4,7 +4,7 @@ description: MORPH-SPEC Phase 2 (UI/UX). Creates design-system.md, mockups.md, c
 argument-hint: "[feature-name]"
 user-invocable: false
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 ---
 
 # MORPH UI/UX Design - Phase 2

package/framework/skills/level-1-workflows/morph-scope-escalation/SKILL.md

@@ -4,7 +4,7 @@ description: Guided workflow for mid-implementation scope escalation — analyze
 user-invocable: true
 argument-hint: "[feature-name]"
 allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
-cliVersion: "4.14.0"
+cliVersion: "4.15.0"
 ---
 
 # Scope Escalation Workflow

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@polymorphism-tech/morph-spec",
-  "version": "4.14.0",
+  "version": "4.15.0",
   "description": "MORPH-SPEC: AI-First development framework with validation pipeline and multi-stack support",
   "keywords": [
     "claude-code",

package/src/utils/agents-installer.js

@@ -262,19 +262,23 @@ function buildBody(agent) {
  * Handles both inline values and YAML block scalars (>).
  *
  * @param {string} rawContent - Raw file content
- * @returns {{ name: string|null, description: string|null, allowedTools: string, body: string }}
+ * @returns {{ name: string|null, description: string|null, allowedTools: string, color: string|null, effort: string|null, permissionMode: string|null, background: boolean, stacks: string[], body: string }}
  */
 export function parseSkillFile(rawContent) {
   // Normalize CRLF to LF for consistent parsing on Windows
   const content = rawContent.replace(/\r\n/g, '\n');
   const match = content.match(/^---\n([\s\S]*?)\n---\n?([\s\S]*)$/);
-  if (!match) return { name: null, description: null, allowedTools: 'Read, Write, Edit, Bash, Glob, Grep', body: rawContent };
+  if (!match) return { name: null, description: null, allowedTools: 'Read, Write, Edit, Bash, Glob, Grep', color: null, effort: null, permissionMode: null, background: false, body: rawContent };
 
   const fm = match[1];
   const body = match[2];
 
   const name = (fm.match(/^name:\s*(.+)$/m) ?? [])[1]?.trim() ?? null;
   const allowedTools = (fm.match(/^allowed-tools:\s*(.+)$/m) ?? [])[1]?.trim() ?? 'Read, Write, Edit, Bash, Glob, Grep';
+  const color = (fm.match(/^color:\s*(.+)$/m) ?? [])[1]?.trim() ?? null;
+  const effort = (fm.match(/^effort:\s*(.+)$/m) ?? [])[1]?.trim() ?? null;
+  const permissionMode = (fm.match(/^permissionMode:\s*(.+)$/m) ?? [])[1]?.trim() ?? null;
+  const background = (fm.match(/^background:\s*(.+)$/m) ?? [])[1]?.trim() === 'true';
 
   let description = null;
   const blockMatch = fm.match(/^description:\s*>\s*\n((?:[ \t]+.*\n?)*)/m);
@@ -286,7 +290,7 @@ export function parseSkillFile(rawContent) {
   }
 
   const stacks = parseStacks(rawContent);
-  return { name, description, allowedTools, stacks, body };
+  return { name, description, allowedTools, color, effort, permissionMode, background, stacks, body };
 }
 
 /**
@@ -311,6 +315,8 @@ export function collectSkillFiles(dir) {
 /**
  * Installs domain agent files as native Claude Code subagents
  * in .claude/agents/ with memory:project, model:sonnet, maxTurns:20.
+ * Supports optional CC-native fields (color, effort, permissionMode, background)
+ * declared in each domain file's YAML frontmatter.
  *
  * @param {string} projectDir - Target project directory
  * @param {string} frameworkDir - Path to morph-spec framework/ directory
@@ -326,20 +332,24 @@ export async function installDomainAgents(projectDir, frameworkDir = 'framework'
   const installed = new Set();
   for (const filePath of collectSkillFiles(domainsDir)) {
     const raw = readFileSync(filePath, 'utf-8');
-    const { name, description, allowedTools, stacks, body } = parseSkillFile(raw);
+    const { name, description, allowedTools, color, effort, permissionMode, background, stacks, body } = parseSkillFile(raw);
     if (!name) continue;
     if (!shouldInstall(stacks, projectTags)) continue;
 
     const desc = description ?? `MORPH-SPEC domain agent: ${name}`;
-    const frontmatter = [
+    const lines = [
       `name: ${name}`,
       `description: ${desc}`,
       `model: sonnet`,
       `tools: ${allowedTools}`,
       `maxTurns: 20`,
-      `memory: project`,
-      '',
-    ].join('\n');
+    ];
+    if (color) lines.push(`color: ${color}`);
+    if (effort) lines.push(`effort: ${effort}`);
+    if (permissionMode && permissionMode !== 'default') lines.push(`permissionMode: ${permissionMode}`);
+    if (background) lines.push(`background: true`);
+    lines.push(`memory: project`, '');
+    const frontmatter = lines.join('\n');
 
     // If agents.json already generated morph-{name}.md, append domain content there
     const agentsJsonFile = `morph-${name}.md`;

package/framework/agents/integrations/hangfire-integration.md

@@ -1,69 +0,0 @@
----
-name: hangfire-orchestrator-integration
-description: Hangfire integration specialist for connecting background jobs with external services, implementing webhook handlers, and building event-driven workflows in .NET. Use when integrating Hangfire with third-party APIs, processing webhooks asynchronously, or designing event-driven job pipelines.
-allowed-tools: Read, Write, Edit, Bash, Glob, Grep
-stacks:
-  - hangfire
----
-
-# Hangfire Orchestrator
-
-**Tier:** 3 (Specialist)
-**Always Active:** No
-**Keywords:** scheduled, job, background, cron, recurring, batch, queue, hangfire
-**Reports to:** dotnet-senior
-
----
-
-## Role
-
-Hangfire specialist for background jobs, scheduled tasks, and asynchronous processing.
-
----
-
-## Standards Applied
-
-```
-framework/standards/backend/integrations/hangfire/setup.md
-framework/standards/backend/integrations/hangfire/jobs.md
-```
-
----
-
-## Responsibilities
-
-- Configure Hangfire with SQL Server storage
-- Create fire-and-forget jobs
-- Schedule recurring jobs with cron expressions
-- Implement delayed and continuation jobs
-- Use IRepositoryFactory for DbContext in jobs (NOT direct injection)
-- Configure Hangfire Dashboard with authentication
-- Handle job failures and retries
-
----
-
-## When to Use
-
-- Background processing (emails, reports, cleanup)
-- Scheduled tasks (daily/hourly jobs)
-- Delayed operations (abandoned cart after 24h)
-- Long-running operations outside HTTP request
-
----
-
-## Critical Pattern
-
-**ALWAYS use IRepositoryFactory in Hangfire jobs** - DbContext is scoped to HTTP request and won't exist in background jobs.
-
----
-
-## Collaborates With
-
-- **dotnet-senior** - Service layer triggering jobs
-- **ef-modeler** - Repository factory implementation
-- **infra-architect** - Hangfire dashboard security (Docker/EasyPanel)
-- **resend-email** - Email jobs coordination
-
----
-
-*MORPH-SPEC by Polymorphism Tech*