@polymorphism-tech/morph-spec 7.9.3 → 8.0.0

package/framework/standards/ai-agents/sweet-spot.md

@@ -1,109 +1,109 @@
-# Sweet Spot — When to use what in MAF
-
-> **Scope:** stacks=["dotnet"]
-> **Layer:** 0 (always-load via persona maf-expert)
-> **Keywords:** sweet spot, when to use agent, agent vs workflow, when not to use workflow, MAF decision, simple agent
-> **Read by Claude in:** plan (decide arquitetura da feature antes de quebrar em tasks) + implement (validar que a arquitetura ainda é a mais simples possível)
-
-**Verified against:** MAF Tier List research (2026-05-18) + Microsoft Learn docs. Last-verified: 2026-05-19.
-
----
-
-## The 4-feature rule
-
-```
-95% of production AI agents need ONLY:
-
-  1. Chat (the LLM call)
-  2. Structured Output (typed records, not free text)
-  3. Tools (typed functions the agent can call)
-  4. RAG Custom (pgvector tool, not hosted RAG)
-
-If your feature needs ONLY these 4 → use a single agent. Don't reach for workflows.
-```
-
-Apply this rule before deciding multi-agent or workflow. Most of the time the answer is "single agent".
-
----
-
-## Decision tree (Claude reads this in plan phase)
-
-```
-Step 1 — Does the task even need an LLM?
-├─ "Can a deterministic function solve this?" → YES → write the function, no agent
-└─ NO → continue
-
-Step 2 — Single agent vs multi-agent?
-├─ One topic + one decision → single agent (DEFAULT)
-├─ Multiple specialized topics with clear handoff → multi-agent
-│   └─ Prefer Agent-as-Tool pattern (one agent uses another as a tool)
-│   └─ See ai-agents-multi-agent-patterns
-└─ "I'm not sure" → start with single agent, escalate if needed
-
-Step 3 — Need a Workflow?
-├─ The feature has fan-in/out (many inputs aggregated) → maybe workflow
-│   └─ Confirm: can you write it as a foreach + LINQ aggregate?
-│       └─ YES → write the foreach, NO workflow
-│       └─ NO → workflow may help
-├─ Long-running with human-in-the-loop checkpoints → maybe workflow
-│   └─ See ai-agents-workflows (Onda 2)
-└─ Otherwise → NO workflow
-
-Step 4 — Which provider?
-├─ ALWAYS direct models — never a hosted agent service
-├─ Provider choice (OpenAI / Google / Anthropic / Ollama) lives in the
-│  project's Model Registry, not hardcoded → see ai-agents-providers-model-registry
-└─ Hosted services (Foundry Agent Service, Vertex AI hosted) → NOT used
-
-Step 5 — RAG approach?
-├─ Need control over chunking/embedding/storage? → RAG custom (pgvector)
-│   └─ See ai-agents-rag-custom-pgvector (Onda 2)
-└─ Don't reach for hosted RAG — loses control
-```
-
----
-
-## Anti-patterns (what Claude should NOT do)
-
-| Anti-pattern | Why it's wrong | What to do instead |
-|--------------|----------------|---------------------|
-| Reach for Workflow when a function does the job | "Tudo que Workflows fazem, código C# normal faz com menos complexidade" — pesquisa | Write the function. Wrap in a tool if an agent needs to call it. |
-| Use a hosted agent service | Hosted is "always 6-9 months behind" on models + removes control | Direct models always (OpenAI / Google / Anthropic / Ollama) |
-| Upload PDFs to a hosted RAG | Loses control of chunking + embedding + storage | Custom RAG with pgvector. See ai-agents-rag-custom-pgvector |
-| Add Memory/Session because "agents need state" | If not building a chatbot, don't add chat state | Skip. Add when a real chat UI exists. |
-| Use Semantic Kernel for new features | SK is superseded by MAF | Use Microsoft.Agents.AI. See ai-agents-setup |
-| Return free text and parse it downstream | LLM output is non-deterministic | Structured Output. See ai-agents-structured-output (Onda 2) |
-
----
-
-## When the 4-feature rule does NOT apply
-
-You may need to step outside the sweet spot when:
-- The feature genuinely fans-out (e.g., monthly report aggregating N items) → workflow with fan-in
-- The feature needs vision/audio/image-gen → modality-specific standards (see ai-agents-modalities-* — Onda 3)
-
-**Even in these cases:** the core of the agent still follows the 4-feature rule. Only the orchestration layer changes.
-
----
-
-## Checklist (verifiable by morph-eval)
-
-- [ ] Was each agent designed as single-agent BEFORE reaching for multi-agent? (Check `decisions.md`.)
-- [ ] If a Workflow is used, is fan-in/out or HITL checkpointing genuinely present? Or could `foreach + LINQ` replace it?
-- [ ] Are the 4 features (Chat, Structured Output, Tools, RAG Custom) all present where applicable?
-- [ ] Are hosted agent services avoided?
-
----
-
-## References
-
-- `ai-agents-setup` — packages and DI
-- `ai-agents-providers-model-registry` — provider-agnostic config
-- `ai-agents-structured-output` (Onda 2)
-- `ai-agents-multi-agent-patterns` (Onda 2)
-- `ai-agents-workflows` (Onda 2, reframed)
-- `ai-agents-rag-custom-pgvector` (Onda 2)
-
----
-
-*MORPH-SPEC by Polymorphism Tech — ai-agents/sweet-spot.md v1.0 (2026-05-19)*
+# Sweet Spot — When to use what in MAF
+
+> **Scope:** stacks=["dotnet"]
+> **Layer:** 0 (always-load via persona maf-expert)
+> **Keywords:** sweet spot, when to use agent, agent vs workflow, when not to use workflow, MAF decision, simple agent
+> **Read by Claude in:** plan (decide arquitetura da feature antes de quebrar em tasks) + implement (validar que a arquitetura ainda é a mais simples possível)
+
+**Verified against:** MAF Tier List research (2026-05-18) + Microsoft Learn docs. Last-verified: 2026-05-19.
+
+---
+
+## The 4-feature rule
+
+```
+95% of production AI agents need ONLY:
+
+  1. Chat (the LLM call)
+  2. Structured Output (typed records, not free text)
+  3. Tools (typed functions the agent can call)
+  4. RAG Custom (pgvector tool, not hosted RAG)
+
+If your feature needs ONLY these 4 → use a single agent. Don't reach for workflows.
+```
+
+Apply this rule before deciding multi-agent or workflow. Most of the time the answer is "single agent".
+
+---
+
+## Decision tree (Claude reads this in plan phase)
+
+```
+Step 1 — Does the task even need an LLM?
+├─ "Can a deterministic function solve this?" → YES → write the function, no agent
+└─ NO → continue
+
+Step 2 — Single agent vs multi-agent?
+├─ One topic + one decision → single agent (DEFAULT)
+├─ Multiple specialized topics with clear handoff → multi-agent
+│   └─ Prefer Agent-as-Tool pattern (one agent uses another as a tool)
+│   └─ See ai-agents-multi-agent-patterns
+└─ "I'm not sure" → start with single agent, escalate if needed
+
+Step 3 — Need a Workflow?
+├─ The feature has fan-in/out (many inputs aggregated) → maybe workflow
+│   └─ Confirm: can you write it as a foreach + LINQ aggregate?
+│       └─ YES → write the foreach, NO workflow
+│       └─ NO → workflow may help
+├─ Long-running with human-in-the-loop checkpoints → maybe workflow
+│   └─ See ai-agents-workflows (Onda 2)
+└─ Otherwise → NO workflow
+
+Step 4 — Which provider?
+├─ ALWAYS direct models — never a hosted agent service
+├─ Provider choice (OpenAI / Google / Anthropic / Ollama) lives in the
+│  project's Model Registry, not hardcoded → see ai-agents-providers-model-registry
+└─ Hosted services (Foundry Agent Service, Vertex AI hosted) → NOT used
+
+Step 5 — RAG approach?
+├─ Need control over chunking/embedding/storage? → RAG custom (pgvector)
+│   └─ See ai-agents-rag-custom-pgvector (Onda 2)
+└─ Don't reach for hosted RAG — loses control
+```
+
+---
+
+## Anti-patterns (what Claude should NOT do)
+
+| Anti-pattern | Why it's wrong | What to do instead |
+|--------------|----------------|---------------------|
+| Reach for Workflow when a function does the job | "Tudo que Workflows fazem, código C# normal faz com menos complexidade" — pesquisa | Write the function. Wrap in a tool if an agent needs to call it. |
+| Use a hosted agent service | Hosted is "always 6-9 months behind" on models + removes control | Direct models always (OpenAI / Google / Anthropic / Ollama) |
+| Upload PDFs to a hosted RAG | Loses control of chunking + embedding + storage | Custom RAG with pgvector. See ai-agents-rag-custom-pgvector |
+| Add Memory/Session because "agents need state" | If not building a chatbot, don't add chat state | Skip. Add when a real chat UI exists. |
+| Use Semantic Kernel for new features | SK is superseded by MAF | Use Microsoft.Agents.AI. See ai-agents-setup |
+| Return free text and parse it downstream | LLM output is non-deterministic | Structured Output. See ai-agents-structured-output (Onda 2) |
+
+---
+
+## When the 4-feature rule does NOT apply
+
+You may need to step outside the sweet spot when:
+- The feature genuinely fans-out (e.g., monthly report aggregating N items) → workflow with fan-in
+- The feature needs vision/audio/image-gen → modality-specific standards (see ai-agents-modalities-* — Onda 3)
+
+**Even in these cases:** the core of the agent still follows the 4-feature rule. Only the orchestration layer changes.
+
+---
+
+## Checklist (verifiable by morph-eval)
+
+- [ ] Was each agent designed as single-agent BEFORE reaching for multi-agent? (Check `decisions.md`.)
+- [ ] If a Workflow is used, is fan-in/out or HITL checkpointing genuinely present? Or could `foreach + LINQ` replace it?
+- [ ] Are the 4 features (Chat, Structured Output, Tools, RAG Custom) all present where applicable?
+- [ ] Are hosted agent services avoided?
+
+---
+
+## References
+
+- `ai-agents-setup` — packages and DI
+- `ai-agents-providers-model-registry` — provider-agnostic config
+- `ai-agents-structured-output` (Onda 2)
+- `ai-agents-multi-agent-patterns` (Onda 2)
+- `ai-agents-workflows` (Onda 2, reframed)
+- `ai-agents-rag-custom-pgvector` (Onda 2)
+
+---
+
+*MORPH-SPEC by Polymorphism Tech — ai-agents/sweet-spot.md v1.0 (2026-05-19)*

package/framework/standards/backend/integrations/neon-auth/neon-auth.md

@@ -2,7 +2,7 @@
 
 > **Scope:** universal
 > **Layer:** 2 (on keyword)
-> **Keywords:** neon auth, better auth, authentication, nextjs, user management, session, JWT, trusted origins, EdDSA, Ed25519, BouncyCastle, signature validator, jwks, middleware runtime, api prefix
+> **Keywords:** neon auth, better auth, authentication, nextjs, user management, session, JWT, trusted origins, EdDSA, Ed25519, BouncyCastle, signature validator, jwks, middleware runtime, api prefix, data api, postgrest, bypass backend, direct database access
 > **Load When:** neon auth or authentication keywords detected
 
 **Verified against:** Neon Auth — @neondatabase/auth + @neondatabase/auth-ui (Better Auth). Last-verified: 2026-07-13.
@@ -37,13 +37,42 @@ Neon Auth provides:
 1. **Database-First**: Auth data lives in `neon_auth` schema — no external service to sync
 2. **Branch Isolation**: Each Neon branch gets isolated users, sessions, and auth config
 3. **Server-First**: Use server-side auth checks with `auth.getSession()`
-4. **JWT for RLS**: Tokens contain `sub` (user ID), `email`, `role: "authenticated"` for database policies
+4. **JWT for RLS**: Tokens contain `sub` (user ID), `email`, `role: "authenticated"` for database
+   policies — used only inside the justified Data API exception path, not by default (see
+   [Data Access Boundary](#data-access-boundary--backend-first-by-default))
 5. **No OIDC discovery**: Neon Auth does **not** expose `/.well-known/openid-configuration` — only the
    raw `/.well-known/jwks.json`. Never assume `options.Authority` alone gives you working discovery on
    the .NET side (see [.NET Backend Integration](#net-backend-integration)).
 
 ---
 
+## Data Access Boundary — Backend-First by Default
+
+The Next.js frontend has exactly one inherent reason to talk to Neon directly: Neon Auth's own
+client SDK (`authClient`, `useSession`, `auth.getSession()`) — that's Better Auth's session/JWT
+mechanism, not a business-data call. Every read or write of application/business data goes through
+the .NET backend instead, either as a server-direct fetch or a client-via-proxy call (see
+[API Prefix Convention](#api-prefix-convention--server-direct-vs-client-proxy) for the mechanics).
+
+**Rule:** the frontend does not query Neon directly for business data — not via a Neon Data API
+(REST-over-Postgres) endpoint, not via a browser-held connection string, not via any other bypass
+of the .NET backend. The .NET backend is the sole gateway to business data, for the same reason
+`architecture/vertical-slice/vertical-slice.md` makes the backend the sole gateway to the database
+in general: handler-level authorization, no business rules duplicated on two sides of the wire, one
+place to audit.
+
+**The exception process:** a feature that genuinely needs the frontend to reach Neon directly for
+business data (for example, via the Neon MCP `provision_neon_data_api` tool) is an exception, not a
+default — treat it exactly like vertical-slice.md's "Stores dedicados (exceção justificada)" clause:
+document the justification in the feature's `decisions.md` before writing the code. A tool being
+available is not, by itself, justification.
+
+See [Row-Level Security Integration](#row-level-security-integration) for how to constrain a
+Data-API-exception session once one exists — those RLS policies are not a signal that the frontend
+should have direct access by default.
+
+---
+
 ## Installation & Setup
 
 ### Install Packages
@@ -299,6 +328,10 @@ export async function GET() {
 
 ## API Prefix Convention — Server-Direct vs Client-Proxy
 
+> Assumes the [Data Access Boundary](#data-access-boundary--backend-first-by-default) rule: all
+> business data routes through the backend by default. This section covers only the *mechanics* of
+> doing so from each render context.
+
 A Next.js app talking to a Neon-Auth-protected .NET backend fetches from **two different places**
 depending on where the code runs:
 
@@ -616,7 +649,13 @@ app.Run();
 
 ## Row-Level Security Integration
 
-Neon Auth JWT tokens are automatically validated by the Data API. The `auth.user_id()` function (via `pg_session_jwt` extension) exposes the authenticated user ID from the JWT `sub` claim.
+> Defense-in-depth on a JWT-scoped Postgres session — the Data API exception above, not a directive
+> to call Neon from the browser for business data by default. See
+> [Data Access Boundary](#data-access-boundary--backend-first-by-default).
+
+When a Data API endpoint is provisioned (the justified exception above), Neon Auth JWT tokens are
+automatically validated by it. The `auth.user_id()` function (via `pg_session_jwt` extension)
+exposes the authenticated user ID from the JWT `sub` claim to any RLS policy on that session.
 
 ```sql
 -- Enable RLS
@@ -673,6 +712,9 @@ Each Neon branch gets its own isolated auth data. This means:
    service silently becomes a phantom `[FromBody]` parameter and crashes the app at startup
 10. **On .NET, never rely on `options.Authority` alone** — Neon Auth has no OIDC discovery document;
     fetch and cache the JWKS yourself and verify EdDSA signatures manually (BouncyCastle)
+11. **Route business data through the .NET backend by default** — the frontend's only inherent
+    reason to talk to Neon directly is its own auth/session SDK; a direct Data API call needs a
+    `decisions.md` ADR (see [Data Access Boundary](#data-access-boundary--backend-first-by-default))
 
 ---
 

package/framework/templates/.idea/morph-templates.xml

@@ -0,0 +1,92 @@
+<templateSet group="MORPH Templates">
+  <template name="morph-pascal" value="{{pascalCase $FEATURE_NAME$}}" description="Convert to PascalCase (UserAuth)" toReformat="false" toShortenFQNames="true">
+    <variable name="FEATURE_NAME" expression="" defaultValue="&quot;FEATURE_NAME&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-camel" value="{{camelCase $FEATURE_NAME$}}" description="Convert to camelCase (userAuth)" toReformat="false" toShortenFQNames="true">
+    <variable name="FEATURE_NAME" expression="" defaultValue="&quot;FEATURE_NAME&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-snake" value="{{snakeCase $FEATURE_NAME$}}" description="Convert to snake_case (user_auth)" toReformat="false" toShortenFQNames="true">
+    <variable name="FEATURE_NAME" expression="" defaultValue="&quot;FEATURE_NAME&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-title" value="{{titleCase $FEATURE_NAME$}}" description="Convert to Title Case (User Auth)" toReformat="false" toShortenFQNames="true">
+    <variable name="FEATURE_NAME" expression="" defaultValue="&quot;FEATURE_NAME&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-kebab" value="{{kebabCase $FEATURE_NAME$}}" description="Convert to kebab-case (user-auth)" toReformat="false" toShortenFQNames="true">
+    <variable name="FEATURE_NAME" expression="" defaultValue="&quot;FEATURE_NAME&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-if" value="{{#if $CONDITION$}}&#10;  $END$&#10;{{/if}}" description="Handlebars if block" toReformat="false" toShortenFQNames="true">
+    <variable name="CONDITION" expression="" defaultValue="&quot;condition&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-if-else" value="{{#if $CONDITION$}}&#10;  $TRUE_BRANCH$&#10;{{else}}&#10;  $FALSE_BRANCH$&#10;{{/if}}" description="Handlebars if-else block" toReformat="false" toShortenFQNames="true">
+    <variable name="CONDITION" expression="" defaultValue="&quot;condition&quot;" alwaysStopAt="true" />
+    <variable name="TRUE_BRANCH" expression="" defaultValue="&quot;&quot;" alwaysStopAt="true" />
+    <variable name="FALSE_BRANCH" expression="" defaultValue="&quot;&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-each" value="{{#each $ITEMS$}}&#10;  {{this.$PROPERTY$}}&#10;{{/each}}" description="Handlebars each loop" toReformat="false" toShortenFQNames="true">
+    <variable name="ITEMS" expression="" defaultValue="&quot;items&quot;" alwaysStopAt="true" />
+    <variable name="PROPERTY" expression="" defaultValue="&quot;name&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="OTHER" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-service" value="namespace {{NAMESPACE}}.Application.Features.{{pascalCase FEATURE_NAME}}.Services;&#10;&#10;public class {{pascalCase FEATURE_NAME}}Service(&#10;    I{{pascalCase FEATURE_NAME}}Repository repository,&#10;    ILogger&lt;{{pascalCase FEATURE_NAME}}Service&gt; logger) : I{{pascalCase FEATURE_NAME}}Service&#10;{&#10;    public async Task&lt;{{pascalCase FEATURE_NAME}}Dto?&gt; GetByIdAsync(int id, CancellationToken cancellationToken = default)&#10;    {&#10;        $END$&#10;    }&#10;}" description="MORPH .NET Service class template" toReformat="false" toShortenFQNames="true">
+    <context>
+      <option name="C_SHARP" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-repository" value="public class {{pascalCase FEATURE_NAME}}Repository(AppDbContext context) : I{{pascalCase FEATURE_NAME}}Repository&#10;{&#10;    private readonly DbSet&lt;{{pascalCase FEATURE_NAME}}&gt; _dbSet = context.Set&lt;{{pascalCase FEATURE_NAME}}&gt;();&#10;&#10;    public async Task&lt;{{pascalCase FEATURE_NAME}}?&gt; GetByIdAsync(int id, CancellationToken cancellationToken = default)&#10;    {&#10;        $END$&#10;    }&#10;}" description="MORPH .NET Repository class template" toReformat="false" toShortenFQNames="true">
+    <context>
+      <option name="C_SHARP" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-component" value="@page &quot;/{{kebabCase FEATURE_NAME}}&quot;&#10;@inject I{{pascalCase FEATURE_NAME}}Service {{pascalCase FEATURE_NAME}}Service&#10;@inject ILogger&lt;{{pascalCase FEATURE_NAME}}Page&gt; Logger&#10;&#10;&lt;PageTitle&gt;{{pascalCase FEATURE_NAME}}&lt;/PageTitle&gt;&#10;&#10;&lt;div class=&quot;container-fluid&quot;&gt;&#10;    $END$&#10;&lt;/div&gt;&#10;&#10;@code {&#10;&#10;}" description="MORPH Blazor component template" toReformat="false" toShortenFQNames="true">
+    <context>
+      <option name="HTML" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-migration" value="public partial class Add{{pascalCase FEATURE_NAME}} : Migration&#10;{&#10;    protected override void Up(MigrationBuilder migrationBuilder)&#10;    {&#10;        migrationBuilder.CreateTable(&#10;            name: &quot;{{pascalCase FEATURE_NAME}}s&quot;,&#10;            columns: table =&gt; new&#10;            {&#10;                Id = table.Column&lt;int&gt;(type: &quot;int&quot;, nullable: false)&#10;                    .Annotation(&quot;SqlServer:Identity&quot;, &quot;1, 1&quot;),&#10;                $END$&#10;            },&#10;            constraints: table =&gt;&#10;            {&#10;                table.PrimaryKey(&quot;PK_{{pascalCase FEATURE_NAME}}s&quot;, x =&gt; x.Id);&#10;            });&#10;    }&#10;&#10;    protected override void Down(MigrationBuilder migrationBuilder)&#10;    {&#10;        migrationBuilder.DropTable(name: &quot;{{pascalCase FEATURE_NAME}}s&quot;);&#10;    }&#10;}" description="MORPH EF Core migration template" toReformat="false" toShortenFQNames="true">
+    <context>
+      <option name="C_SHARP" value="true" />
+    </context>
+  </template>
+
+  <template name="morph-ts-contract" value="export interface {{pascalCase FEATURE_NAME}} {&#10;  id: number;&#10;  $FIELD1$&#10;}&#10;&#10;export interface Create{{pascalCase FEATURE_NAME}}Request {&#10;  $FIELD2$&#10;}&#10;&#10;export interface Update{{pascalCase FEATURE_NAME}}Request {&#10;  $END$&#10;}" description="MORPH TypeScript contract template" toReformat="false" toShortenFQNames="true">
+    <variable name="FIELD1" expression="" defaultValue="&quot;&quot;" alwaysStopAt="true" />
+    <variable name="FIELD2" expression="" defaultValue="&quot;&quot;" alwaysStopAt="true" />
+    <context>
+      <option name="TypeScript" value="true" />
+    </context>
+  </template>
+</templateSet>

package/framework/templates/.vscode/morph-templates.code-snippets

@@ -0,0 +1,186 @@
+{
+  "MORPH Template - PascalCase": {
+    "prefix": "morph-pascal",
+    "body": ["{{pascalCase ${1:FEATURE_NAME}}}"],
+    "description": "Convert to PascalCase (UserAuth)"
+  },
+  "MORPH Template - camelCase": {
+    "prefix": "morph-camel",
+    "body": ["{{camelCase ${1:FEATURE_NAME}}}"],
+    "description": "Convert to camelCase (userAuth)"
+  },
+  "MORPH Template - snake_case": {
+    "prefix": "morph-snake",
+    "body": ["{{snakeCase ${1:FEATURE_NAME}}}"],
+    "description": "Convert to snake_case (user_auth)"
+  },
+  "MORPH Template - Title Case": {
+    "prefix": "morph-title",
+    "body": ["{{titleCase ${1:FEATURE_NAME}}}"],
+    "description": "Convert to Title Case (User Auth)"
+  },
+  "MORPH Template - kebab-case": {
+    "prefix": "morph-kebab",
+    "body": ["{{kebabCase ${1:FEATURE_NAME}}}"],
+    "description": "Convert to kebab-case (user-auth)"
+  },
+  "MORPH Template - UPPER_SNAKE_CASE": {
+    "prefix": "morph-upper-snake",
+    "body": ["{{upperSnakeCase ${1:FEATURE_NAME}}}"],
+    "description": "Convert to UPPER_SNAKE_CASE (USER_AUTH)"
+  },
+  "MORPH Template - Conditional If": {
+    "prefix": "morph-if",
+    "body": [
+      "{{#if ${1:condition}}}",
+      "  $2",
+      "{{/if}}"
+    ],
+    "description": "Handlebars if block"
+  },
+  "MORPH Template - Conditional If-Else": {
+    "prefix": "morph-if-else",
+    "body": [
+      "{{#if ${1:condition}}}",
+      "  $2",
+      "{{else}}",
+      "  $3",
+      "{{/if}}"
+    ],
+    "description": "Handlebars if-else block"
+  },
+  "MORPH Template - Each Loop": {
+    "prefix": "morph-each",
+    "body": [
+      "{{#each ${1:items}}}",
+      "  {{this.$2}}",
+      "{{/each}}"
+    ],
+    "description": "Handlebars each loop"
+  },
+  "MORPH Template - Unless": {
+    "prefix": "morph-unless",
+    "body": [
+      "{{#unless ${1:condition}}}",
+      "  $2",
+      "{{/unless}}"
+    ],
+    "description": "Handlebars unless block"
+  },
+  "MORPH Template - .NET Service Class": {
+    "prefix": "morph-service",
+    "body": [
+      "namespace {{NAMESPACE}}.Application.Features.{{pascalCase FEATURE_NAME}}.Services;",
+      "",
+      "public class {{pascalCase FEATURE_NAME}}Service(",
+      "    I{{pascalCase FEATURE_NAME}}Repository repository,",
+      "    ILogger<{{pascalCase FEATURE_NAME}}Service> logger) : I{{pascalCase FEATURE_NAME}}Service",
+      "{",
+      "    public async Task<{{pascalCase FEATURE_NAME}}Dto?> GetByIdAsync(int id, CancellationToken cancellationToken = default)",
+      "    {",
+      "        $1",
+      "    }",
+      "}"
+    ],
+    "description": "MORPH .NET Service class template"
+  },
+  "MORPH Template - .NET Repository Class": {
+    "prefix": "morph-repository",
+    "body": [
+      "public class {{pascalCase FEATURE_NAME}}Repository(AppDbContext context) : I{{pascalCase FEATURE_NAME}}Repository",
+      "{",
+      "    private readonly DbSet<{{pascalCase FEATURE_NAME}}> _dbSet = context.Set<{{pascalCase FEATURE_NAME}}>();",
+      "",
+      "    public async Task<{{pascalCase FEATURE_NAME}}?> GetByIdAsync(int id, CancellationToken cancellationToken = default)",
+      "    {",
+      "        $1",
+      "    }",
+      "}"
+    ],
+    "description": "MORPH .NET Repository class template"
+  },
+  "MORPH Template - Blazor Component": {
+    "prefix": "morph-component",
+    "body": [
+      "@page \"/{{kebabCase FEATURE_NAME}}\"",
+      "@inject I{{pascalCase FEATURE_NAME}}Service {{pascalCase FEATURE_NAME}}Service",
+      "@inject ILogger<{{pascalCase FEATURE_NAME}}Page> Logger",
+      "",
+      "<PageTitle>{{pascalCase FEATURE_NAME}}</PageTitle>",
+      "",
+      "<div class=\"container-fluid\">",
+      "    $1",
+      "</div>",
+      "",
+      "@code {",
+      "    $2",
+      "}"
+    ],
+    "description": "MORPH Blazor component template"
+  },
+  "MORPH Template - EF Core Migration": {
+    "prefix": "morph-migration",
+    "body": [
+      "public partial class Add{{pascalCase FEATURE_NAME}} : Migration",
+      "{",
+      "    protected override void Up(MigrationBuilder migrationBuilder)",
+      "    {",
+      "        migrationBuilder.CreateTable(",
+      "            name: \"{{pascalCase FEATURE_NAME}}s\",",
+      "            columns: table => new",
+      "            {",
+      "                Id = table.Column<int>(type: \"int\", nullable: false)",
+      "                    .Annotation(\"SqlServer:Identity\", \"1, 1\"),",
+      "                $1",
+      "            },",
+      "            constraints: table =>",
+      "            {",
+      "                table.PrimaryKey(\"PK_{{pascalCase FEATURE_NAME}}s\", x => x.Id);",
+      "            });",
+      "    }",
+      "",
+      "    protected override void Down(MigrationBuilder migrationBuilder)",
+      "    {",
+      "        migrationBuilder.DropTable(name: \"{{pascalCase FEATURE_NAME}}s\");",
+      "    }",
+      "}"
+    ],
+    "description": "MORPH EF Core migration template"
+  },
+  "MORPH Template - Hangfire Job": {
+    "prefix": "morph-job",
+    "body": [
+      "public class {{pascalCase FEATURE_NAME}}ProcessorJob(",
+      "    I{{pascalCase FEATURE_NAME}}Service service,",
+      "    ILogger<{{pascalCase FEATURE_NAME}}ProcessorJob> logger) : I{{pascalCase FEATURE_NAME}}ProcessorJob",
+      "{",
+      "    [AutomaticRetry(Attempts = 3, DelaysInSeconds = new[] { 60, 300, 900 })]",
+      "    [Queue(\"default\")]",
+      "    [JobDisplayName(\"{{pascalCase FEATURE_NAME}} Processing - ID: {0}\")]",
+      "    public async Task ExecuteAsync(int id, CancellationToken cancellationToken)",
+      "    {",
+      "        $1",
+      "    }",
+      "}"
+    ],
+    "description": "MORPH Hangfire job template"
+  },
+  "MORPH Template - TypeScript Contract": {
+    "prefix": "morph-ts-contract",
+    "body": [
+      "export interface {{pascalCase FEATURE_NAME}} {",
+      "  id: number;",
+      "  $1",
+      "}",
+      "",
+      "export interface Create{{pascalCase FEATURE_NAME}}Request {",
+      "  $2",
+      "}",
+      "",
+      "export interface Update{{pascalCase FEATURE_NAME}}Request {",
+      "  $3",
+      "}"
+    ],
+    "description": "MORPH TypeScript contract template"
+  }
+}