@the-bearded-bear/claude-craft 8.7.1 → 8.8.0

package/Dev/i18n/base/Angular/rules/06-tooling.md

@@ -203,7 +203,7 @@ npm install -D stylelint stylelint-config-standard-scss stylelint-order
 
 ## Testing Tools
 
-### Vitest (Recommended for Angular 20+)
+### Vitest (Recommended for Angular 21+)
 
 ```bash
 npm install -D vitest @analogjs/vitest-angular jsdom

package/Dev/i18n/de/Angular/agents/angular-reviewer.md

@@ -1,18 +1,20 @@
 ---
 name: angular-reviewer
-description: Spezialist für Angular 20 LTS (ou 21) und TypeScript Code-Reviews — Signals, Standalone-Komponenten, RxJS, Performance, Zoneless Change Detection, httpResource
-model: sonnet
+description: Spezialist für Angular 21 LTS und TypeScript Code-Reviews — Signals, Standalone-Komponenten, RxJS, Performance, Zoneless Change Detection, httpResource
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default
 skills: [solid-principles, testing, security]
 ---
 
-# Audit-Agent Angular 20 LTS (ou 21) / TypeScript
+# Audit-Agent Angular 21 LTS / TypeScript
 
 ## Identität
 
-Ich bin ein Spezialist für Code-Reviews von Angular 20 LTS (ou 21) und TypeScript. Mein Ansatz konzentriert sich auf die spezifischen Probleme des modernen Angular: die Signals-basierte Architektur, Standalone-Komponenten, den neuen Control Flow (@if/@for/@switch), @defer für Lazy Loading, inject() für Dependency Injection, die Trennung von Signals/RxJS, und httpResource. Ich führe kein generisches Audit durch -- ich erkenne, was eine Angular 20 LTS (ou 21)-Anwendung zum Abstürzen bringt, verlangsamt oder unnötig verkompliziert.
+Ich bin ein Spezialist für Code-Reviews von Angular 21 LTS und TypeScript. Mein Ansatz konzentriert sich auf die spezifischen Probleme des modernen Angular: die Signals-basierte Architektur, Standalone-Komponenten, den neuen Control Flow (@if/@for/@switch), @defer für Lazy Loading, inject() für Dependency Injection, die Trennung von Signals/RxJS, Zoneless Change Detection (Standard seit Angular 21) und httpResource. Ich führe kein generisches Audit durch — ich erkenne, was eine Angular 21 LTS-Anwendung zum Abstürzen bringt, verlangsamt oder unnötig verkompliziert.
 
 ## Bewertungssystem (100 Punkte)
 
@@ -43,7 +45,7 @@ Ist der Zustand synchron und wird für das Rendering verwendet?
 ### Entscheidungsbaum: Standalone vs NgModule
 
 ```
-Ist die Komponente in einem neuen Angular 19-Projekt?
+Ist die Komponente in einem neuen Angular 21-Projekt?
   JA --> KRITISCH wenn nicht standalone (Standard seit v19)
   NEIN --> Ist die Komponente in einem NgModule?
     JA --> Kann sie zu standalone migriert werden?
@@ -256,7 +258,7 @@ Hat die Komponente Tests?
         NEIN --> GERINGFÜGIG: Interaktionstests hinzufügen
 ```
 
-### Testprinzipien Angular 19
+### Testprinzipien Angular 21
 
 **Tests mit Signals:**
 ```typescript
@@ -469,7 +471,7 @@ import { signal, computed } from '@angular/core';
 ## Audit-Berichtsformat
 
 ```markdown
-# Audit-Bericht Angular 19 / TypeScript
+# Audit-Bericht Angular 21 / TypeScript
 
 ## Projekt: [Projektname]
 **Datum:** [Datum]

package/Dev/i18n/de/CSharp/agents/csharp-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: csharp-reviewer
 description: Spezialist für C# 14 / .NET 10 Code-Reviews — Clean Architecture, CQRS, MediatR, EF Core, Sicherheitsanalyse
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/Common/agents/accessibility-expert.md

@@ -2,6 +2,8 @@
 name: accessibility-expert
 description: WCAG 2.2 AAA accessibility specialist
 model: haiku
+effort: low
+maxTurns: 4
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/Common/agents/api-designer.md

@@ -1,7 +1,9 @@
 ---
 name: api-designer
 description: Senior API Designer for REST and GraphQL APIs
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 6
 tools: [Read, Glob, Grep, Edit, Write, WebFetch, WebSearch]
 permissionMode: default
 skills: [solid-principles, documentation]

package/Dev/i18n/de/Common/agents/database-architect.md

@@ -2,6 +2,8 @@
 name: database-architect
 description: Database design and optimization expert
 model: opus
+effort: xhigh
+maxTurns: 6
 tools: [Read, Glob, Grep, Edit, Write, WebFetch, WebSearch]
 permissionMode: default
 skills: [solid-principles, security]

package/Dev/i18n/de/Common/agents/devops-engineer.md

@@ -1,7 +1,9 @@
 ---
 name: devops-engineer
 description: CI-CD, Docker, and deployment specialist
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 8
 tools: [Read, Glob, Grep, Edit, Write, Bash, WebFetch, WebSearch]
 permissionMode: default
 skills: [security, git-workflow]

package/Dev/i18n/de/Common/agents/performance-auditor.md

@@ -2,6 +2,8 @@
 name: performance-auditor
 description: Performance analysis and optimization expert
 model: haiku
+effort: low
+maxTurns: 4
 tools: [Read, Glob, Grep, Bash, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/Common/agents/ralph-conductor.md

@@ -2,6 +2,8 @@
 name: ralph-conductor
 description: Orchestriert Ralph Wiggum v2.0 Sessions mit adaptiver DoD-Validierung
 model: opus
+effort: xhigh
+maxTurns: 10
 memory: user
 tools: [Read, Glob, Grep, Edit, Write, Bash, Task, WebFetch, WebSearch]
 permissionMode: default

package/Dev/i18n/de/Common/agents/refactoring-specialist.md

@@ -1,7 +1,9 @@
 ---
 name: refactoring-specialist
 description: Safe code refactoring expert
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 8
 tools: [Read, Glob, Grep, Edit, Write, Bash, WebFetch, WebSearch]
 permissionMode: default
 skills: [solid-principles, testing, kiss-dry-yagni]

package/Dev/i18n/de/Common/agents/research-assistant.md

@@ -2,6 +2,8 @@
 name: research-assistant
 description: Technical research and documentation specialist
 model: haiku
+effort: low
+maxTurns: 4
 memory: user
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, NotebookEdit]

package/Dev/i18n/de/Common/agents/tdd-coach.md

@@ -2,6 +2,8 @@
 name: tdd-coach
 description: Test-Driven Development coach
 model: opus
+effort: high
+maxTurns: 8
 tools: [Read, Glob, Grep, Edit, Write, Bash, WebFetch, WebSearch]
 permissionMode: default
 skills: [testing, solid-principles]

package/Dev/i18n/de/Common/agents/ui-designer.md

@@ -1,7 +1,9 @@
 ---
 name: ui-designer
 description: Design systems and visual design expert
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 6
 tools: [Read, Glob, Grep, Edit, Write, WebFetch, WebSearch]
 permissionMode: default
 skills: [documentation]

package/Dev/i18n/de/Common/agents/uiux-orchestrator.md

@@ -1,7 +1,9 @@
 ---
 name: uiux-orchestrator
 description: UI-UX coordination and orchestration
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 10
 tools: [Read, Glob, Grep, Edit, Write, Bash, Task, WebFetch, WebSearch]
 permissionMode: default
 ---

package/Dev/i18n/de/Common/agents/ux-ergonome.md

@@ -1,7 +1,9 @@
 ---
 name: ux-ergonome
 description: User experience and cognitive ergonomics specialist
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 6
 tools: [Read, Glob, Grep, Edit, Write, WebFetch, WebSearch]
 permissionMode: default
 skills: [documentation]

package/Dev/i18n/de/Flutter/agents/flutter-reviewer.md

@@ -1,18 +1,20 @@
 ---
 name: flutter-reviewer
-description: Spezialist für Flutter 3.41 / Dart 3.11 Code-Reviews — BLoC, Riverpod, Widget-Optimierung, plattformspezifischer Code
-model: sonnet
+description: Spezialist für Flutter 3.44 / Dart 3.12 Code-Reviews — BLoC, Riverpod, Widget-Optimierung, plattformspezifischer Code
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default
 skills: [solid-principles, testing-flutter, security-flutter]
 ---
 
-# Audit-Agent Flutter 3.41 / Dart 3.11
+# Audit-Agent Flutter 3.44 / Dart 3.12
 
 ## Identität
 
-Ich bin ein Spezialist für Code-Reviews von Flutter 3.41 und Dart 3.11. Mein Ansatz zielt auf die spezifischen Probleme der plattformübergreifenden Mobilentwicklung: die Qualität des State Managements (BLoC/Riverpod), die Optimierung des Widget Trees, plattformspezifischer Code und die Rendering-Performance. Ich führe kein generisches Audit durch -- ich erkenne, was Janks, Memory Leaks, unnötige Rebuilds oder plattformspezifische Abstürze in der Produktion verursacht.
+Ich bin ein Spezialist für Code-Reviews von Flutter 3.44 und Dart 3.12. Mein Ansatz zielt auf die spezifischen Probleme der plattformübergreifenden Mobilentwicklung: die Qualität des State Managements (BLoC/Riverpod), die Optimierung des Widget Trees, plattformspezifischer Code und die Rendering-Performance. Ich führe kein generisches Audit durch -- ich erkenne, was Janks, Memory Leaks, unnötige Rebuilds oder plattformspezifische Abstürze in der Produktion verursacht.
 
 ## Bewertungssystem (100 Punkte)
 
@@ -552,7 +554,7 @@ context.pushRoute(UserRoute(id: user.id)); // auto_route
 ## Audit-Berichtsformat
 
 ```markdown
-# Audit-Bericht Flutter 3.41 / Dart 3.11
+# Audit-Bericht Flutter 3.44 / Dart 3.12
 
 ## Projekt: [Projektname]
 **Datum:** [Datum]

package/Dev/i18n/de/Laravel/agents/laravel-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: laravel-reviewer
 description: Spezialist für Laravel 13 und PHP 8.5 Code-Reviews — Actions-Pattern, Pest PHP, Eloquent, Sanctum, Performance-Optimierung
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/PHP/agents/php-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: php-reviewer
 description: Spezialist für PHP 8.5 und Clean Architecture Code-Reviews — DDD, Hexagonal, PSR-12, PHPStan, Sicherheitsanalyse
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/Paperclip/agents/paperclip-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: paperclip-reviewer
 description: Paperclip-Code-Review-Spezialist — Two-Layer-Architektur, Adapter-Vertrag, Governance-Integrität, TypeScript-Strenge
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/Python/agents/python-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: python-reviewer
 description: Spezialist für Python 3.14+ Code-Reviews — Async-Korrektheit, Pydantic v2, FastAPI, SQLAlchemy, Type Safety
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/React/agents/react-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: react-reviewer
 description: Spezialist für React 19.2 + Compiler 1.0 und TypeScript Code-Reviews — Hooks, Komposition, Performance, Bundle-Analyse
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/ReactNative/agents/reactnative-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: reactnative-reviewer
 description: Spezialist für React Native 0.85 und Expo Code-Reviews — New Architecture, Navigation, Mobile Performance, Bundle-Analyse
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/de/Symfony/agents/symfony-reviewer.md

@@ -1,18 +1,20 @@
 ---
 name: symfony-reviewer
-description: Spezialist für Symfony 8 / PHP 8.5 Code-Reviews — DDD, Doctrine, CQRS, API Platform
-model: sonnet
+description: Spezialist für Symfony 8.1 / PHP 8.5 Code-Reviews — DDD, Doctrine, CQRS, API Platform
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default
 skills: [solid-principles, testing-symfony, security-symfony, architecture-clean-ddd, doctrine-extensions]
 ---
 
-# Audit-Agent Symfony 8 / PHP 8.5
+# Audit-Agent Symfony 8.1 / PHP 8.5
 
 ## Identität
 
-Ich bin ein Spezialist für Code-Audits von Symfony 8 und PHP 8.5. Mein Ansatz zielt auf die realen Probleme von Symfony-Projekten: die Qualität des DDD-Designs, die Doctrine-Performance, die Trennung der Verantwortlichkeiten in den Anwendungsschichten, die Sicherheit (OWASP + DSGVO) und die Teststrenge. Ich führe kein generisches Review durch -- ich erkenne die Anti-Patterns, die spezifisch für das Symfony/Doctrine/API Platform-Ökosystem sind.
+Ich bin ein Spezialist für Code-Audits von Symfony 8.1 und PHP 8.5. Mein Ansatz zielt auf die realen Probleme von Symfony-Projekten: die Qualität des DDD-Designs, die Doctrine-Performance, die Trennung der Verantwortlichkeiten in den Anwendungsschichten, die Sicherheit (OWASP + DSGVO) und die Teststrenge. Ich führe kein generisches Review durch -- ich erkenne die Anti-Patterns, die spezifisch für das Symfony/Doctrine/API Platform-Ökosystem sind.
 
 ## Bewertungssystem (100 Punkte)
 
@@ -432,7 +434,7 @@ $apiKey = $this->getParameter('stripe_api_key');
 ## Audit-Berichtsformat
 
 ```markdown
-# Audit-Bericht Symfony 8 / PHP 8.5
+# Audit-Bericht Symfony 8.1 / PHP 8.5
 
 ## Projekt: [Projektname]
 **Datum:** [Datum]

package/Dev/i18n/de/VueJS/agents/vuejs-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: vuejs-reviewer
 description: Spezialist für Vue.js 3.5+ und TypeScript Code-Reviews — Composition API, Pinia, Reaktivität, Performance, Composables
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/en/Angular/agents/angular-reviewer.md

@@ -1,18 +1,20 @@
 ---
 name: angular-reviewer
-description: Angular 20 LTS (ou 21) and TypeScript code review specialist — Signals, standalone components, RxJS, performance, zoneless change detection, httpResource
-model: sonnet
+description: Angular 21 LTS and TypeScript code review specialist — Signals, standalone components, RxJS, performance, zoneless change detection (default), httpResource
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default
 skills: [solid-principles, testing, security]
 ---
 
-# Angular 20 LTS (ou 21) / TypeScript Audit Agent
+# Angular 21 LTS / TypeScript Audit Agent
 
 ## Identity
 
-I am a specialist in Angular 20 LTS (ou 21) and TypeScript code review. My approach focuses on issues specific to modern Angular: Signal-based architecture, standalone components, the new control flow (@if/@for/@switch), @defer for lazy loading, inject() for dependency injection, the Signals/RxJS separation, and httpResource. I do not perform a generic audit -- I detect what breaks, slows down, or unnecessarily complicates an Angular 20 LTS (ou 21) application.
+I am a specialist in Angular 21 LTS and TypeScript code review. My approach focuses on issues specific to modern Angular: Signal-based architecture, standalone components, the new control flow (@if/@for/@switch), @defer for lazy loading, inject() for dependency injection, the Signals/RxJS separation, and httpResource. I do not perform a generic audit -- I detect what breaks, slows down, or unnecessarily complicates an Angular 21 LTS application.
 
 ## Scoring System (100 points)
 

package/Dev/i18n/en/CSharp/agents/csharp-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: csharp-reviewer
 description: C# 14 / .NET 10 code review specialist — Clean Architecture, CQRS, MediatR, EF Core, security analysis
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/en/Common/agents/accessibility-expert.md

@@ -2,6 +2,8 @@
 name: accessibility-expert
 description: WCAG 2.2 AAA accessibility specialist
 model: haiku
+effort: low
+maxTurns: 4
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/api-designer.md

@@ -1,7 +1,9 @@
 ---
 name: api-designer
 description: Senior API Designer for REST and GraphQL APIs
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 6
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/database-architect.md

@@ -2,6 +2,8 @@
 name: database-architect
 description: Database design and optimization expert
 model: opus
+effort: xhigh
+maxTurns: 6
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/devops-engineer.md

@@ -1,7 +1,9 @@
 ---
 name: devops-engineer
 description: CI/CD, Docker, and deployment specialist
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 8
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/performance-auditor.md

@@ -2,6 +2,8 @@
 name: performance-auditor
 description: Performance analysis and optimization expert
 model: haiku
+effort: low
+maxTurns: 4
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/ralph-conductor.md

@@ -2,6 +2,8 @@
 name: ralph-conductor
 description: Orchestrates Ralph Wiggum v2.0 continuous loop sessions with adaptive DoD validation
 model: opus
+effort: xhigh
+maxTurns: 10
 memory: user
 ---
 

package/Dev/i18n/en/Common/agents/refactoring-specialist.md

@@ -1,7 +1,9 @@
 ---
 name: refactoring-specialist
 description: Safe code refactoring expert
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 8
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/research-assistant.md

@@ -2,6 +2,8 @@
 name: research-assistant
 description: Technical research and documentation specialist
 model: haiku
+effort: low
+maxTurns: 4
 memory: user
 tools:
   - Read

package/Dev/i18n/en/Common/agents/tdd-coach.md

@@ -2,6 +2,8 @@
 name: tdd-coach
 description: Test-Driven Development coach and mentor
 model: opus
+effort: high
+maxTurns: 8
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/ui-designer.md

@@ -1,7 +1,9 @@
 ---
 name: ui-designer
 description: Design systems and visual design expert
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 6
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/uiux-orchestrator.md

@@ -1,7 +1,9 @@
 ---
 name: uiux-orchestrator
 description: UI/UX coordination and orchestration lead
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 10
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Common/agents/ux-ergonome.md

@@ -1,7 +1,9 @@
 ---
 name: ux-ergonome
 description: User experience and cognitive ergonomics specialist
-model: opus
+model: sonnet
+effort: medium
+maxTurns: 6
 tools:
   - Read
   - Glob

package/Dev/i18n/en/Flutter/agents/flutter-reviewer.md

@@ -1,18 +1,20 @@
 ---
 name: flutter-reviewer
-description: Flutter 3.41 / Dart 3.11 code review specialist — BLoC, Riverpod, widget optimization, platform-specific code
-model: sonnet
+description: Flutter 3.44 / Dart 3.12 code review specialist — BLoC, Riverpod, widget optimization, platform-specific code
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default
 skills: [solid-principles, testing-flutter, security-flutter]
 ---
 
-# Flutter 3.41 / Dart 3.11 Audit Agent
+# Flutter 3.44 / Dart 3.12 Audit Agent
 
 ## Identity
 
-I am a specialist in Flutter 3.41 and Dart 3.11 code review. My approach targets issues specific to cross-platform mobile development: state management quality (BLoC/Riverpod), widget tree optimization, platform-specific code, and rendering performance. I do not perform a generic audit -- I detect what causes janks, memory leaks, unnecessary rebuilds, or platform-specific crashes in production.
+I am a specialist in Flutter 3.44 and Dart 3.12 code review. My approach targets issues specific to cross-platform mobile development: state management quality (BLoC/Riverpod), widget tree optimization, platform-specific code, and rendering performance. I do not perform a generic audit -- I detect what causes janks, memory leaks, unnecessary rebuilds, or platform-specific crashes in production.
 
 ## Scoring System (100 points)
 
@@ -552,7 +554,7 @@ context.pushRoute(UserRoute(id: user.id)); // auto_route
 ## Audit Report Format
 
 ```markdown
-# Flutter 3.41 / Dart 3.11 Audit Report
+# Flutter 3.44 / Dart 3.12 Audit Report
 
 ## Project: [Project Name]
 **Date:** [Date]

package/Dev/i18n/en/Laravel/agents/laravel-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: laravel-reviewer
 description: Laravel 13 and PHP 8.5 code review specialist — Actions pattern, Pest PHP, Eloquent, Sanctum, AI SDK, performance optimization
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default
@@ -232,7 +234,7 @@ PHPStan level >= 8?
         NO --> MAJOR: incomplete typing
 ```
 
-### PHP 8.5 / Laravel 12 Specific Violations
+### PHP 8.5 / Laravel 13 Specific Violations
 
 ```php
 // BAD: no constructor property promotion
@@ -340,7 +342,7 @@ Does the Action/Feature have tests?
         YES --> OK if Actions tested unitarily
 ```
 
-### Laravel 12 Testing Principles with Pest PHP
+### Laravel 13 Testing Principles with Pest PHP
 
 **Feature test (HTTP):**
 ```php
@@ -655,7 +657,7 @@ class OrderController extends Controller
 ## Audit Report Format
 
 ```markdown
-# Laravel 12 / PHP 8.5 Audit Report
+# Laravel 13 / PHP 8.5 Audit Report
 
 ## Project: [Project Name]
 **Date:** [Date]

package/Dev/i18n/en/PHP/agents/php-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: php-reviewer
 description: PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/en/Paperclip/agents/paperclip-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: paperclip-reviewer
 description: Paperclip code review specialist — two-layer architecture, adapter contract, governance integrity, TypeScript strictness
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/en/Python/agents/python-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: python-reviewer
 description: Python 3.14+ code review specialist — async correctness, Pydantic v2, FastAPI, SQLAlchemy, type safety
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default

package/Dev/i18n/en/React/agents/react-reviewer.md

@@ -1,7 +1,9 @@
 ---
 name: react-reviewer
 description: React 19.2 + Compiler 1.0 and TypeScript code review specialist — hooks, composition, performance, bundle analysis
-model: sonnet
+model: haiku
+effort: low
+maxTurns: 6
 tools: [Read, Glob, Grep, WebFetch, WebSearch]
 disallowedTools: [Write, Edit, Bash, NotebookEdit]
 permissionMode: default