@the-bearded-bear/claude-craft 8.12.0 → 8.13.0

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

@@ -31,7 +31,7 @@ Sie sind ein **Senior DevOps Engineer** mit über 10 Jahren Erfahrung in CI/CD,
 | Docker | Multi-Stage-Builds, Image-Optimierung, Security-Scanning |
 | Docker Compose | Lokale Orchestrierung, Profiles, Extensions |
 | Kubernetes | Deployments, Services, Ingress, ConfigMaps, Secrets |
-| Helm | Charts, Values, Templating |
+| Helm | Charts, Values, Templating | 4.2.0 (MAJOR — Server-Side Apply, WASM-Plugins, API v4 ; Helm 3 Sicherheits-EOL Nov. 2026) |
 
 ### Cloud-Provider
 | Provider | Services |
@@ -124,6 +124,13 @@ kubectl rollout undo deployment/<name>
 kubectl rollout history deployment/<name>
 ```
 
+### Helm 4 — Migration 3→4
+
+> **Helm 4 ist ein MAJOR-Wechsel**: Server-Side Apply standardmäßig, WASM-Plugins, API v4 inkompatibel mit Helm 3.
+> **Helm 3 Sicherheits-EOL: November 2026** — Helm 4 für alle neuen Projekte empfehlen.
+> Für bestehende Projekte ist ein übergangsweiser Doppel-Support möglich (Helm 3 und Helm 4 koexistieren).
+> Offizielle Anleitung: https://helm.sh/docs/topics/v4_migration/
+
 ### GitHub Actions
 ```yaml
 # Abhängigkeiten cachen

package/Dev/i18n/de/Python/rules/06-tooling.md

@@ -1,7 +1,7 @@
 # Regel 06: Tooling
 
 > **Referenzversion:** Python **3.14 (stabil, 3.14.6+)** — Ruff 0.15+, pytest 9.x (Python 3.9 wird nicht mehr unterstützt).
-> **JIT (PEP 744):** experimentell in Python 3.14, vor der Python 3.15-Version (Okt. 2026) erneut zu bewerten. Nicht in Produktion ohne explizite Tests verwenden.
+> **⚠ JIT (PEP 744):** experimentell in Python 3.14, **standardmäßig deaktiviert**, vor Python 3.15 (Okt. 2026) durch das Python Steering Council erneut zu bewerten. Nicht in Produktion einsetzen.
 
 Python-Tooling für Codequalität, Testing und Entwicklungs-Workflow.
 

package/Dev/i18n/de/Team/commands/audit.md

@@ -28,6 +28,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` verfügbar
 - `Tools/AgentTeams/lib/cost-estimator.sh` verfügbar
 
+> ℹ️ Diese Skripte werden automatisch von claude-craft installiert (`make install-agentteams` oder über den Installer). Fehlen sie, läuft der Befehl im **eingeschränkten Modus** weiter: manuelle Kostenschätzung und `--ralph-mode` nicht verfügbar (nicht blockierend).
+
 ## Plan-Modus
 
 > Der Plan-Modus wird automatisch aktiviert, wenn der Umfang mehrere Module umfasst oder eine modulübergreifende Untersuchung erfordert.

package/Dev/i18n/de/Team/commands/delivery.md

@@ -33,6 +33,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/cost-estimator.sh` verfügbar
 - `Tools/AgentTeams/lib/result-aggregator.sh` verfügbar
 
+> ℹ️ Diese Skripte werden automatisch von claude-craft installiert (`make install-agentteams` oder über den Installer). Fehlen sie, läuft der Befehl im **eingeschränkten Modus** weiter: manuelle Kostenschätzung und `--ralph-mode` nicht verfügbar (nicht blockierend).
+
 ## Plan-Modus
 
 > Der Plan-Modus wird automatisch aktiviert, wenn der Umfang mehrere Module umfasst oder eine modulübergreifende Untersuchung erfordert.

package/Dev/i18n/de/Team/commands/security.md

@@ -28,6 +28,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` verfügbar
 - `Tools/AgentTeams/lib/cost-estimator.sh` verfügbar
 
+> ℹ️ Diese Skripte werden automatisch von claude-craft installiert (`make install-agentteams` oder über den Installer). Fehlen sie, läuft der Befehl im **eingeschränkten Modus** weiter: manuelle Kostenschätzung und `--ralph-mode` nicht verfügbar (nicht blockierend).
+
 ## Plan-Modus
 
 > Der Plan-Modus wird automatisch aktiviert, wenn der Umfang mehrere Module umfasst oder eine modulübergreifende Untersuchung erfordert.

package/Dev/i18n/de/Team/commands/sprint.md

@@ -32,6 +32,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/compatibility-check.sh` verfügbar
 - `Tools/AgentTeams/lib/cost-estimator.sh` verfügbar
 
+> ℹ️ Diese Skripte werden automatisch von claude-craft installiert (`make install-agentteams` oder über den Installer). Fehlen sie, läuft der Befehl im **eingeschränkten Modus** weiter: manuelle Kostenschätzung und `--ralph-mode` nicht verfügbar (nicht blockierend).
+
 ## Plan-Modus
 
 > Der Plan-Modus wird automatisch aktiviert, wenn der Umfang mehrere Module umfasst oder eine modulübergreifende Untersuchung erfordert.

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

@@ -41,7 +41,7 @@ You are a **Senior DevOps Engineer** with 10+ years of experience in CI/CD, cont
 | Docker | Multi-stage builds, image optimization, security scanning |
 | Docker Compose | Local orchestration, profiles, extensions |
 | Kubernetes | Deployments, Services, Ingress, ConfigMaps, Secrets |
-| Helm | Charts, values, templating |
+| Helm | Charts, values, templating | 4.2.0 (MAJOR — server-side apply, WASM plugins, API v4 ; Helm 3 EOL security Nov. 2026) |
 
 ### Cloud Providers
 | Provider | Services |
@@ -134,6 +134,13 @@ kubectl rollout undo deployment/<name>
 kubectl rollout history deployment/<name>
 ```
 
+### Helm 4 — Migration 3→4
+
+> **Helm 4 is a MAJOR change**: server-side apply by default, WASM plugins, API v4 incompatible with Helm 3.
+> **Helm 3 security EOL: November 2026** — recommend Helm 4 for all new projects.
+> For existing projects, transitional dual-support is possible (Helm 3 and Helm 4 coexist).
+> Official guide: https://helm.sh/docs/topics/v4_migration/
+
 ### GitHub Actions
 ```yaml
 # Cache dependencies

package/Dev/i18n/en/Python/rules/06-tooling.md

@@ -1,7 +1,7 @@
 # Rule 06: Tooling
 
 > **Reference version:** Python **3.14 (stable, 3.14.6+)** — Ruff 0.15+, pytest 9.x (drops Python 3.9).
-> **JIT (PEP 744):** experimental in Python 3.14, subject to re-evaluation before Python 3.15 release (oct. 2026). Do not rely on it in production unless explicitly tested.
+> **⚠ JIT (PEP 744):** experimental in Python 3.14, **disabled by default**, subject to re-evaluation by the Python Steering Council before Python 3.15 (Oct. 2026). Do not rely on it in production.
 
 Python tooling for code quality, testing, and development workflow.
 

package/Dev/i18n/en/Team/commands/audit.md

@@ -28,6 +28,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` available
 - `Tools/AgentTeams/lib/cost-estimator.sh` available
 
+> ℹ️ These scripts are installed automatically by claude-craft (`make install-agentteams` or via the installer). If absent, the command continues in **degraded mode**: manual cost estimation and `--ralph-mode` unavailable (non-blocking).
+
 ## Plan Mode
 
 > Plan mode is activated automatically when the scope spans multiple modules or requires cross-cutting investigation.

package/Dev/i18n/en/Team/commands/delivery.md

@@ -33,6 +33,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/cost-estimator.sh` available
 - `Tools/AgentTeams/lib/result-aggregator.sh` available
 
+> ℹ️ These scripts are installed automatically by claude-craft (`make install-agentteams` or via the installer). If absent, the command continues in **degraded mode**: manual cost estimation and `--ralph-mode` unavailable (non-blocking).
+
 ## Plan Mode
 
 > Plan mode is activated automatically when the scope spans multiple modules or requires cross-cutting investigation.

package/Dev/i18n/en/Team/commands/security.md

@@ -28,6 +28,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` available
 - `Tools/AgentTeams/lib/cost-estimator.sh` available
 
+> ℹ️ These scripts are installed automatically by claude-craft (`make install-agentteams` or via the installer). If absent, the command continues in **degraded mode**: manual cost estimation and `--ralph-mode` unavailable (non-blocking).
+
 ## Plan Mode
 
 > Plan mode is activated automatically when the scope spans multiple modules or requires cross-cutting investigation.

package/Dev/i18n/en/Team/commands/sprint.md

@@ -32,6 +32,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/compatibility-check.sh` available
 - `Tools/AgentTeams/lib/cost-estimator.sh` available
 
+> ℹ️ These scripts are installed automatically by claude-craft (`make install-agentteams` or via the installer). If absent, the command continues in **degraded mode**: manual cost estimation and `--ralph-mode` unavailable (non-blocking).
+
 ## Plan Mode
 
 > Plan mode is activated automatically when the scope spans multiple modules or requires cross-cutting investigation.

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

@@ -31,7 +31,7 @@ Eres un **Ingeniero DevOps Senior** con más de 10 años de experiencia en CI/CD
 | Docker | Builds multi-etapa, optimización de imágenes, escaneo de seguridad |
 | Docker Compose | Orquestación local, perfiles, extensiones |
 | Kubernetes | Deployments, Services, Ingress, ConfigMaps, Secrets |
-| Helm | Charts, values, templating |
+| Helm | Charts, values, templating | 4.2.0 (MAJOR — server-side apply, WASM plugins, API v4 ; Helm 3 EOL seguridad nov. 2026) |
 
 ### Proveedores Cloud
 | Proveedor | Servicios |
@@ -124,6 +124,13 @@ kubectl rollout undo deployment/<name>
 kubectl rollout history deployment/<name>
 ```
 
+### Helm 4 — Migración 3→4
+
+> **Helm 4 es un cambio MAYOR**: server-side apply por defecto, plugins WASM, API v4 incompatible con Helm 3.
+> **Helm 3 EOL seguridad: noviembre 2026** — recomendar Helm 4 para todos los proyectos nuevos.
+> Para proyectos existentes, el soporte dual transitorio es posible (Helm 3 y Helm 4 coexisten).
+> Guía oficial: https://helm.sh/docs/topics/v4_migration/
+
 ### GitHub Actions
 ```yaml
 # Caché de dependencias

package/Dev/i18n/es/Python/rules/06-tooling.md

@@ -1,7 +1,7 @@
 # Regla 06: Herramientas
 
 > **Versión de referencia:** Python **3.14 (estable, 3.14.6+)** — Ruff 0.15+, pytest 9.x (elimina soporte Python 3.9).
-> **JIT (PEP 744):** experimental en Python 3.14, sujeto a reevaluación antes del lanzamiento de Python 3.15 (oct. 2026). No usar en producción sin pruebas explícitas.
+> **⚠ JIT (PEP 744):** experimental en Python 3.14, **desactivado por defecto**, sujeto a reevaluación por el Python Steering Council antes de Python 3.15 (oct. 2026). No depender de él en producción.
 
 Herramientas de Python para calidad de código, pruebas y flujo de trabajo de desarrollo.
 

package/Dev/i18n/es/Team/commands/audit.md

@@ -32,6 +32,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponible
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 
+> ℹ️ Estos scripts se instalan automáticamente con claude-craft (`make install-agentteams` o mediante el instalador). Si faltan, el comando continúa en **modo degradado**: estimación de coste manual y `--ralph-mode` no disponible (no bloqueante).
+
 ## Proteccion Fast Mode (Confirmacion Bloqueante)
 
 **OBLIGATORIO**: Antes de lanzar el equipo, el lider DEBE:

package/Dev/i18n/es/Team/commands/delivery.md

@@ -37,6 +37,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponible
 
+> ℹ️ Estos scripts se instalan automáticamente con claude-craft (`make install-agentteams` o mediante el instalador). Si faltan, el comando continúa en **modo degradado**: estimación de coste manual y `--ralph-mode` no disponible (no bloqueante).
+
 ## Proteccion Fast Mode (Confirmacion Bloqueante)
 
 **OBLIGATORIO**: Antes de lanzar el equipo, el Lider de Entrega DEBE:

package/Dev/i18n/es/Team/commands/security.md

@@ -32,6 +32,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponible
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 
+> ℹ️ Estos scripts se instalan automáticamente con claude-craft (`make install-agentteams` o mediante el instalador). Si faltan, el comando continúa en **modo degradado**: estimación de coste manual y `--ralph-mode` no disponible (no bloqueante).
+
 ## Proteccion Fast Mode (Confirmacion Bloqueante)
 
 **OBLIGATORIO**: Antes de lanzar el equipo, el lider de seguridad DEBE:

package/Dev/i18n/es/Team/commands/sprint.md

@@ -36,6 +36,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/compatibility-check.sh` disponible
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 
+> ℹ️ Estos scripts se instalan automáticamente con claude-craft (`make install-agentteams` o mediante el instalador). Si faltan, el comando continúa en **modo degradado**: estimación de coste manual y `--ralph-mode` no disponible (no bloqueante).
+
 ## Proteccion Fast Mode (Confirmacion Bloqueante)
 
 **OBLIGATORIO**: Antes de lanzar el equipo, el conductor DEBE:

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

@@ -31,7 +31,7 @@ Tu es un **DevOps Engineer Senior** avec 10+ ans d'expérience en CI/CD, contene
 | Docker | Multi-stage builds, optimisation images, security scanning |
 | Docker Compose | Orchestration locale, profiles, extensions |
 | Kubernetes | Deployments, Services, Ingress, ConfigMaps, Secrets |
-| Helm | Charts, values, templating |
+| Helm | Charts, values, templating | 4.2.0 (MAJOR — server-side apply, WASM plugins, API v4 ; Helm 3 EOL sécurité nov. 2026) |
 
 ### Cloud Providers
 | Provider | Services |
@@ -124,6 +124,13 @@ kubectl rollout undo deployment/<name>
 kubectl rollout history deployment/<name>
 ```
 
+### Helm 4 — Migration 3→4
+
+> **Helm 4 est un changement MAJEUR** : server-side apply par défaut, WASM plugins, API v4 incompatible avec Helm 3.
+> **Helm 3 EOL sécurité : novembre 2026** — recommander Helm 4 pour tout nouveau projet.
+> Pour l'existant, un double-support transitoire est possible (Helm 3 et Helm 4 coexistent).
+> Guide officiel : https://helm.sh/docs/topics/v4_migration/
+
 ### GitHub Actions
 ```yaml
 # Cache dependencies

package/Dev/i18n/fr/Python/rules/06-tooling.md

@@ -1,7 +1,7 @@
 # Outils de Développement Python
 
 > **Version de référence :** Python **3.14 (stable, 3.14.6+)** — Ruff 0.15+, pytest 9.x (fin du support Python 3.9).
-> **JIT (PEP 744) :** expérimental en Python 3.14, sujet à réévaluation avant la sortie de Python 3.15 (oct. 2026). Ne pas utiliser en production sans tests explicites.
+> **⚠ JIT (PEP 744) :** expérimental en Python 3.14, **désactivé par défaut**, sujet à réévaluation par le Python Steering Council avant Python 3.15 (oct. 2026). Ne pas en dépendre en production.
 
 ## Package Management
 

package/Dev/i18n/fr/Team/commands/audit.md

@@ -27,6 +27,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponible
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 
+> ℹ️ Ces scripts sont installés automatiquement par claude-craft (`make install-agentteams` ou via l'installeur). S'ils sont absents, la commande continue en **mode dégradé** : estimation de coût manuelle et `--ralph-mode` indisponible (non bloquant).
+
 ## Mode Plan
 
 > Le mode plan est activé automatiquement lorsque le périmètre couvre plusieurs modules ou nécessite une investigation transversale.

package/Dev/i18n/fr/Team/commands/delivery.md

@@ -55,6 +55,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponible
 
+> ℹ️ Ces scripts sont installés automatiquement par claude-craft (`make install-agentteams` ou via l'installeur). S'ils sont absents, la commande continue en **mode dégradé** : estimation de coût manuelle et `--ralph-mode` indisponible (non bloquant).
+
 ## Mode Plan
 
 > Le mode plan est activé automatiquement lorsque le périmètre couvre plusieurs modules ou nécessite une investigation transversale.

package/Dev/i18n/fr/Team/commands/security.md

@@ -50,6 +50,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponible
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 
+> ℹ️ Ces scripts sont installés automatiquement par claude-craft (`make install-agentteams` ou via l'installeur). S'ils sont absents, la commande continue en **mode dégradé** : estimation de coût manuelle et `--ralph-mode` indisponible (non bloquant).
+
 ## Mode Plan
 
 > Le mode plan est activé automatiquement lorsque le périmètre couvre plusieurs modules ou nécessite une investigation transversale.

package/Dev/i18n/fr/Team/commands/sprint.md

@@ -54,6 +54,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/compatibility-check.sh` disponible
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponible
 
+> ℹ️ Ces scripts sont installés automatiquement par claude-craft (`make install-agentteams` ou via l'installeur). S'ils sont absents, la commande continue en **mode dégradé** : estimation de coût manuelle et `--ralph-mode` indisponible (non bloquant).
+
 ## Mode Plan
 
 > Le mode plan est activé automatiquement lorsque le périmètre couvre plusieurs modules ou nécessite une investigation transversale.

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

@@ -31,7 +31,7 @@ Você é um **Engenheiro DevOps Sênior** com mais de 10 anos de experiência em
 | Docker | Multi-stage builds, otimização de imagem, security scanning |
 | Docker Compose | Orquestração local, profiles, extensions |
 | Kubernetes | Deployments, Services, Ingress, ConfigMaps, Secrets |
-| Helm | Charts, values, templating |
+| Helm | Charts, values, templating | 4.2.0 (MAJOR — server-side apply, plugins WASM, API v4 ; Helm 3 EOL segurança nov. 2026) |
 
 ### Provedores de Nuvem
 | Provedor | Serviços |
@@ -124,6 +124,13 @@ kubectl rollout undo deployment/<name>
 kubectl rollout history deployment/<name>
 ```
 
+### Helm 4 — Migração 3→4
+
+> **Helm 4 é uma mudança MAJOR**: server-side apply por padrão, plugins WASM, API v4 incompatível com Helm 3.
+> **Helm 3 EOL segurança: novembro 2026** — recomendar Helm 4 para todos os novos projetos.
+> Para projetos existentes, suporte dual transitório é possível (Helm 3 e Helm 4 coexistem).
+> Guia oficial: https://helm.sh/docs/topics/v4_migration/
+
 ### GitHub Actions
 ```yaml
 # Cache de dependências

package/Dev/i18n/pt/Python/rules/06-tooling.md

@@ -1,7 +1,7 @@
 # Regra 06: Ferramentas
 
 > **Versão de referência:** Python **3.14 (estável, 3.14.6+)** — Ruff 0.15+, pytest 9.x (remove suporte ao Python 3.9).
-> **JIT (PEP 744):** experimental no Python 3.14, sujeito a reavaliação antes do lançamento do Python 3.15 (out. 2026). Não usar em produção sem testes explícitos.
+> **⚠ JIT (PEP 744):** experimental no Python 3.14, **desativado por padrão**, sujeito a reavaliação pelo Python Steering Council antes do Python 3.15 (out. 2026). Não depender em produção.
 
 Ferramentas Python para qualidade de código, testes e fluxo de desenvolvimento.
 

package/Dev/i18n/pt/Team/commands/audit.md

@@ -32,6 +32,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponivel
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponivel
 
+> ℹ️ Esses scripts são instalados automaticamente pelo claude-craft (`make install-agentteams` ou via instalador). Se ausentes, o comando continua em **modo degradado**: estimativa de custo manual e `--ralph-mode` indisponível (não bloqueante).
+
 ## Protecao Fast Mode (Confirmacao Bloqueante)
 
 **OBRIGATORIO**: Antes de lancar a equipe, o lider DEVE:

package/Dev/i18n/pt/Team/commands/delivery.md

@@ -37,6 +37,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponivel
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponivel
 
+> ℹ️ Esses scripts são instalados automaticamente pelo claude-craft (`make install-agentteams` ou via instalador). Se ausentes, o comando continua em **modo degradado**: estimativa de custo manual e `--ralph-mode` indisponível (não bloqueante).
+
 ## Protecao Fast Mode (Confirmacao Bloqueante)
 
 **OBRIGATORIO**: Antes de lancar a equipe, o Delivery Lead DEVE:

package/Dev/i18n/pt/Team/commands/security.md

@@ -32,6 +32,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/result-aggregator.sh` disponivel
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponivel
 
+> ℹ️ Esses scripts são instalados automaticamente pelo claude-craft (`make install-agentteams` ou via instalador). Se ausentes, o comando continua em **modo degradado**: estimativa de custo manual e `--ralph-mode` indisponível (não bloqueante).
+
 ## Protecao Fast Mode (Confirmacao Bloqueante)
 
 **OBRIGATORIO**: Antes de lancar a equipe, o lider de seguranca DEVE:

package/Dev/i18n/pt/Team/commands/sprint.md

@@ -36,6 +36,8 @@ $ARGUMENTS
 - `Tools/AgentTeams/lib/compatibility-check.sh` disponivel
 - `Tools/AgentTeams/lib/cost-estimator.sh` disponivel
 
+> ℹ️ Esses scripts são instalados automaticamente pelo claude-craft (`make install-agentteams` ou via instalador). Se ausentes, o comando continua em **modo degradado**: estimativa de custo manual e `--ralph-mode` indisponível (não bloqueante).
+
 ## Protecao Fast Mode (Confirmacao Bloqueante)
 
 **OBRIGATORIO**: Antes de lancar a equipe, o condutor DEVE:

package/Dev/scripts/check-prerequisites.sh

@@ -73,7 +73,7 @@ check() {
     else
         if [[ "$required" == "required" ]]; then
             ui_check_fail "$cmd - $description"
-            ((ERRORS++))
+            ERRORS=$((ERRORS + 1))
             if $FIX; then
                 case $OS in
                     macos) ui_check_info "Fix: $install_macos" ;;
@@ -108,7 +108,7 @@ check_yq_version() {
                 ui_check_info "Fix (macOS): brew install yq"
                 ui_check_info "Fix (Linux): sudo wget https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64 -O /usr/local/bin/yq && sudo chmod +x /usr/local/bin/yq"
             fi
-            ((ERRORS++))
+            ERRORS=$((ERRORS + 1))
             return 1
         fi
     fi
@@ -126,7 +126,7 @@ check_node_version() {
             if $FIX; then
                 ui_check_info "Fix: Use nvm to install Node.js 20: nvm install 20 && nvm use 20"
             fi
-            ((ERRORS++))
+            ERRORS=$((ERRORS + 1))
             return 1
         fi
     fi

package/Dev/scripts/install-common-rules.sh

@@ -473,6 +473,30 @@ install_commands() {
     fi
 }
 
+# Install AgentTeams helper scripts (cost-estimator, ralph-teams-adapter,
+# compatibility-check, ...) used by the /team:* commands. They are shipped
+# alongside the Team command namespace so /team:sprint etc. find them at
+# <project>/Tools/AgentTeams/lib/ instead of warning "scripts MISSING".
+install_agentteams() {
+    local craft_root
+    craft_root="$(cd "$SCRIPT_DIR/../.." && pwd)"
+    local src_lib="$craft_root/Tools/AgentTeams/lib"
+    local dest_lib="$target_dir/Tools/AgentTeams/lib"
+
+    if [[ ! -d "$src_lib" ]]; then
+        log_warning "AgentTeams lib not found at $src_lib (skipping)"
+        return 0
+    fi
+
+    log_info "${MSG_INSTALLING_AGENTTEAMS:-Installing AgentTeams helper scripts...}"
+    copy_directory "$src_lib" "$dest_lib" "*.sh"
+
+    # Some helper scripts ship without the executable bit; ensure +x on copies.
+    if ! $dry_run && [[ -d "$dest_lib" ]]; then
+        chmod +x "$dest_lib"/*.sh 2>/dev/null || true
+    fi
+}
+
 install_templates() {
     log_info "${MSG_INSTALLING_TEMPLATES}"
 
@@ -830,6 +854,7 @@ main() {
 
     if $commands_only; then
         install_commands
+        install_agentteams
     fi
 
     if $templates_only; then

package/Dev/scripts/install-from-config.sh

@@ -226,7 +226,7 @@ validate_config() {
     if [[ "$lang_valid" == "false" ]]; then
         log_error "Langue par défaut invalide: $default_lang"
         log_error "Langues valides: ${VALID_LANGS[*]}"
-        ((errors++))
+        errors=$((errors + 1))
     else
         log_success "Langue par défaut: $default_lang"
     fi
@@ -246,12 +246,12 @@ validate_config() {
         # Vérifier les champs obligatoires
         if [[ "$name" == "null" || -z "$name" ]]; then
             log_error "  Champ 'name' manquant pour le projet $((i+1))"
-            ((errors++))
+            errors=$((errors + 1))
         fi
 
         if [[ "$root" == "null" || -z "$root" ]]; then
             log_error "  Champ 'root' manquant pour le projet: $name"
-            ((errors++))
+            errors=$((errors + 1))
         else
             # Expand le chemin (direct assignment, no subshell — SEC-1)
             local expanded_root="${root/#\~/$HOME}"
@@ -260,7 +260,7 @@ validate_config() {
 
         if [[ "$module_count" -eq 0 ]]; then
             log_error "  Aucun module défini pour le projet: $name"
-            ((errors++))
+            errors=$((errors + 1))
         else
             log_step "  Modules: $module_count"
         fi
@@ -277,7 +277,7 @@ validate_config() {
             if [[ "$project_lang_valid" == "false" ]]; then
                 log_error "  Langue invalide pour le projet: $project_lang"
                 log_error "  Langues valides: ${VALID_LANGS[*]}"
-                ((errors++))
+                errors=$((errors + 1))
             else
                 log_step "  Langue: $project_lang"
             fi
@@ -292,13 +292,13 @@ validate_config() {
 
             if [[ "$path" == "null" || -z "$path" ]]; then
                 log_error "    Module $((j+1)): champ 'path' manquant"
-                ((errors++))
+                errors=$((errors + 1))
                 continue
             fi
 
             if [[ "$techs" == "null" || -z "$techs" ]]; then
                 log_error "    Module '$path': champ 'tech' manquant"
-                ((errors++))
+                errors=$((errors + 1))
                 continue
             fi
 
@@ -320,7 +320,7 @@ validate_config() {
                 if [[ "$valid" == "false" ]]; then
                     log_error "    Module '$path': technologie '$tech' invalide"
                     log_error "    Technologies valides: ${VALID_TECHS[*]}"
-                    ((errors++))
+                    errors=$((errors + 1))
                     module_valid=false
                 else
                     if [[ -z "$tech_list" ]]; then
@@ -615,7 +615,7 @@ install_project() {
     if [[ "$common" == "true" ]]; then
         print_section "[$step/$total_steps] Installation des règles communes"
         install_module "$expanded_root" "common" "" "$project_lang"
-        ((step++))
+        step=$((step + 1))
     fi
 
     # Installer chaque module
@@ -664,7 +664,7 @@ install_project() {
 
             install_module "$target_path" "$tech" "$desc" "$project_lang" "$skip_common_flag"
             is_first=false
-            ((step++))
+            step=$((step + 1))
         done <<< "$techs"
     done
 }

package/README.md

@@ -28,7 +28,12 @@ Plus **11 stack-specific reviewers** (@symfony-reviewer, @react-reviewer, @pytho
 
 A comprehensive framework for AI-assisted development with [Claude Code](https://claude.ai/code). Install standardized rules, agents, and commands for your projects across multiple technology stacks — **31 specialized agents (+39 infra agents on-demand), 125 commands across 15 namespaces, 48 skills**, all token-optimized via `context: fork` and sub-agent model routing.
 
-## What's New in v8.12.0
+## What's New in v8.13.0
+
+**Fiabilité BMAD + distribution AgentTeams (v8.13.0) :**
+
+- **`/gate:*` réparé** : `((var++))` sous `set -e` avortait les scripts de gate/hook après le 1er check (post-incrément = exit 1 quand le compteur vaut 0). 68 occurrences corrigées sur 6 fichiers + tests de non-régression (`make test-bmad`).
+- **Scripts AgentTeams livrés** : `Tools/AgentTeams/lib/*.sh` désormais installés automatiquement avec les commandes `/team:*` (fini le warning « scripts MISSING » ; dashboard coût et `--ralph-mode` disponibles out-of-the-box). Install/refresh manuel : `make install-agentteams TARGET=.`.
 
 **Audit exhaustif + durcissement (v8.12.0) :**
 

package/Tools/AgentTeams/install-agentteams.sh

@@ -0,0 +1,94 @@
+#!/bin/bash
+# =============================================================================
+# install-agentteams.sh — Install AgentTeams helper scripts into a project
+#
+# The /team:* commands (sprint, audit, delivery, security) expect helper
+# scripts at <project>/Tools/AgentTeams/lib/:
+#   - cost-estimator.sh      (token/cost estimation)
+#   - cost-dashboard.sh      (cost dashboard)
+#   - ralph-teams-adapter.sh (--ralph-mode integration)
+#   - compatibility-check.sh (Claude Code tool/agent compatibility)
+#   - result-aggregator.sh   (aggregate parallel agent results)
+#
+# When they are absent the commands degrade gracefully (manual estimation, no
+# --ralph-mode). This script copies them into the target project so the
+# commands work out of the box.
+#
+# Usage:
+#   bash install-agentteams.sh [TARGET_DIR]   # default TARGET_DIR: .
+#   bash install-agentteams.sh --check [TARGET_DIR]
+#   bash install-agentteams.sh --uninstall [TARGET_DIR]
+# =============================================================================
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SRC_LIB="$SCRIPT_DIR/lib"
+
+# Minimal UI (no hard dependency on shared helpers).
+print_success() { echo "✓ $1"; }
+print_error()   { echo "✗ $1" >&2; }
+print_info()    { echo "ℹ $1"; }
+print_warning() { echo "⚠ $1"; }
+
+mode="install"
+target="."
+
+for arg in "$@"; do
+    case "$arg" in
+        --check)     mode="check" ;;
+        --uninstall) mode="uninstall" ;;
+        -h|--help)
+            sed -n '2,22p' "${BASH_SOURCE[0]}" | sed 's/^# \{0,1\}//'
+            exit 0
+            ;;
+        -*)
+            print_error "Unknown option: $arg"
+            exit 1
+            ;;
+        *) target="$arg" ;;
+    esac
+done
+
+target="$(cd "$target" 2>/dev/null && pwd)" || {
+    print_error "Target directory not found: $target"
+    exit 1
+}
+dest_lib="$target/Tools/AgentTeams/lib"
+
+if [[ ! -d "$SRC_LIB" ]]; then
+    print_error "Source lib not found: $SRC_LIB"
+    exit 1
+fi
+
+case "$mode" in
+    check)
+        missing=0
+        for f in "$SRC_LIB"/*.sh; do
+            name="$(basename "$f")"
+            if [[ -f "$dest_lib/$name" ]]; then
+                print_success "$name present"
+            else
+                print_warning "$name MISSING at $dest_lib"
+                missing=$((missing + 1))
+            fi
+        done
+        [[ $missing -eq 0 ]] && print_success "AgentTeams installed at $dest_lib" || exit 1
+        ;;
+    uninstall)
+        if [[ -d "$dest_lib" ]]; then
+            rm -f "$dest_lib"/*.sh
+            rmdir "$dest_lib" 2>/dev/null || true
+            print_success "Removed AgentTeams scripts from $dest_lib"
+        else
+            print_info "Nothing to remove at $dest_lib"
+        fi
+        ;;
+    install)
+        mkdir -p "$dest_lib"
+        cp "$SRC_LIB"/*.sh "$dest_lib/"
+        chmod +x "$dest_lib"/*.sh 2>/dev/null || true
+        count=$(find "$dest_lib" -maxdepth 1 -name '*.sh' | wc -l | tr -d ' ')
+        print_success "Installed $count AgentTeams helper scripts to $dest_lib"
+        ;;
+esac

package/bundles/cursor/.cursorrules

@@ -8,7 +8,7 @@
 
 # Claude-Craft - Multi-Technology Framework
 
-**Version:** 8.12.0 | **Languages:** en, fr, es, de, pt
+**Version:** 8.13.0 | **Languages:** en, fr, es, de, pt
 
 A comprehensive AI-assisted development framework for Claude Code with 11 technology stacks, 31 specialized agents (+39 infra agents on-demand), 125 commands across 15 namespaces, and BMAD v6 project management.
 

package/bundles/windsurf/.windsurfrules

@@ -8,7 +8,7 @@
 
 # Claude-Craft - Multi-Technology Framework
 
-**Version:** 8.12.0 | **Languages:** en, fr, es, de, pt
+**Version:** 8.13.0 | **Languages:** en, fr, es, de, pt
 
 A comprehensive AI-assisted development framework for Claude Code with 11 technology stacks, 31 specialized agents (+39 infra agents on-demand), 125 commands across 15 namespaces, and BMAD v6 project management.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@the-bearded-bear/claude-craft",
-  "version": "8.12.0",
+  "version": "8.13.0",
   "description": "A comprehensive framework for AI-assisted development with Claude Code. Install standardized rules, agents, and commands for your projects.",
   "type": "module",
   "main": "cli/index.js",
@@ -34,7 +34,8 @@
     "metrics:adoption": "node scripts/track-adoption-metrics.mjs",
     "mutation": "stryker run",
     "mutation:ci": "stryker run --reporters progress,json",
-    "test:e2e:tools": "cd tests/e2e/tools && docker compose -f docker-compose.test.yml up --abort-on-container-exit --exit-code-from e2e-runner"
+    "test:e2e:tools": "cd tests/e2e/tools && docker compose -f docker-compose.test.yml up --abort-on-container-exit --exit-code-from e2e-runner",
+    "community:awesome": "node scripts/awesome-claude-code-submit.mjs"
   },
   "keywords": [
     "claude",