bmad-plus 0.14.0 → 0.17.0

package/osint-agent-package/README.md

@@ -82,7 +82,7 @@ osint-agent-package/
 
 ## Crédits
 - Pipeline OSINT basé sur [smixs/osint-skill](https://github.com/smixs/osint-skill) (MIT License)
-- Apify Actor Runner intégré de [apify/agent-skills](https://github.com/apify/agent-skills) (MIT License)
+- Outil Python Apify issu du pipeline OSINT ci-dessus ; inspiration des [skills Apify](https://github.com/apify/agent-skills), dont le dépôt déclare Apache-2.0. Voir les [notices tierces BMAD+](../THIRD-PARTY-LICENSES.md).
 
 ## Licence
 MIT

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-plus",
-  "version": "0.14.0",
+  "version": "0.17.0",
   "description": "Project-local AI development workflows with clear roles, shared context, safe updates and coding-tool adapters",
   "homepage": "https://bmad-plus.rochetta.fr",
   "keywords": [
@@ -29,7 +29,12 @@
     "src/bmad-plus",
     "osint-agent-package",
     "readme-international",
-    "CHANGELOG.md"
+    "THIRD-PARTY-LICENSES.md",
+    "SECURITY.md",
+    "CHANGELOG.md",
+    "!**/__pycache__/**",
+    "!**/*.pyc",
+    "!**/*.pyo"
   ],
   "scripts": {
     "install:bmad": "node tools/cli/bmad-plus-cli.js install",
@@ -38,6 +43,8 @@
     "build": "node tools/build/generate.js --out tools/cli/lib/packs.js --module-out src/bmad-plus/module.yaml",
     "build:check": "node tools/build/generate.js --check",
     "check:counts": "node tools/build/check-counts.js",
+    "uat:spec": "node src/bmad-plus/skills/bmad-plus-uat/templates/uat-spec-present.mjs --dir recettes",
+    "uat:gate": "node src/bmad-plus/skills/bmad-plus-uat/templates/uat-release-gate.mjs --dir recettes --cli tools/cli/bmad-plus-cli.js",
     "lint": "eslint tools/ tests/",
     "format": "prettier --write \"tools/**/*.js\" \"tests/**/*.js\"",
     "format:check": "prettier --check \"tools/**/*.js\" \"tests/**/*.js\"",
@@ -68,7 +75,8 @@
   "jest": {
     "testPathIgnorePatterns": [
       "/node_modules/",
-      "/website/"
+      "/website/",
+      "/evals/"
     ],
     "collectCoverage": true,
     "coverageDirectory": "coverage",

package/readme-international/README.de.md

@@ -1,6 +1,6 @@
 # 🚀 BMAD+ — Erweitertes Multi-Agent KI-Framework
 
-[![Version](https://img.shields.io/badge/version-0.14.0-blue.svg)](../CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.17.0-blue.svg)](../CHANGELOG.md)
 [![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
 [![License](https://img.shields.io/badge/license-MIT-yellow.svg)](../LICENSE)
 
@@ -8,6 +8,10 @@
   <a href="../README.md">English</a> | <a href="README.fr.md">Français</a> | <a href="README.es.md">Español</a> | 🌐 <b>Deutsch</b>
 </div>
 
+**Quelldokumentation: 0.17.0.** Das [npm-Paket](https://www.npmjs.com/package/bmad-plus) und die [öffentliche Anleitung](https://bmad-plus.rochetta.fr/de/docs/) nennen die veröffentlichte Version. Das [offizielle Distributionsrepository](https://github.com/lrochetta/BMAD-PLUS) ist öffentlich. Version 0.15.0 wurde mit 0.16.0 ausgeliefert und nicht separat veröffentlicht.
+
+Version 0.17.0 behebt unbemerkt verlorene Abnahmeantworten und leere JSON-Exporte, findet Rezepte anhand ihrer Kennung und führt Veröffentlichungsprüfungen unter Windows mit Node aus. Sie ergänzt verständlichen Fortschritt, kopierbare Befehle und Vorlagen für Projektprüfungen. Blockierte Prüfungen erfordern eine Wiederholung oder eine ausdrückliche Risikoübernahme durch eine benannte Person; automatische Tests und menschliche Beobachtungen bleiben getrennt.
+
 > **Multirole-Agenten · 9 modulare Packs · Autopilot-Modus · Parallele Ausführung**
 > Intelligenter Fork von [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) — Selbstaktivierende Agenten mit 3-Stufen-Kontexterkennung, GRC-Compliance (Shield), vollständige SDLC-Pipeline (Dev Studio), OSINT-Intelligence, SEO-Audit, persistentes Cross-Session-Gedächtnis und 10-Sprachen CLI-Installer.
 
@@ -15,9 +19,9 @@
 
 ## 📋 Inhaltsverzeichnis
 
-Repository-Prüfung: **980 JavaScript-Tests** (`npm test`). Die Deinstallation erhält den Projektspeicher und angepasste Dateien; für Installation oder Deinstallation ohne interaktives Terminal `--yes` verwenden.
+Repository-Prüfung: **1272 JavaScript-Tests** (`npm test`). Die Deinstallation erhält den Projektspeicher und angepasste Dateien; für Installation oder Deinstallation ohne interaktives Terminal `--yes` verwenden.
 
-Version 0.14.0 vervollständigt die Dev-Studio-Workflows und ergänzt `bmad-plus studio list --json` sowie `bmad-plus studio prepare create-prd --request "Eine Offline-Aufgabenliste definieren" --json`. In einem Projekt mit installiertem Dev Studio lädt die Vorbereitung die tatsächlichen Anweisungen, Konfiguration und Eingaben für deinen KI-Assistenten; sie führt die Arbeit nicht aus. `doctor --json` prüft den installierten Ressourcengraphen. Siehe [Einstieg und Versionshinweise](https://bmad-plus.rochetta.fr/de/docs/).
+Version 0.16.0 ergänzt die menschliche Abnahme: eine Lieferung erzeugt eine Schritt-für-Schritt-Seite, die eine Person durchgeht, ihr Durchlauf kommt als JSON zurück, das die Agenten lesen und einordnen, und `uat gate` weist einen unfertigen, veralteten, nicht eingeordneten oder unbestätigten Durchlauf zurück. Die Seite spricht die zehn Sprachen des Installers. Sie liefert auch die für 0.15.0 vorbereiteten Änderungen: persistente Nexus-Versuche, optionale Befehls- oder Codex-Ausführung im Vordergrund und eine Speicherbewertung anhand akzeptierter Ergebnisse. Ein abgeschlossener Agentenlauf benötigt weiterhin unabhängige Prüfungen. Alle neun Packs haben bewertete deterministische Kontrollen; Modellbeobachtungen bleiben davon getrennt. Dev-Studio-Kontextvorbereitung und geschützte Updates bleiben verfügbar. Siehe [Einstieg und Versionshinweise](https://bmad-plus.rochetta.fr/de/docs/).
 
 - [Warum BMAD+?](#-warum-bmad-)
 - [Schnellstart](#-schnellstart)
@@ -163,21 +167,22 @@ Nexus orchestriert alles automatisch mit Checkpoints für deine Genehmigung.
 | `npx bmad-plus memory status` | Statusbericht des Gedächtnisses (Projekt + globales Gehirn) |
 | `npx bmad-plus memory export` | Gehirn als portables Markdown-Archiv exportieren |
 | `npx bmad-plus doctor` | Installationsintegrität prüfen |
-| `node tools/cli/bmad-plus-cli.js doctor --json` | Quellrepository: schreibgeschützter Bericht über Inventar und Fähigkeiten (nächste Version) |
+| `node tools/cli/bmad-plus-cli.js doctor --json` | Quellrepository: schreibgeschützter Bericht über Inventar und Fähigkeiten |
 | `npx bmad-plus update` | Agenten und Skills aktualisieren (Konfiguration bleibt erhalten) |
 | `npx bmad-plus uninstall` | BMAD+ vom aktuellen Projekt entfernen |
 | `npx bmad-plus autoconfig` | Intelligentes Bootstrap — Auto-Erkennung, Installation und Konfiguration |
+| `npx bmad-plus uat <action>` | Menschliche Abnahme: lint, build, serve, import, read, gate, order (Alias `recette`) |
 
 #### Framework aktualisieren
 
 Die installierten Anweisungen bitten das LLM um eine Prüfung pro Sitzung. Das Ergebnis wird 24 Stunden zwischengespeichert; offline bleibt die veröffentlichte Version unbekannt. Automatische Updates erfordern eine ausdrückliche Richtlinie und unveränderte verwaltete Dateien.
 
-Für Installationen mit 0.12.2 oder älter einmal die neue CLI mit `npx --yes bmad-plus@0.14.0 update --yes` laden. Diese ausdrückliche Migration sichert vorhandene Dateien vor dem Ersetzen.
+Für Installationen mit 0.12.2 oder älter einmal die neue CLI mit `npx --yes bmad-plus@0.17.0 update --yes` laden. Diese ausdrückliche Migration sichert vorhandene Dateien vor dem Ersetzen.
 
 ```bash
 npx bmad-plus update-check --json
 npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.14.0"
+npx bmad-plus update-policy --mode auto --range "^0.17.0"
 npx bmad-plus update --latest --auto
 npx bmad-plus update-check --offline --json
 ```
@@ -598,6 +603,9 @@ BMAD+/
 | **0.12.2** | 2026-07-16 | 🚚 **Fähigkeiten ausgeliefert** — SEO-Toolkit in-pack ausgeliefert (funktioniert von npm), OSINT-Rechtsgrundlagen-Gate auf jedem Pfad, Monitor rebuildbar, Crawler-SSRF geschlossen, mcp-server + CLI Testabdeckung; 483 Tests |
 | **0.13.0** | 2026-09-08 | Kontrollierte Updates, geschützte Agenten, wiederherstellbare Sicherungen und Registry-basierte Installation; 709 Tests |
 | **0.14.0** | 2026-09-09 | Vollständige Dev-Studio-Workflows und Kontextvorbereitung, Diagnosen, synchronisierte npm-Dokumentation und mehrsprachige Website |
+| **0.15.0** | 2026-09-11 | Im Quellstand vorbereitet; mit 0.16.0 ausgeliefert. Persistente Nexus-Ausfuehrung, evidenzbasierter Speicher, Pack-Kontrollen und gepruefte Archive |
+| **0.16.0** | 2026-09-16 | Menschliche Abnahme: Seite fuer eine Person, zurueckgelesener Durchlauf, Einordnung und evidenzgebundene Pruefung, zehn Sprachen |
+| **0.17.0** | 2026-09-22 | Zuverlässige Abnahmeseiten, Suche nach Kennung, Windows-Veröffentlichungsprüfungen, ausdrückliche Risikoentscheidungen und synchronisierte Anleitungen |
 
 Siehe [CHANGELOG.md](../CHANGELOG.md) für vollständige Details.
 
@@ -607,6 +615,9 @@ Siehe [CHANGELOG.md](../CHANGELOG.md) für vollständige Details.
 
 MIT — Basierend auf [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) (MIT)
 
+BMAD+ ist eine unabhängige Ableitung, keine offizielle Veröffentlichung oder Empfehlung von BMad Code, LLC.
+Quellenangaben und Bedingungen: [Hinweise zu Drittquellen](../THIRD-PARTY-LICENSES.md).
+
 ### Credits
 
 **Ersteller**
@@ -619,10 +630,10 @@ MIT — Basierend auf [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD
 
 **Externe Quellen & Inspirationen**
 - **BMAD-METHOD** von [bmad-code-org](https://github.com/bmad-code-org) — Ursprüngliche Multi-Agenten-Methodik (MIT)
-- **Shield GRC** — 27 Compliance-Agenten + 11 Workflows basierend auf öffentlichen Regulierungstexten (DSGVO, ISO 27001, SOC 2, HIPAA, EU AI Act, DORA, NIST, CMMC, usw.)
+- **Shield GRC** — 27 Compliance-Agenten + 11 Workflows, angepasst aus den [GRC-Skills von Hemant Naik](https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance) (MIT)
 - **OSINT Pipeline** basierend auf [smixs/osint-skill](https://github.com/smixs/osint-skill) (MIT)
-- **Apify Actor Runner** integriert von [apify/agent-skills](https://github.com/apify/agent-skills) (MIT)
-- **Karpathy Guardrails** adaptiert von [Andrej Karpathy](https://github.com/multica-ai/andrej-karpathy-skills) (MIT) — Verhaltensregeln für das Memory Pack
+- **Apify-Integration** — OSINT-Helfer und Anregungen aus [Apify Agent Skills](https://github.com/apify/agent-skills) (Upstream deklariert Apache-2.0; siehe Hinweise)
+- **Karpathy Guardrails** — Memory-Pack-Anpassung der [Community-Regeln von forrestchang](https://github.com/multica-ai/andrej-karpathy-skills), inspiriert von Andrej Karpathy (Upstream deklariert MIT)
 
 **Werkzeuge & Infrastruktur**
 - [Evolution API](https://github.com/EvolutionAPI/evolution-api) — WhatsApp-Benachrichtigungen für Upstream-Überwachung

package/readme-international/README.es.md

@@ -1,6 +1,6 @@
 # 🚀 BMAD+ — Framework Multi-Agente IA Aumentado
 
-[![Version](https://img.shields.io/badge/version-0.14.0-blue.svg)](../CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.17.0-blue.svg)](../CHANGELOG.md)
 [![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
 [![License](https://img.shields.io/badge/license-MIT-yellow.svg)](../LICENSE)
 
@@ -8,6 +8,10 @@
   <a href="../README.md">English</a> | <a href="README.fr.md">Français</a> | 🌐 <b>Español</b> | <a href="README.de.md">Deutsch</a>
 </div>
 
+**Documentación fuente: 0.17.0.** Consulta el [paquete npm](https://www.npmjs.com/package/bmad-plus) y la [guía pública](https://bmad-plus.rochetta.fr/es/docs/) para conocer la versión publicada. El [repositorio oficial de distribución](https://github.com/lrochetta/BMAD-PLUS) es público. La 0.15.0 se entregó con la 0.16.0, sin publicación separada.
+
+La versión 0.17.0 corrige la pérdida silenciosa de respuestas y las exportaciones JSON vacías, encuentra recetas por su identificador y ejecuta los controles de publicación con Node en Windows. Añade un progreso más claro, comandos que se pueden copiar y plantillas de controles de proyecto. Una comprobación bloqueada requiere repetirla o una aceptación explícita del riesgo por un responsable identificado; las pruebas automáticas y las observaciones humanas siguen separadas.
+
 > **Agentes multirrol · 9 packs modulares · Modo Autopilot · Ejecución paralela**
 > Fork inteligente de [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) — Agentes auto-activables con detección contextual en 3 niveles, cumplimiento GRC (Shield), pipeline SDLC completo (Dev Studio), inteligencia OSINT, auditoría SEO, memoria persistente cross-session e instalador CLI en 10 idiomas.
 
@@ -15,9 +19,9 @@
 
 ## 📋 Tabla de contenidos
 
-Validación del repositorio: **980 tests JavaScript** (`npm test`). La desinstalación conserva la memoria del proyecto y los archivos personalizados; utiliza `--yes` para instalar o desinstalar sin un terminal interactivo.
+Validación del repositorio: **1272 tests JavaScript** (`npm test`). La desinstalación conserva la memoria del proyecto y los archivos personalizados; utiliza `--yes` para instalar o desinstalar sin un terminal interactivo.
 
-La versión 0.14.0 repara la entrega completa de Dev Studio y añade `bmad-plus studio list --json` y `bmad-plus studio prepare create-prd --request "Definir una lista de tareas sin conexión" --json`. En un proyecto con Dev Studio instalado, la preparación carga instrucciones reales, configuración y entradas para tu asistente de IA; no ejecuta el trabajo. `doctor --json` verifica el grafo de recursos instalados. Consulta la [guía de inicio y las novedades](https://bmad-plus.rochetta.fr/es/docs/).
+La versión 0.16.0 añade la aceptación humana: una entrega produce una página paso a paso que una persona recorre, su prueba vuelve en JSON que los agentes leen y clasifican, y `uat gate` rechaza una prueba inacabada, desactualizada, sin clasificar o sin confirmar. La página habla los diez idiomas del instalador. También entrega el trabajo preparado para la 0.15.0: intentos Nexus persistentes, ejecución opcional de comandos o Codex en primer plano y clasificación de memoria basada en resultados aceptados. Un turno de agente terminado aún requiere verificación independiente. Los nueve paquetes tienen controles deterministas puntuados; las observaciones de modelos se mantienen separadas. La preparación de contexto Dev Studio y las protecciones de actualización siguen disponibles. Consulta la [guía de inicio y las novedades](https://bmad-plus.rochetta.fr/es/docs/).
 
 - [¿Por qué BMAD+?](#-por-qué-bmad-)
 - [Inicio Rápido](#-inicio-rápido)
@@ -163,21 +167,22 @@ Nexus orquesta todo automáticamente con puntos de control (checkpoints) para tu
 | `npx bmad-plus memory status` | Informe de salud de memoria (proyecto + cerebro global) |
 | `npx bmad-plus memory export` | Exportar cerebro como archivo Markdown portable |
 | `npx bmad-plus doctor` | Verificar integridad de la instalación |
-| `node tools/cli/bmad-plus-cli.js doctor --json` | Repositorio fuente: informe de inventario y capacidades de solo lectura (próxima versión) |
+| `node tools/cli/bmad-plus-cli.js doctor --json` | Repositorio fuente: informe de inventario y capacidades de solo lectura |
 | `npx bmad-plus update` | Actualizar agentes y skills (preserva la config) |
 | `npx bmad-plus uninstall` | Eliminar BMAD+ del proyecto actual |
 | `npx bmad-plus autoconfig` | Bootstrap inteligente — detección auto, instalación y configuración |
+| `npx bmad-plus uat <action>` | Aceptación humana: lint, build, serve, import, read, gate, order (alias `recette`) |
 
 #### Actualizaciones del framework
 
 Las instrucciones instaladas piden al LLM una comprobación por sesión. El resultado se conserva durante 24 horas; sin conexión, la versión publicada permanece desconocida. Las actualizaciones automáticas requieren una política explícita y archivos administrados sin cambios locales.
 
-Para instalaciones con 0.12.2 o anterior, carga una vez el nuevo CLI con `npx --yes bmad-plus@0.14.0 update --yes`. Esta migración explícita guarda copias de seguridad antes de reemplazar los archivos antiguos.
+Para instalaciones con 0.12.2 o anterior, carga una vez el nuevo CLI con `npx --yes bmad-plus@0.17.0 update --yes`. Esta migración explícita guarda copias de seguridad antes de reemplazar los archivos antiguos.
 
 ```bash
 npx bmad-plus update-check --json
 npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.14.0"
+npx bmad-plus update-policy --mode auto --range "^0.17.0"
 npx bmad-plus update --latest --auto
 npx bmad-plus update-check --offline --json
 ```
@@ -302,7 +307,7 @@ graph TB
 | **QA Engineer** | Pruebas API/E2E, edge cases, cobertura, revisión de código | "prueba", "QA", "bug", post-implementación |
 | **UX Reviewer** | Evaluación de UX, accesibilidad, diseño de interacción | "UX", "interfaz", "responsive", cambios frontend |
 
-**Capacidades:** QA Tests (QA), Code Review (CR), UX Design (CU)
+**Capacidades:** QA Tests (QA), Code Review (CR), UX Design (CU), Recette build (RB), Recette read (RR), Recette gate (RG)
 
 ---
 
@@ -613,6 +618,9 @@ BMAD+/
 | **0.12.2** | 2026-07-16 | 🚚 **Capacidades entregadas** — toolkit SEO embarcado in-pack (funciona desde npm), gate de base legal OSINT en cada ruta, monitor reconstruible, SSRF del crawler cerrado, cobertura de tests mcp-server + CLI; 483 tests |
 | **0.13.0** | 2026-09-08 | Actualizaciones controladas, agentes protegidos, copias restaurables e instalación derivada del registro; 709 tests |
 | **0.14.0** | 2026-09-09 | Flujos completos de Dev Studio y preparación del contexto, diagnósticos, documentación npm y web multilingüe sincronizadas |
+| **0.15.0** | 2026-09-11 | Preparada en el repositorio; entregada con la 0.16.0. Ejecucion Nexus persistente, memoria con evidencias, controles de paquetes y archivos verificados |
+| **0.16.0** | 2026-09-16 | Aceptacion humana: pagina recorrida por una persona, prueba releida, clasificacion y control con evidencias, diez idiomas |
+| **0.17.0** | 2026-09-22 | Páginas de aceptación fiables, búsqueda por identificador, controles de Windows, decisiones explícitas de riesgo y guías sincronizadas |
 
 Más descripciones a fondo en el archivo: [CHANGELOG.md](../CHANGELOG.md).
 
@@ -624,6 +632,9 @@ Proyecto BMAD+ (Adaptación: MIT)
 
 Basado nativamente en el repositorio: [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) (MIT LIC)
 
+BMAD+ es un derivado independiente, sin carácter oficial ni respaldo de BMad Code, LLC.
+Atribuciones y condiciones de las fuentes incluidas: [Avisos de terceros](../THIRD-PARTY-LICENSES.md).
+
 ### Reconocimientos
 
 **Creador**
@@ -636,10 +647,10 @@ Basado nativamente en el repositorio: [BMAD-METHOD](https://github.com/bmad-code
 
 **Fuentes Externas e Inspiraciones**
 - **BMAD-METHOD** por [bmad-code-org](https://github.com/bmad-code-org/BMAD-METHOD) — Metodología multi-agente original (MIT)
-- **Shield GRC** — 27 agentes de cumplimiento + 11 workflows basados en textos regulatorios públicos (GDPR, ISO 27001, SOC 2, HIPAA, EU AI Act, DORA, NIST, CMMC, etc.)
+- **Shield GRC** — 27 agentes de cumplimiento + 11 workflows adaptados de los [skills GRC de Hemant Naik](https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance) (MIT)
 - **OSINT Pipeline** basado en [smixs/osint-skill](https://github.com/smixs/osint-skill) (MIT)
-- **Apify Actor Runner** integrado desde [apify/agent-skills](https://github.com/apify/agent-skills) (MIT)
-- **Karpathy Guardrails** adaptado de [Andrej Karpathy](https://github.com/multica-ai/andrej-karpathy-skills) (MIT) — Reglas de comportamiento para Memory Pack
+- **Integración Apify** — herramienta OSINT e inspiración de los [skills Apify](https://github.com/apify/agent-skills) (Apache-2.0 declarado en origen; véanse los avisos)
+- **Karpathy Guardrails** — adaptación para Memory Pack de las [reglas comunitarias de forrestchang](https://github.com/multica-ai/andrej-karpathy-skills), inspiradas en Andrej Karpathy (MIT declarado en origen)
 
 **Herramientas e Infraestructura**
 - [Evolution API](https://github.com/EvolutionAPI/evolution-api) — Notificaciones WhatsApp para monitoreo upstream

package/readme-international/README.fr.md

@@ -1,6 +1,6 @@
 # 🚀 BMAD+ — Framework Multi-Agent IA Augmenté
 
-[![Version](https://img.shields.io/badge/version-0.14.0-blue.svg)](../CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.17.0-blue.svg)](../CHANGELOG.md)
 [![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
 [![License](https://img.shields.io/badge/license-MIT-yellow.svg)](../LICENSE)
 
@@ -8,6 +8,10 @@
   <a href="../README.md">English</a> | 🌐 <b>Français</b> | <a href="README.es.md">Español</a> | <a href="README.de.md">Deutsch</a>
 </div>
 
+**Documentation source : 0.17.0.** Consultez le [paquet npm](https://www.npmjs.com/package/bmad-plus) et le [guide public](https://bmad-plus.rochetta.fr/fr/docs/) pour connaître la version effectivement publiée. Le [dépôt officiel de distribution](https://github.com/lrochetta/BMAD-PLUS) est public. La 0.15.0 a été livrée avec la 0.16.0, sans publication séparée.
+
+La version 0.17.0 corrige la perte silencieuse des réponses de recette et les exports JSON vides, retrouve les recettes par identifiant et exécute les contrôles de publication avec Node sous Windows. Elle ajoute une progression lisible, des commandes copiables et des modèles de contrôles projet. Un contrôle bloqué nécessite un nouveau passage ou une acceptation explicite du risque par un responsable nommé ; tests automatisés et observations humaines restent distincts.
+
 > **Agents multi-rôles · 9 packs modulaires · Mode Autopilot · Exécution parallèle**
 > Fork intelligent de [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) — Agents auto-activables avec détection contextuelle 3 niveaux, conformité GRC (Shield), pipeline SDLC complet (Dev Studio), intelligence OSINT, audit SEO, mémoire persistante cross-session, et installeur CLI 10 langues.
 
@@ -15,9 +19,9 @@
 
 ## 📋 Table des matières
 
-Validation du dépôt : **980 tests JavaScript** (`npm test`). La désinstallation conserve la mémoire du projet et les fichiers personnalisés ; utilisez `--yes` pour installer ou désinstaller sans terminal interactif.
+Validation du dépôt : **1272 tests JavaScript** (`npm test`). La désinstallation conserve la mémoire du projet et les fichiers personnalisés ; utilisez `--yes` pour installer ou désinstaller sans terminal interactif.
 
-La version 0.14.0 répare la livraison complète de Dev Studio et ajoute `bmad-plus studio list --json` et `bmad-plus studio prepare create-prd --request "Définir une liste de tâches hors ligne" --json`. Dans un projet où Dev Studio est installé, la préparation charge les instructions réelles, la configuration et les entrées pour votre assistant IA ; elle n’exécute pas le travail. `doctor --json` vérifie le graphe des ressources installées. Consultez le [guide de démarrage et les nouveautés](https://bmad-plus.rochetta.fr/fr/docs/).
+La version 0.16.0 ajoute la recette humaine : une livraison produit une page pas à pas qu’une personne joue, son passage revient en JSON que les agents lisent et classent, et `uat gate` refuse un passage inachevé, périmé, non classé ou non confirmé. La page parle les dix langues de l’installeur. Elle livre aussi le travail préparé pour la 0.15.0 : des tentatives Nexus persistantes, le lancement facultatif de commandes ou de Codex au premier plan et un classement mémoire fondé sur des résultats acceptés. Un tour d’agent terminé doit encore passer une vérification indépendante. Les neuf packs disposent de contrôles déterministes notés ; les observations de modèles restent distinctes. La préparation Dev Studio et les protections de mise à jour restent disponibles. Consultez le [guide de démarrage et les nouveautés](https://bmad-plus.rochetta.fr/fr/docs/).
 
 - [Pourquoi BMAD+ ?](#-pourquoi-bmad-)
 - [Quick Start](#-quick-start)
@@ -163,21 +167,22 @@ Nexus orchestre tout automatiquement avec des checkpoints pour ton approbation.
 | `npx bmad-plus memory status` | Rapport de santé mémoire (projet + cerveau global) |
 | `npx bmad-plus memory export` | Export du cerveau en archive Markdown portable |
 | `npx bmad-plus doctor` | Vérifier l'intégrité de l'installation |
-| `node tools/cli/bmad-plus-cli.js doctor --json` | Dépôt source : rapport en lecture seule sur l'inventaire et les capacités (prochaine version) |
+| `node tools/cli/bmad-plus-cli.js doctor --json` | Dépôt source : rapport en lecture seule sur l'inventaire et les capacités |
 | `npx bmad-plus update` | Mettre à jour agents et skills (préserve la config) |
 | `npx bmad-plus uninstall` | Supprimer BMAD+ du projet actuel |
 | `npx bmad-plus autoconfig` | Bootstrap intelligent — détection auto, installation et configuration |
+| `npx bmad-plus uat <action>` | Recette humaine : lint, build, serve, import, read, gate, order (alias `recette`) |
 
 #### Mises à jour du framework
 
 Les instructions installées demandent au LLM une vérification par session. Le résultat est conservé 24 heures ; hors connexion, la version publiée reste inconnue. Les mises à jour automatiques exigent une politique explicite et des fichiers gérés sans modification locale.
 
-Pour les installations en 0.12.2 ou antérieures, chargez une fois le nouveau CLI avec `npx --yes bmad-plus@0.14.0 update --yes`. Cette migration explicite sauvegarde les anciens fichiers avant leur remplacement.
+Pour les installations en 0.12.2 ou antérieures, chargez une fois le nouveau CLI avec `npx --yes bmad-plus@0.17.0 update --yes`. Cette migration explicite sauvegarde les anciens fichiers avant leur remplacement.
 
 ```bash
 npx bmad-plus update-check --json
 npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.14.0"
+npx bmad-plus update-policy --mode auto --range "^0.17.0"
 npx bmad-plus update --latest --auto
 npx bmad-plus update-check --offline --json
 ```
@@ -613,6 +618,9 @@ BMAD+/
 | **0.12.2** | 2026-07-16 | 🚚 **Capacités livrées** — toolkit SEO embarqué in-pack (fonctionne depuis npm), gate base légale OSINT sur tout chemin, monitor reconstructible, SSRF crawler fermé, couverture de tests mcp-server + CLI ; 483 tests |
 | **0.13.0** | 2026-09-08 | Mises à jour contrôlées, agents protégés, sauvegardes restaurables et installation issue du registre ; 709 tests |
 | **0.14.0** | 2026-09-09 | Workflows Dev Studio complets et préparation du contexte, diagnostics, documentation npm et landing multilingue synchronisées |
+| **0.15.0** | 2026-09-11 | Préparée dans le dépôt ; livrée avec la 0.16.0. Execution Nexus persistante, memoire fondee sur des preuves, controles des packs et archives verifiees |
+| **0.16.0** | 2026-09-16 | Recette humaine : page jouee par une personne, passage relu, classement et porte liee aux preuves, dix langues |
+| **0.17.0** | 2026-09-22 | Recettes fiables, recherche par identifiant, contrôles de publication sous Windows, décisions de risque explicites et guides synchronisés |
 
 Voir [CHANGELOG.md](../CHANGELOG.md) pour le détail complet.
 
@@ -622,6 +630,9 @@ Voir [CHANGELOG.md](../CHANGELOG.md) pour le détail complet.
 
 MIT — Basé sur [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) (MIT)
 
+BMAD+ est un dérivé indépendant, sans statut officiel ni approbation de BMad Code, LLC.
+Attributions et conditions des sources intégrées : [Notices tierces](../THIRD-PARTY-LICENSES.md).
+
 ### Crédits
 
 **Créateur**
@@ -634,10 +645,10 @@ MIT — Basé sur [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) (M
 
 **Sources Externes et Inspirations**
 - **BMAD-METHOD** par [bmad-code-org](https://github.com/bmad-code-org/BMAD-METHOD) — Méthodologie multi-agents originale (MIT)
-- **Shield GRC** — 27 agents de conformité + 11 workflows basés sur des textes réglementaires publics (RGPD, ISO 27001, SOC 2, HIPAA, EU AI Act, DORA, NIST, CMMC, etc.)
+- **Shield GRC** — 27 agents de conformité + 11 workflows adaptés des [skills GRC de Hemant Naik](https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance) (MIT)
 - **OSINT Pipeline** basé sur [smixs/osint-skill](https://github.com/smixs/osint-skill) (MIT)
-- **Apify Actor Runner** intégré de [apify/agent-skills](https://github.com/apify/agent-skills) (MIT)
-- **Karpathy Guardrails** adapté de [Andrej Karpathy](https://github.com/multica-ai/andrej-karpathy-skills) (MIT) — Règles comportementales pour Memory Pack
+- **Intégration Apify** — outil OSINT et inspiration des [skills Apify](https://github.com/apify/agent-skills) (Apache-2.0 déclaré en amont ; voir les notices)
+- **Karpathy Guardrails** — adaptation pour Memory Pack des [règles communautaires de forrestchang](https://github.com/multica-ai/andrej-karpathy-skills), inspirées d’Andrej Karpathy (MIT déclaré en amont)
 
 **Outils et Infrastructure**
 - [Evolution API](https://github.com/EvolutionAPI/evolution-api) — Notifications WhatsApp pour la surveillance upstream

package/src/bmad-plus/agents/agent-architect-dev/SKILL.md

@@ -20,7 +20,7 @@ Switches between calm architectural reasoning and ultra-succinct dev precision d
 ## Principles
 
 - User journeys drive technical decisions. Embrace boring technology for stability. Design simple solutions that scale when needed.
-- All existing and new tests must pass 100% before any story is ready for review. Every task/subtask must be covered by comprehensive unit tests.
+- Establish acceptance with checks of the changed behavior at its real consumer. Use meaningful regression tests and required project checks; record unrelated failures and unavailable checks without calling them passes.
 - Every word in documentation serves a purpose. A diagram is worth thousands of words — include diagrams over drawn out text.
 - Developer productivity is architecture. Connect every decision to business value and user impact.
 
@@ -36,7 +36,7 @@ Forge operates in three switchable roles. Roles can be **explicitly requested**
 
 Focuses on: technical design, stack decisions, API design, distributed systems, scalability trade-offs.
 
-> 💡 **Auto-activates** when: keywords like "architecture", "design", "API", "schema", "structure", "stack" are detected, when starting a new module, when security is involved, or when changes span 5+ files.
+> 💡 **Auto-activates** when: keywords like "architecture", "design", "API", "schema", "structure", "stack" are detected, when starting a new module, or when shared contracts, data or security boundaries need a design decision.
 
 ### Role: Developer (default for implementation)
 
@@ -54,14 +54,14 @@ When auto-activating a role, **announce it**: "💡 I'm switching to [Role] mode
 
 ## Critical Actions (Developer Role)
 
-- READ the entire story file BEFORE any implementation — tasks/subtasks sequence is your authoritative implementation guide
-- Execute tasks/subtasks IN ORDER as written in story file — no skipping, no reordering
-- Mark task/subtask [x] ONLY when both implementation AND tests are complete and passing
-- Run full test suite after each task — NEVER proceed with failing tests
-- Execute continuously without pausing until all tasks/subtasks are complete
-- Document in story file Dev Agent Record what was implemented, tests created, and any decisions made
-- Update story file File List with ALL changed files after each task completion
-- NEVER lie about tests being written or passing — tests must actually exist and pass 100%
+1. Read the actual request, project instructions, relevant memory and the entire supplied story before editing. Establish the observable outcome and acceptance criteria. Reuse an existing valid plan; do not invent a story or reopen a settled decision.
+2. Inspect the working tree and trace the affected behavior through callers, data, interfaces and tests. Before choosing the amount of process, record what the inspected code settles, any consequential intent gap, possible external or irreversible effects, and the expected change scope. A keyword or file count alone does not establish complexity.
+3. Use a compact plan for a routine change. Expand it when investigation reveals a shared contract, migration or unresolved user-visible choice. If that happens during implementation, record the new evidence and revise the affected slice before proceeding; preserve completed work and continue independent authorized work. Ask only for essential information that the available evidence and prior decisions cannot settle. Existing authorization and checkpoint policy still apply.
+4. Follow the story's task dependencies and reconcile any outdated instructions with current code. Implement the smallest coherent change in the project's style. Preserve unrelated edits and handwritten tracking data. Do not reset, revert, stage, commit or publish merely because a workflow reaches its final step.
+5. Map each acceptance criterion to an executed test, command or direct observation. For a meaningful regression test, demonstrate the missing behavior first when practical, then make it pass. Exercise the real changed consumer: a helper-only test does not establish CLI, installed-package or interface adoption. Run required project checks at the relevant boundary; repeat or broaden them only for new changes, failures or unresolved coverage.
+6. Record the check, observed result and tested artifact identity, including relevant callers, tests and configuration. Use revision and content hashes when available; otherwise identify the inspected snapshot and its limits. After an edit or resume, reuse only evidence whose relevant inputs are unchanged. Changed requirements, callers or assertions can invalidate a pass even when the cited implementation lines did not move.
+7. Reconcile task completion from current evidence. Failed, skipped, unavailable and unrun checks remain distinct; a completion claim or an existing test file is not a pass. Report implementation, verification and required review separately. Sentinel or the designated acceptance owner inspects the result; if the same assistant also reviews it, say so rather than claiming independent acceptance.
+8. Update authorized story records with decisions, changed files, actual check results and the next incomplete action. Mark a task complete only when its required evidence is established. Preserve partial work and explain the specific remaining dependency when completion is blocked.
 
 ## Capabilities
 
@@ -89,8 +89,6 @@ When auto-activating a role, **announce it**: "💡 I'm switching to [Role] mode
    - **Load role triggers** — Search for `**/role-triggers.yaml`. If found, use for auto-activation rules. If not found, use built-in defaults.
    - **Greet and present capabilities** — Greet `{user_name}` warmly by name, always speaking in `{communication_language}` and applying your persona throughout the session.
 
-3. Remind the user they can invoke the `bmad-help` skill at any time for advice and then present the capabilities table from the Capabilities section above.
-
-   **STOP and WAIT for user input** — Do NOT execute menu items automatically. Accept number, menu code, or fuzzy command match.
+3. If the user already supplied a clear task or continuation, select its registered route and proceed within the established authorization. A greeting or menu does not require another confirmation. If the user only asked to meet Forge, mention `bmad-help`, present the capabilities table and wait for a selection. Accept a number, menu code or fuzzy command match.
 
 **CRITICAL Handling:** When user responds with a code, line number or skill, invoke the corresponding skill by its exact registered name from the Capabilities table. DO NOT invent capabilities on the fly.

package/src/bmad-plus/agents/agent-orchestrator/SKILL.md

@@ -23,7 +23,7 @@ Crisp and checklist-driven for sprint management. Confident and direct for quick
 - Planning and execution are two sides of the same coin. Specs are for building, not bureaucracy.
 - Code that ships is better than perfect code that doesn't.
 - Parallel when possible, sequential when required. Never parallelize dependent tasks.
-- Escalate to human when 3 automatic retries fail. Transparency over silent failure.
+- Bound retries by the task's recorded policy. Reconcile interrupted or ambiguous work before starting another attempt; report the unresolved condition when the limit is reached.
 
 You must fully embody this persona so the user gets the best experience and help they need, therefore its important to remember you must not break character until the users dismisses this persona.
 
@@ -49,7 +49,12 @@ Focuses on: rapid spec creation, lean implementation, minimum ceremony tasks.
 
 Focuses on: end-to-end pipeline management, agent sequencing, checkpoint management, progress tracking, WhatsApp notifications.
 
-**Autopilot Pipeline:**
+Inspect the request, existing artifacts and relevant consumers before choosing
+the route. A small correction can use Quick Flow; a discovered contract change,
+missing requirement or wider impact may require planning. Preserve prior user
+authorization and completed work when changing depth.
+
+**Autopilot Pipeline for work that needs these stages:**
 
 1. **Discovery Phase** → Invoke `bmad-plus-agent-strategist`
    - Run brainstorming → product brief → PRD → UX design
@@ -62,13 +67,14 @@ Focuses on: end-to-end pipeline management, agent sequencing, checkpoint managem
    - 🟡 NOTIFY after each story completion
 
 3. **Ship Phase** → Invoke `bmad-plus-agent-quality` + `bmad-plus-agent-architect-dev`
+   - Human acceptance: the Quality agent builds the delivery's recette, delivers the page, then reads the run and classifies every failure (`bmad-plus uat`). `uat.mode` in `_bmad/config.yaml` decides whether the delivery checkpoint waits for the gate (`gate`) or only reports it (`advisory`, the default)
    - Run full code review → UX review → documentation
    - 🔴 CHECKPOINT: Wait for user approval before finalization
 
 Read `execution_mode` and `checkpoints` from `_bmad/config.yaml` before starting the pipeline. The checkpoint keys are `discovery`, `architecture`, `story`, and `delivery`.
 
 **Checkpoint behavior** (configurable):
-- `require_approval` (🔴 STOP): Present the checkpoint in the session and wait for user input. If an external channel is configured and sending is authorized, also notify through it.
+- `require_approval` (🔴 STOP): Check whether the existing user authorization covers the concrete next action. If approval is still required, present the reviewable checkpoint and wait; do not ask again for an action already authorized. If an external channel is configured and sending is authorized, also notify through it.
 - `notify_only` (🟡 INFO): Report progress in the session and continue. If an external channel is configured and sending is authorized, also notify through it.
 - `auto` (🟢 AUTO): Continue automatically. Log for audit trail.
 
@@ -89,11 +95,11 @@ Focuses on: detecting parallelizable tasks, launching agents in parallel, confli
 
 **Supervision Actions:**
 - **Launch**: Detect independent tasks → start parallel agents
-- **Monitor**: Track progress of all running agents via orchestrator-state.yaml
+- **Monitor**: Inspect durable attempt/evidence state with `bmad-plus nexus inspect RUN --json`; keep the pipeline YAML only as a navigation summary.
 - **Stop**: Detect conflicts (shared file edits) → pause conflicting agent
-- **Restart**: After conflict resolution → restart with merged context
+- **Restart**: Inspect the existing host and artifacts, reconcile the attempt, then use a new bounded retry with an explicit host/session identity.
 - **Reallocate**: Agent finishes early → assign next available task
-- **Escalate**: 3 consecutive failures → report the failure and evidence in the session. If an external channel is configured and sending is authorized, also notify through it.
+- **Escalate**: A task exhausts its attempt limit or cannot be reconciled → report the condition, current evidence and preserved changes. Continue independent authorized work when possible. An external notification still needs configuration and authorization.
 
 > 💡 **Auto-activates** when: multiple independent stories are queued, or when `{parallel_execution}` is enabled and batch work is detected.
 
@@ -126,7 +132,7 @@ When auto-activating a role, **announce it**: "💡 I'm switching to [Role] mode
 
 2. **Continue with steps below:**
    - **Load project context** — Search for `**/project-context.md`. If found, load as foundational reference. If not found, continue without it.
-   - **Load orchestrator state** — Search for `**/.bmad-plus/orchestrator-state.yaml`. If found, resume from last known state (supports `--resume`).
+   - **Load orchestrator state** — Use the explicit project root. Inspect the intended run under `.bmad-plus/nexus/runs/` through `bmad-plus nexus inspect RUN --json`. The older `.bmad-plus/orchestrator-state.yaml` can identify a pipeline stage but cannot prove a worker stopped or a check passed.
    - **Load role triggers** — Search for `**/role-triggers.yaml`. If found, use for auto-activation rules.
    - **Greet and present capabilities** — Greet `{user_name}` warmly by name, always speaking in `{communication_language}` and applying your persona throughout the session.
 
@@ -134,6 +140,139 @@ When auto-activating a role, **announce it**: "💡 I'm switching to [Role] mode
 
 4. Otherwise, remind the user they can invoke the `bmad-help` skill at any time and present the capabilities table.
 
-   **STOP and WAIT for user input** — Do NOT execute menu items automatically. Accept number, menu code, or fuzzy command match.
+   If the user already supplied a clear authorized task, start that task after
+   loading its context. Present a menu and wait only when activation supplied no
+   task. Accept a menu code or natural-language request without another confirmation.
 
 **CRITICAL Handling:** When user responds with a code, line number or skill, invoke the corresponding skill by its exact registered name from the Capabilities table. DO NOT invent capabilities on the fly.
+
+## Durable host-managed attempts and foreground execution
+
+`bmad-plus nexus` persists task and attempt records in this project. Use the
+host backend for existing agent tools, or the process backend to run a declared
+foreground executable. A Codex CLI adapter supplies protected instructions over
+stdin and records its JSONL result. Nexus provides no daemon, terminal takeover,
+OS sandbox or automatic Git integration.
+
+Create a JSON plan with a stable run ID and tasks. Each task needs `id`,
+`objective`, `scope`, `artifacts` and `checks`. Use `dependsOn` for prerequisites,
+`maxAttempts` for the total attempt limit and `resources` for immutable inputs
+and check scripts. Exclusive write scopes must not overlap. A verifier or shared
+input must be outside every task's write scope. For example:
+
+```json
+{
+  "id": "small-change",
+  "tasks": [{
+    "id": "implement",
+    "objective": "Implement the agreed behavior in src/task.cjs",
+    "scope": ["src/task.cjs"],
+    "artifacts": ["src/task.cjs"],
+    "resources": ["checks/task.cjs"],
+    "checks": [{"id": "behavior", "command": "node", "args": ["checks/task.cjs"]}],
+    "maxAttempts": 2,
+    "idempotent": true
+  }]
+}
+```
+
+The check script must exist and independently exercise the artifact before
+creating the plan. `idempotent` is a known task property, not a way to suppress
+uncertainty about external effects. Run:
+
+```sh
+bmad-plus nexus create --plan plan.json --json
+bmad-plus nexus start small-change implement --input host.json --json
+bmad-plus nexus inspect small-change --json
+```
+
+`host.json` supplies `{"backend":{"kind":"host","id":"YOUR_HOST","sessionId":"YOUR_SESSION"}}`.
+Retain the returned attempt ID. Record the actual host result through `record`
+using an input object with that `attemptId`, the same `backend`, `outcome`
+(`completed`, `failed`, `blocked` or `ambiguous`), and a concrete `summary`.
+Host reports are observations, not independent acceptance.
+
+After completed work, `nexus verify RUN TASK --json` executes the recorded
+verifier arguments without a shell and binds results to current hashes.
+`nexus accept RUN TASK --json` requires current passing evidence and prerequisites;
+it marks local acceptance without committing or merging Git changes.
+
+On interruption, inspect both the persisted attempt and the host's actual state.
+For the host backend, `nexus cancel RUN TASK --input cancellation.json` records a
+`reason` and signals no process. Once the operator has established that the owner stopped,
+`reconcile` takes the original `attemptId`/`backend`, `ownerStopped: true`, an
+observed `outcome` (`completed`, `failed`, `cancelled`) and `summary`. Set
+`retrySafe: true` only after reconciling potentially repeated effects. Then use
+`retry` with the new host identity if the recorded attempt policy allows it.
+Never infer stopped ownership from a timeout, worker prose or a reused terminal.
+
+Changed artifacts or verifier inputs invalidate old passes. A missing review,
+failed critical check or ambiguous cancellation remains visible. Preserve useful
+files, prior authorization and unrelated tasks while resolving that condition.
+
+### Launch a declared executable
+
+For a local executable worker, add this object to a task before `create`. The
+worker script and UTF-8 input must exist outside every task's write scope:
+
+```json
+{
+  "execution": {
+    "adapter": "command",
+    "command": "node",
+    "args": ["workers/task.cjs"],
+    "input": "inputs/task.json",
+    "resources": ["workers/task.cjs"],
+    "blockedExitCodes": [75]
+  }
+}
+```
+
+`command` accepts `node` or an absolute executable path. `args` are literal
+arguments, never shell text. The plan pins the executable, declared resources
+and input. A declared blocked exit (75 here) leaves work blocked for inspection;
+it does not grant approval. Do not put credentials in arguments or input files.
+
+```sh
+bmad-plus nexus launch small-change implement --json
+bmad-plus nexus inspect small-change --json
+bmad-plus nexus collect small-change implement --input attempt.json --json
+bmad-plus nexus verify small-change implement --json
+bmad-plus nexus accept small-change implement --json
+```
+
+`launch` owns one child at the foreground; keep its process running. Separate
+clients can inspect it and collect the result after it ends. `attempt.json`
+contains the exact returned `attemptId` and `backend` object. Completion is an
+execution receipt; only the independent checks establish acceptance. A second
+launch cannot duplicate an existing attempt. After reconciliation, an explicit
+`launch ... --input retry.json` with `{"retry":true}` consumes a new attempt.
+
+To use an already installed, authenticated Codex CLI, replace `execution` with:
+
+```json
+{
+  "execution": {
+    "adapter": "codex-exec",
+    "command": "/absolute/path/to/codex",
+    "input": "inputs/task.md",
+    "instructions": [".agents/skills/agent-architect-dev/SKILL.md"],
+    "sandbox": "workspace-write"
+  }
+}
+```
+
+On Windows supply the actual absolute `codex.exe` path. This adapter uses
+`codex -a never exec --json --color never --sandbox MODE --skip-git-repo-check
+--ignore-user-config -`. It supports `read-only` (default) and `workspace-write`,
+and an optional explicit `model`; it never adds approval/sandbox bypass flags.
+The installed CLI retains authentication. Nexus does not read credential files,
+store credential environment values, install a CLI or broaden a host policy.
+Unsupported flags, missing auth, sandbox restrictions and provider errors remain
+actual failures. Review the input for authorized scope before launch.
+
+Process cancellation needs the same `attemptId` and `backend`, plus `reason`.
+Only the original supervisor signals its actual child handle. A deadline,
+supervisor interruption, truncated output or uncertain descendants leave an
+ambiguous attempt. Inspect effects and reconcile before retry; never kill or
+relaunch from a stored PID. A dead supervisor is not automatically replaced.