bear-craft
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
Its scripts were only partly scanned.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/TheBeardedBearSAS/bear-craft with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/TheBeardedBearSAS/bear-craft'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/thebeardedbearsas--claude-craft)HTML
<a href="/listings/thebeardedbearsas--claude-craft"><img src="/api/listings/thebeardedbearsas--claude-craft/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# Install to your project (picks your tech stack interactively) npx @the-bearded-bear/bear-craft # Or install directly npx @the-bearded-bear/bear-craft install ~/my-project --tech=react --lang=en # Zero-prompt install (auto-detects your stack + locale, target < 2 min) npx @the-bearded-bear/bear-craft install --auto # Install from a team config URL (Gist or internal endpoint) npx @the-bearded-bear/bear-craft install --from=https://org.example/cc-team.json # Add a community skill from npm (bear-craft-skill-* convention) npx @the-bearded-bear/bear-craft skill add bear-craft-skill-foo # Open Claude Code and run your first audit claude /bear-team:audit
That's it. You get an architecture, security, and quality audit of your project in minutes.
**New to Bear Craft?** Run `/bear-common:getting-started` in Claude Code for a 10-minute guided tour that shows you the 3 most valuable commands for YOUR project.
> See [Quickstart](docs/QUICKSTART.md) for a step-by-step walkthrough with expected output at each stage.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 469 lines
- {
- "$schema": "https://claude.ai/schemas/marketplace.json",
- "name": "bear-craft",
- "owner": {
- "name": "The Bearded Bear",
- "email": "flavien.metivier@gmail.com",
- "url": "https://the-bearded-bear.com"
- },
- "metadata": {
- "description": "Bear Craft — multi-stack framework for Claude Code teams (11 stacks, BMAD v6, QA Recette, Kanban, RTK token optimization)."
- },
- "plugins": [
- {
- "name": "bear-angular",
- "source": "./marketplaces/en/plugins/bear-angular",
- "description": "Angular 22: Frontend TS with Signals, Zoneless, httpResource, Signal Forms. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "angular"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-ansible",
- "source": "./marketplaces/en/plugins/bear-ansible",
- "description": "Ansible: automation architecture, deployment setup, security audit and debugging.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "ansible"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-common",
- "source": "./marketplaces/en/plugins/bear-common",
- "description": "Shared agents, skills, rules, checklists and token/CI/ADR utilities (hooks live in bear-hooks).",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "common"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-coolify",
- "source": "./marketplaces/en/plugins/bear-coolify",
- "description": "Coolify: self-hosted PaaS setup, deployment, backups and debugging.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "coolify"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-csharp",
- "source": "./marketplaces/en/plugins/bear-csharp",
- "description": "C# / .NET 10 LTS / C# 14: Backend with Clean Architecture, CQRS, MediatR, EF Core. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "csharp"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-docker",
- "source": "./marketplaces/en/plugins/bear-docker",
- "description": "Docker: Dockerfile, Compose, CI/CD image pipelines and debugging, with specialist agents.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "docker"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-flutter",
- "source": "./marketplaces/en/plugins/bear-flutter",
- "description": "Flutter / Dart 3.47 / Dart 3.13: Mobile Dart with BLoC v9, Riverpod 3, Material 3, Impeller. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "flutter"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-frankenphp",
- "source": "./marketplaces/en/plugins/bear-frankenphp",
- "description": "FrankenPHP: PHP application server architecture, deployment setup, security audit and debugging.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "frankenphp"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-gate",
- "source": "./marketplaces/en/plugins/bear-gate",
- "description": "Quality gates: PRD, tech spec, backlog, sprint, story, alignment, commit, merge and release.",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "gate"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-hcloud",
- "source": "./marketplaces/en/plugins/bear-hcloud",
- "description": "Hetzner Cloud (hcloud): architecture, deployment setup, security audit and debugging.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "hcloud"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-hooks",
- "source": "./marketplaces/en/plugins/bear-hooks",
- "description": "Default safety hooks: network guard, dangerous-command blocker, sensitive-file protection, pre-commit check and output-size hint (guards fail closed).",
- "version": "10.0.0",
- "category": "safety-hooks",
- "keywords": [
- "bear-craft",
- "claude-code",
- "hooks"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-hooks-full",
- "source": "./marketplaces/en/plugins/bear-hooks-full",
- "description": "Extra hooks of the full profile: quality gate on stop, post-edit lint, tool-failure log, session init/end and Slack notifications. Install it next to bear-hooks.",
- "version": "10.0.0",
- "category": "safety-hooks",
- "keywords": [
- "bear-craft",
- "claude-code",
- "hooks-full"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-hooks-memory",
- "source": "./marketplaces/en/plugins/bear-hooks-memory",
- "description": "Cross-session memory hooks backed by SQLite (session start, prompt submit, post-tool, pre-compact, session end).",
- "version": "10.0.0",
- "category": "safety-hooks",
- "keywords": [
- "bear-craft",
- "claude-code",
- "hooks-memory"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-kubernetes",
- "source": "./marketplaces/en/plugins/bear-kubernetes",
- "description": "Kubernetes: architecture, deployment setup, security audit and troubleshooting.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "kubernetes"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-laravel",
- "source": "./marketplaces/en/plugins/bear-laravel",
- "description": "Laravel 13.x / PHP 8.3+: PHP backend with Actions, Pest 5, Sanctum, AI SDK, Passkey. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "laravel"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-opentofu",
- "source": "./marketplaces/en/plugins/bear-opentofu",
- "description": "OpenTofu: infrastructure-as-code architecture, deployment setup, security audit and debugging.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "opentofu"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-paperclip",
- "source": "./marketplaces/en/plugins/bear-paperclip",
- "description": "Paperclip 2026.1106.0: Governance-first integration platform (control plane + adapters). Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "paperclip"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-pgbouncer",
- "source": "./marketplaces/en/plugins/bear-pgbouncer",
- "description": "PgBouncer: connection pooling architecture, deployment setup, security audit and debugging.",
- "version": "10.0.0",
- "category": "infrastructure",
- "keywords": [
- "bear-craft",
- "claude-code",
- "pgbouncer"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-php",
- "source": "./marketplaces/en/plugins/bear-php",
- "description": "PHP 8.5: Backend PHP 8.5 with PSR-12, PHPStan, Pest PHP. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "php"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-project",
- "source": "./marketplaces/en/plugins/bear-project",
- "description": "Project management: epics, stories, tasks, backlog and sprint tracking with product-owner and tech-lead agents.",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "project"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-python",
- "source": "./marketplaces/en/plugins/bear-python",
- "description": "Python 3.15 / 3.14+: Backend with FastAPI, Pydantic, free-threading, JIT. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "python"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-qa",
- "source": "./marketplaces/en/plugins/bear-qa",
- "description": "Browser acceptance testing (QA Recette) with regression registry and TDD bug fixing.",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "qa"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-react",
- "source": "./marketplaces/en/plugins/bear-react",
- "description": "React 19.3 + Compiler 1.0: Frontend JS/TS with Hooks, Compiler 1.0, Server Components. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "react"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-reactnative",
- "source": "./marketplaces/en/plugins/bear-reactnative",
- "description": "React Native 0.88: Mobile JS/TS New Architecture (JSI, TurboModules, Fabric). Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "react-native"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-ruby",
- "source": "./marketplaces/en/plugins/bear-ruby",
- "description": "Ruby / Rails 8.1 / Ruby 4.0: Backend Ruby 4.0 with Rails 8.1, Hotwire, Solid Queue, RSpec/Minitest. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "ruby"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-rust",
- "source": "./marketplaces/en/plugins/bear-rust",
- "description": "Rust / Axum 0.8 / Rust 1.99: Backend Rust 1.99 (edition 2024) with Axum 0.8, Tokio, SQLx, cargo-nextest. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "rust"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-symfony",
- "source": "./marketplaces/en/plugins/bear-symfony",
- "description": "Symfony / PHP 8.1 / PHP 8.4+: PHP backend with Clean Architecture, DDD, API Platform. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "symfony"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-tauri",
- "source": "./marketplaces/en/plugins/bear-tauri",
- "description": "Tauri 2.12: Desktop & mobile apps: Rust core + web frontend, capabilities/permissions, plugins, signed updater. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "tauri"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-team",
- "source": "./marketplaces/en/plugins/bear-team",
- "description": "Parallel multi-agent teams: audit, security review and sprint delivery.",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "team"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-uiux",
- "source": "./marketplaces/en/plugins/bear-uiux",
- "description": "UI/UX/accessibility audits, component specs, design tokens, user flows and DESIGN.md.",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "uiux"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-vercel",
- "source": "./marketplaces/en/plugins/bear-vercel",
- "description": "Vercel 65.14.0: Framework-agnostic deployment platform: vercel.json, Functions (Node.js/Fluid Compute), ISR, Cron Jobs, Storage. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "vercel"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-vite",
- "source": "./marketplaces/en/plugins/bear-vite",
- "description": "Vite 8.3: Framework-agnostic build tool: vanilla JS/TS, library authoring, multi-page apps. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "vite"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-vuejs",
- "source": "./marketplaces/en/plugins/bear-vuejs",
- "description": "Vue.js 3.5+: Frontend JS/TS with Composition API, Pinia, Vitest. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "vuejs"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-wordpress",
- "source": "./marketplaces/en/plugins/bear-wordpress",
- "description": "WordPress 7.1: Plugins & block themes: blocks (block.json), REST API, WP-CLI, WPCS/PHPStan, wp-env; WooCommerce as opt-in skill. Audit and generation commands, reviewer agent and stack skills.",
- "version": "10.0.0",
- "category": "technology-stack",
- "keywords": [
- "bear-craft",
- "claude-code",
- "wordpress"
- ],
- "license": "MIT"
- },
- {
- "name": "bear-workflow",
- "source": "./marketplaces/en/plugins/bear-workflow",
- "description": "BMAD v6 sprint workflow: init, plan, design, start, implement, review, retro and status.",
- "version": "10.0.0",
- "category": "development-framework",
- "keywords": [
- "bear-craft",
- "claude-code",
- "workflow"
- ],
- "license": "MIT"
- }
- ]
- }
README.md · README · 506 lines
- # Bear Craft — Sprint workflow, multi-stack reviewers, and browser QA for Claude Code teams
- > **The AI framework where bugs don't come back.** Sprint workflow, a continuous build loop, browser-based acceptance testing, and token-optimized multi-stack reviewers for tech leads adopting Claude Code with their team. **11 stacks, 5 languages, BMAD v6.**
- ## Why teams pick Bear Craft
- Four things Claude Code + an Anthropic cookbook **won't** give you — they're workflow and orchestration, not prompts:
- | Differentiator | What it does |
- |----------------|--------------|
- | 🏆 **QA Recette** (browser-based) | `/bear-qa:recette` drives Chrome to run acceptance tests and auto-generates a regression test for every bug you fix — the Golden Rule: a fixed bug never comes back. No other Claude Code framework does this. |
- | 🚀 **BMAD v6 sprint workflow** | Analyze → Plan → Design → Implement → QA, executed by Claude Code directly with quality gates. Quick Flow < 5 min, Standard < 15 min, Enterprise < 30 min. |
- | 🔁 **Ralph Wiggum loop** | `/bear-common:ralph-run` runs Claude in a continuous loop until your Definition of Done holds — adaptive circuit breaker, native `/goal` integration, DoD validators. |
- | ⚡ **RTK token optimization** | Forked sub-agents, `context: fork` on heavy skills, 1h prompt caching, Haiku/Sonnet/Opus routing per task. Target 55-65% token savings vs raw Claude Code. |
- Plus **11 stack-specific reviewers** (@symfony-reviewer, @react-reviewer, @python-reviewer…) that enforce SOLID/TDD/Clean Architecture so you don't re-type your conventions every sprint.
- > **Why not just Claude Code + a cookbook?** Claude already knows React, Symfony, and Flutter patterns — so Bear Craft's value isn't the prompts, it's the **workflow and orchestration around them**: a sprint lifecycle with gates, a continuous loop with a real DoD, browser-based regression capture, and per-task token routing. Those are the parts a per-stack cookbook doesn't cover.
- [](https://www.npmjs.com/package/@the-bearded-bear/bear-craft)
- [](https://www.npmjs.com/package/@the-bearded-bear/bear-craft)
- [](https://code.claude.com)
- [](https://github.com/TheBeardedBearSAS/bear-craft/actions/workflows/npm-publish.yml)
- [](https://opensource.org/licenses/MIT)
- [](https://dashboard.stryker-mutator.io/reports/github.com/TheBeardedBearSAS/bear-craft/main)
- [](https://sonarcloud.io/summary/new_code?id=TheBeardedBearSAS_claude-craft)
- [](https://sonarcloud.io/summary/new_code?id=TheBeardedBearSAS_claude-craft)
- [](https://sonarcloud.io/summary/new_code?id=TheBeardedBearSAS_claude-craft)
- [](https://sonarcloud.io/summary/new_code?id=TheBeardedBearSAS_claude-craft)
- 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 — **33 specialized agents (+39 infra agents on-demand), 82 commands across 18 namespaces, 55 skills**, all token-optimized via `context: fork` and sub-agent model routing.
- ## What's New in v10.0.0
- **Claude Craft devient Bear Craft (2026-11-17, v10.0.0) :**
- - **Nouveau nom** : paquet `@the-bearded-bear/bear-craft`, commande `bear-craft` (l'alias `claude-craft` reste en 10.x), dépôt `TheBeardedBearSAS/bear-craft`, plugins et marketplace `bear-craft`. Claude Code réserve le préfixe `claude-` aux plugins d'Anthropic.
- - **Installation par plugins Claude Code** : `bear-craft install` installe dans le projet les plugins de la langue choisie (5 langues, 35 plugins chacune), puis copie les règles. Commandes, agents et skills portent **le même nom quel que soit le canal** : `/bear-react:check`, `/bear-workflow:plan`, `bear-common:tdd-coach`. Infra en plugins (`/bear-docker:architecture`…), hooks en plugins dédiés (`bear-hooks`, `bear-hooks-full`, `bear-hooks-memory`). Nouvelle commande `bear-craft sync` après un clone. Prérequis : Claude Code (`claude`).
- - **Retraits** : les stubs de redirection dépréciés depuis la 9.0 disparaissent (table de correspondance dans le guide de migration) ; `bear-craft update` les nettoie.
- - **Migration** : `bear-craft update` convertit une installation 9.x (fichiers de l'utilisateur conservés). Guide : [MIGRATION-v10](docs/MIGRATION-v10.md). Détails : [CHANGELOG](CHANGELOG.md#1000---2026-11-17).
- ## What's New in v9.4.0
- **Dernière version 9.x — sécurité Claude Code et hooks fail-closed (2026-11-17, v9.4.0) :**
- - **Claude Code** : minimum de sécurité relevé à 2.1.325 (contournements de permissions Bash/sandbox corrigés en 2.1.323 et 2.1.325), version recommandée 2.1.326 ; `bear-craft doctor` échoue sous le minimum, et chaque plugin déclare `engines["claude-code"]: ">=2.1.325"`.
- - **Hooks** : les trois gardes de sécurité bloquent l'appel d'outil si leur script manque, plante ou dépasse son timeout (`onFailure: "block"`) ; la réinstallation met à niveau les projets existants.
- - **Annonce** : Claude Craft devient **bear-craft** en 10.0.0 (paquet `@the-bearded-bear/bear-craft`, commande `bear-craft`, alias `claude-craft` conservé en 10.x). Détails : [CHANGELOG](CHANGELOG.md#940---2026-11-17).
- ## What's New in v9.3.0
- **Kanban en écriture et qualité mesurée (2026-11-16, v9.3.0) :**
- - **Kanban** (`bear-craft kanban`) : création, édition et suppression de stories, planification du backlog, création/démarrage/clôture de sprint avec report, limites WIP, vélocité ; écriture sûre dans `.bmad/sprint-status.yaml` (verrou partagé, détection de conflit) ; interface en 5 langues, accessibilité vérifiée par axe.
- - **Qualité** : analyse SonarCloud en CI à chaque PR (0 issue, quality gate vert, couverture 95 %), score de mutation Stryker publié sur le dashboard ; badges dans ce README.
- - **Sécurité** : `npm ci --ignore-scripts` dans toute la CI, téléchargements HTTPS uniquement, permissions des workflows au plus juste, expressions régulières sans retour arrière super-linéaire, `hono` mis à jour (GHSA-4m76-xfj5-7975). Détails : [CHANGELOG](CHANGELOG.md#930---2026-11-16).
- ## What's New in v9.2.1
- **Audit de fraîcheur du 2026-11-11 (v9.2.1) :**
- - **Sécurité** : PgBouncer 1.26.1 (CVE-2026-107350, usurpation d'un utilisateur SCRAM), FrankenPHP 1.13.5 (PHP2Shell), Docker Engine 29.9.3, OpenTofu 1.13.9 ; règle 11 alignée sur NIST SP 800-63B-4 (15 caractères pour un mot de passe seul facteur, blocklist) ; types de serveurs Hetzner retirés remplacés.
- - **Exemples corrigés** : `array_first()` PHP 8.5, Laravel AI SDK (`laravel/ai`), Signal Forms Angular, configuration Vitest `projects`.
- - **Versions vérifiées sur registres** : React Native 0.88 / Expo SDK 58, Vercel CLI 65, Paperclip 2026.1106.0, Coolify 4.7.5, Kubernetes 1.37.2, ansible-core 2.22, Helm 4.3.1 ; Node 26 Active LTS, testé en CI (22 / 24 / 26).
- - **Aussi dans cette version** : stack WordPress 7.1 (`--tech=wordpress`), hooks installés par défaut (`--hooks=default|full|none`), Fable 5.2 et Claude Code 2.1.322 recommandé. Détails : [CHANGELOG](CHANGELOG.md#921---2026-11-11).
- ## What's New in v9.2.0
- **Deux nouveaux stacks (2026-11-09, v9.2.0) :** Rust / Axum (15e) et Tauri (16e), Claude Code recommandé : 2.1.319. Détails : [CHANGELOG](CHANGELOG.md#920---2026-11-09).
- **Nouveau stack WordPress (2026-11-10) :** `--tech=wordpress` (communautaire) installe WordPress 7.1 pour plugins et thèmes blocs : 6 règles en anglais (architecture plugin/thème, hooks, `block.json`/`render.php`, REST `permission_callback`, WP-CLI, WPCS/PHPStan, wp-env, tests `WP_UnitTestCase` / Playwright), l'agent `@wordpress-reviewer` et `/bear-wordpress:check <axe>` dans les 5 langues. **Modulaire** : WooCommerce 11.2 (HPOS, Store API, blocs Cart/Checkout) est livré comme skill `woocommerce` chargé à la demande, absent du contexte d'un WordPress simple. Détails : [CHANGELOG](CHANGELOG.md#unreleased).
- **Nouveau stack Tauri v2 (2026-11-09) :** `--tech=tauri` (communautaire) installe Tauri 2.12 pour applications desktop et mobile (cœur Rust, front web agnostique) : 6 règles en anglais (architecture `src-tauri/`, commands/IPC, capabilities et permissions, CSP, pattern Isolation, updater signé, tests mock runtime / `mockIPC` / WebdriverIO), l'agent `@tauri-reviewer` et `/bear-tauri:check <axe>` dans les 5 langues. Détails : [CHANGELOG](CHANGELOG.md#920---2026-11-09).
- **Nouveau stack Rust / Axum (2026-11-08) :** `--tech=rust` installe Rust 1.99 (édition 2024) + Axum 0.8 (workspace en couches, Tokio, Tower, SQLx, thiserror + RFC 9457, cargo-nextest, Clippy, cargo-deny) dans les 5 langues : 6 règles, l'agent `@rust-reviewer` et `/bear-rust:check <axe>`. Détails : [CHANGELOG](CHANGELOG.md#920---2026-11-09).
- ## What's New in v9.1.0
- **Nouveau stack Ruby / Rails (2026-11-01, v9.1.0) :** `--tech=ruby` installe Ruby 4.0 + Rails 8.1 (Rails Way, service/form/query objects, Hotwire, Solid Queue, RSpec ou Minitest, RuboCop, Brakeman) dans les 5 langues : 6 règles, l'agent `@ruby-reviewer` et `/bear-ruby:check <axe>`. Claude Code recommandé : 2.1.316. Détails : [CHANGELOG](CHANGELOG.md#910---2026-11-01).
- ## What's New in v9.0.0
- **BREAKING — retrait des commandes dépréciées (2026-10-29, v9.0.0) :** les 54 stubs de redirection (PM, `/bear-common:research-context7`, `/bear-uiux:orchestrator`) et le namespace `/sprint:` sont supprimés ; `bear-craft update` les efface des projets. Table de correspondance : [MIGRATION-v9](docs/MIGRATION-v9.md). Détails : [CHANGELOG](CHANGELOG.md#900---2026-10-29).
- **Un seul `/<tech>:check <axe>` par stack (v9.0.0) :** `/bear-react:check architecture|code-quality|security|testing|all` remplace les 5 `check-*` de chaque stack (`all` = audit noté sur 100) ; `/bear-team:sprint` devient `/bear-team:delivery --phase=implementation`. Les anciens noms restent des stubs de redirection jusqu'en 10.0. Table : [MIGRATION-v9](docs/MIGRATION-v9.md).
- ## What's New in v8.27.0
- **Les commandes `/bear-team:*` sans Agent Teams (2026-10-28, v8.27.0) :** `/bear-team:audit`, `/bear-team:security`, `/bear-team:sprint` et `/bear-team:delivery` délèguent par défaut à des sous-agents (`--engine=subagents`, compatible `claude -p` et CI) ; Agent Teams devient optionnel (`--engine=teams`, repli automatique si `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` est absent). `/bear-common:research-context7` et `/bear-uiux:orchestrator` sont dépréciées au profit du MCP context7 / `/deep-research` et de l'agent `@uiux-orchestrator`. Ralph est fiabilisé en mode parallèle (sessions et worktrees isolés). Claude Code recommandé : 2.1.312. Dernière version 8.x avant la 9.0. Détails : [CHANGELOG](CHANGELOG.md#8270---2026-10-28).
- ## What's New in v8.26.0
- **Un parcours principal pour la gestion de projet (2026-10-26, v8.26.0) :** `/bear-workflow:init → plan → design → start → implement → review → retro` (+ `/bear-workflow:status` à tout moment, `/bear-workflow:auto-sprint` de bout en bout). Le namespace `/sprint:` et les générateurs `/bear-project:*` deviennent des stubs de redirection jusqu'en 9.0. Il reste 35 commandes de gestion de projet actives au lieu de 86. Guide : [Quel parcours ?](docs/guides/en/11-which-path.md). Détails : [CHANGELOG](CHANGELOG.md#8260---2026-10-26).
- ## What's New in v8.25.0
- **Fusion des commandes `/project:` et `/gate:` (2026-10-26, v8.25.0) :** 5 commandes `/project:` (`backlog`, `reverse`, `trace`, `report`, `migrate`) et une seule `/bear-gate:check` remplacent 41 commandes ; les anciennes restent des stubs de redirection jusqu'en 9.0. Détails : [CHANGELOG](CHANGELOG.md#8250---2026-10-26).
- ## What's New in v8.24.0
- **Source de vérité unique du statut (2026-10-26, v8.24.0) :** `.bmad/sprint-status.yaml` porte désormais seul le statut des stories et des tâches. Les fichiers markdown ne portent que le contenu, et le Kanban écrit les déplacements dans la YAML. Nouveau guide [Quel parcours ?](docs/guides/en/11-which-path.md). Les commandes retirées sont désormais supprimées à l'upgrade (`config/removed-commands.yaml`), et les commandes mainteneur ne sont plus installées dans les projets. Détails : [CHANGELOG](CHANGELOG.md#8240---2026-10-26).
- ## What's New in v8.23.4
- **Cohérence des commandes de gestion de projet (2026-10-26, v8.23.4) :** 65 références vers des commandes inexistantes corrigées dans les 5 langues (nouveau garde-fou CI `command-refs.test.mjs`) ; gates alignées sur `project-management/` ; arborescence de sprint unique (`board.md` + `tasks/TASK-*.md`) ; `/bear-workflow:init` crée `.bmad/sprint-status.yaml` ; `/bear-workflow:auto-sprint` démarre un sprint inexistant. Détails : [CHANGELOG](CHANGELOG.md#8234---2026-10-26).
- ## What's New in v8.23.3
- **Maintenance sécurité (2026-10-26, v8.23.3) :** 30 alertes Dependabot résolues, toutes en dépendances de développement (`dompurify` 3.4.17 — *critical*, `vite`, `vitest` 4.1.12, `devalue`…). `npm audit` à 0 à la racine et dans `website/`. Détails : [CHANGELOG](CHANGELOG.md#8233---2026-10-26).
- ## What's New in v8.23.2
- **Correctif de sécurité (2026-10-26, v8.23.2) :**
- - **`zod` 4.6.7** : corrige GHSA-mrhx-c7xc-m3w5 (*high*, épuisement mémoire à la validation).
- - **Précédence modèle des sous-agents** bornée à Claude Code 2.1.251+ dans la règle 12 (5 langues) et la FAQ, avec un garde-fou CI (`claimDenylist`) contre le retour d'affirmations périmées sur les modèles. Détails : [CHANGELOG](CHANGELOG.md#8232---2026-10-26).
- ## What's New in v8.23.1
- **Correctifs d'installation, Kanban et workflow (2026-10-22, v8.23.1) :**
- - **Installation adaptée à la stack** : `--tech=a,b,c` rend le `CLAUDE.md` racine, `AGENTS.md` et `.claude/settings.json` selon les technos réellement installées ; `install-project-commands.sh` n'écrase plus les fichiers existants ; `@tech-lead` agnostique de la stack ; `make config-*` et `check-config.sh` réparés.
- - **Kanban** : lecture des backlogs générés depuis les templates (métadonnées en liste Markdown), plus de documents dupliqués, retrait complet des commentaires HTML imbriqués (alerte CodeQL).
- - **Workflow** : `/bear-workflow:start` crée `.bmad/sprint-status.yaml`, `/bear-gate:check sprint` fonctionne sans lui. Dépendances et GitHub Actions à jour. Détails : [CHANGELOG](CHANGELOG.md#8231---2026-10-22).
- ## What's New in v8.23.0
- **Audit de fraîcheur + alignement Claude (2026-10-13, v8.23.0) :**
- - **Sécurité** : classement OWASP Top 10:2025 officiel (A01–A10) dans la règle 11 et ses miroirs, avec test de régression ; FrankenPHP 1.13.0 et PgBouncer 1.26.0 (versions précédentes vulnérables) ; types de serveurs Hetzner et `datacenter` retirés corrigés.
- - **Versions vérifiées sur registres** : React 19.3, Flutter 3.47, React Native 0.87 / Expo 57, Pinia 4, Vite 8.3 (`rolldownOptions`), Vercel CLI 63, Python 3.15, Paperclip 2026.1012.0, Docker 29.9, Kubernetes 1.37 (Gateway API), Vitest 5, Pest 5, pytest 9, PER-CS 3.0.
- - **Claude Code** : minimum 2.1.260, recommandé 2.1.312, modèles 5.5. Détails : [CHANGELOG](CHANGELOG.md#8230---2026-10-13).
- ## What's New in v8.18.0
- **Nouvelle commande `/bear-workflow:auto-sprint` (2026-06-27, v8.18.0) :**
- - **Orchestrateur de sprint de bout en bout** : une seule commande joue le rôle Product Owner / Scrum Master et enchaîne `start → decompose → validate → implement → PR → CI watch → review → retro → merge`. Chaque cérémonie tourne dans un **sous-agent au contexte isolé** — l'isolation remplace le `/clear` manuel entre étapes ; la phase d'implémentation assume le rôle conductor **inline** (réutilise `/bear-team:sprint`).
- - **PR + CI + merge intégrés** (`gh`) : `--auto-merge` opt-in (défaut : pause + GO humain) ; échec de gate (validate KO / CI rouge / DoD miss) → **auto-fix loop** borné (`--max-fix-attempts`).
- - **5 langues** (`Dev/i18n/{en,fr,es,de,pt}`) ; compteurs réalignés **126 core / 220 total** commandes.
- ## What's New in v8.17.2
- **Revue documentation (2026-06-26, v8.17.2) :**
- - **Nouveau tutoriel phare** : `docs/guides/*/10-complete-workflow.md` réécrit en walkthrough narré de bout en bout (idée → backlog → sprint → livraison) pour grands débutants — glossaire, modes d'exécution, gates, discipline `/clear`, exemple *TaskFlow* + annexe multi-stack. Disponible en 5 langues, lié depuis le README et `guides/index.md`.
- - **Fraîcheur** : compteurs et versions réalignés sur le SSOT (125 core / 219 total commandes, 70 agents, 55 skills, 11 stacks ; versions Claude Code min/recommandée ; Flutter 3.44, RN 0.85, Symfony 8.1). Suppression de `/bmad:init` (→ `/bear-workflow:init`).
- - **Sans doublon** : index des guides de migration, en-têtes « narré vs full » (COMMANDS/AGENTS), bannière PLANNED sur MCP-SERVERS, cross-links entre docs concurrentielles, stub `docs/SECURITY.md` supprimé.
- ## What's New in v8.17.1
- **Correctifs tests (2026-06-26, v8.17.1) :**
- - **`tests/scripts/` sous docker sans bash** : les 12 fichiers shell-out `bash "*.sh"` échouaient en `/bin/sh: bash: not found` sous busybox/alpine. Nouveau target `make test-scripts-docker` (image bash, `node:24`) + garde `tests/scripts/bash-available.test.mjs`.
- **Audit exhaustif multi-agents + mises à jour 2026-06-24 (v8.17.0) :**
- - **Versions infra** : Docker 29.6.1, OpenTofu 1.12.2, Ansible 2.21.1, Helm 4.2.2, Node.js 24.x Active LTS.
- - **Sécurité** : OWASP Top 10:2025 complet (10/10 catégories dans la règle 11) ; RS256 marqué DEPRECATED ; guidance Argon2id précisée ; hook templates `protect-files.json` / `quality-gate.json` corrigés (anti-pattern `$TOOL_INPUT` → lecture stdin JSON).
- - **Modèles** : IDs canoniques dans la table d'effort (Opus 4.8 / **Sonnet 5** sorti 2026-06-30, intro $2/$10 / Haiku 4.5). Sonnet 5 remplace 4.6 comme Sonnet courant. Fable 5 / Mythos 5 alors retirés des recommandations (note corrigée par l'audit d'alignement du 2026-10-13 : Fable 5.1 est courant, Mythos réservé au Cyber Verification Program).
- - **CLI** : `/goal`, `/usage`, `/workflows` documentés dans CLI-REFERENCE.md.
- - **Optimisation tokens** : `ENABLE_PROMPT_CACHING_1H` et `fallbackModel` activés dans `settings.json` distribué.
- - **Docs** : compteur commandes corrigé (133 → 125 core / 219 total) ; TROUBLESHOOTING, FAQ, CHEAT-SHEET, COMPETITIVE-ANALYSIS enrichis.
- **Dépendances et supply chain (v8.16.0 / v8.16.1) :**
- - **Trivy action** : `aquasecurity/trivy-action` mis à jour (v8.16.0) — scan CVE supply chain.
- - **Download artifact** : `actions/download-artifact` bumped de 4.2.1 à 8.0.1 (v8.16.0).
- - **CodeQL action** : `github/codeql-action` mis à jour (v8.16.0) — analyse SAST.
- - **Playwright** : `@playwright/test` mis à jour de 1.60.0 à 1.61.0 dans `/website` (v8.16.0).
- - **Patch de stabilité** : correctifs de dernière minute (v8.16.1).
- **Refonte du design de l'interface web Kanban (v8.15.0) :**
- - **Thème dark-only opiniâtre** d'après une maquette **Claude Design** : accent **acid-lime** (oklch, distinct des six teintes de statut), typographie **Space Grotesk + JetBrains Mono** auto-hébergée via `@fontsource` (CSP `font-src 'self'`).
- - **Panneau Tweaks** : code couleur des cartes (statut / priorité / TDD / epic), accent et densité, persistés en `localStorage`.
- - **Les 6 vues restylées** (board, backlog, sprints, burndown, deps, docs) ; drag&drop, navigation clavier, `<dialog>` natifs et a11y préservés. Coloration en helpers JS purs testés.
- **Interface web Kanban — accès à tous les artefacts BMAD v6 (v8.14.0) :**
- - **Vue Sprints dédiée** : navigation listant **tous** les sprints (points, stories, badges goal/review/retro) ; le détail rend le Goal, les Stories avec leurs Tasks dépliables, et les sections **Review** et **Retro** en markdown (`GET /api/sprints`, `GET /api/sprints/:id`).
- - **Docs élargis** : les corps markdown des EPIC, US, sprint-goal/board/review/retro sont désormais navigables dans le DocsView.
- - **Détail US enrichi** : la modale du board affiche la **liste des tâches associées** et la **description** de la story (`/api/stories/:id` renvoie `body`). Tests RED-first, suite complète verte.
- **Corrections de l'interface web Kanban (v8.13.1) :**
- - **Dashboard Kanban réparé** : 4 bugs corrigés en TDD sur le SPA Svelte 5 (`bear-craft kanban`) — vue Backlog vide (stories à `epic_id` inconnu désormais regroupées au lieu d'être perdues), raccourcis clavier inopérants (synchronisation focus + reducer pur), détails de carte inaccessibles (modale au clic/Entrée), et feedback visible (toast) au lieu d'un échec silencieux sur les cartes read-only `sprint-status.yaml`.
- **Fiabilité BMAD + distribution AgentTeams (v8.13.0) :**
- - **`/bear-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 `/bear-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) :**
- - **Audit multi-domaines** (sécurité, DX, concurrentiel, fiabilité, tokens/modèles, docs, architecture) mené par une équipe d'agents avec devil's advocates et vérification de fraîcheur des 14 stacks -- 80 findings, tous les P0/P1/P2 corrigés.
- - **Sécurité** : CVE FrankenPHP (CVE-2026-45062) et Docker (CVE-2026-33997) patchées ; hook de sécurité distribué corrigé (`exit 2`) ; durcissement Kanban (CSRF, COEP) et CI supply chain (digests épinglés, SHA256).
- - **Optimisation tokens** : templates `settings.json` distribués corrigés (IDs de modèles valides + `CLAUDE_CODE_FORK_SUBAGENT`).
- - **988 Vitest tests** green, mutation testing bloquant sur PRs.
- **Kanban BMAD v6 integration (v8.11.0):**
- - **Kanban ingère `.bmad/sprint-status.yaml`** -- le board Kanban lit les sprints directement depuis le fichier YAML BMAD v6 en lecture seule (icône verrou), sans dépendance SaaS. Les projets BMAD v6 n'ont plus le board vide. *Depuis, le Kanban n'est plus en lecture seule : il permet de créer, modifier et déplacer des stories, de planifier, démarrer et clôturer un sprint et de régler des limites WIP, en écrivant dans `.bmad/sprint-status.yaml` (voir [CLI-REFERENCE](docs/CLI-REFERENCE.md#kanban-command)) ; `--readonly` désactive toute écriture.*
- **Releases 8.8.x → 8.10.x :**
- - **MIT-only strict (v8.8.0)** -- Bear Craft est 100 % open-source MIT, aucune licence commerciale ou enterprise. Stratégie open-core abandonnée.
- - **Parité i18n stricte (v8.8.2)** -- la CI bloque désormais si un fichier traduit est à < 80 % de la taille de l'anglais. Dette i18n résorbée (gap 101 → 0).
- - **Branding the-bearded-bear.com (v8.10.1)** -- migration complète des domaines vers `the-bearded-bear.com`, normalisation de l'organisation GitHub.
- - **126 commandes sur 15 namespaces (v8.10.x)** (220 total avec infra/projet) -- namespace `/bear-paperclip:*` (8 commandes) ajouté, 55 skills disponibles.
- - **Claude Code 2.1.326** -- version recommandée (minimum sécurité 2.1.325 ; Opus 5.5 / Sonnet 5.5 / Haiku 5.5, MCP 2026-07-28, hooks `onFailure: "block"`).
- > ← Versions antérieures (v8.0 → v8.7) : voir le [CHANGELOG](CHANGELOG.md) et [.claude/COMPATIBILITY.md](.claude/COMPATIBILITY.md).
- ## Install and First Result
- ```bash
- # Install to your project (picks your tech stack interactively)
- npx @the-bearded-bear/bear-craft
- # Or install directly
- npx @the-bearded-bear/bear-craft install ~/my-project --tech=react --lang=en
- # Zero-prompt install (auto-detects your stack + locale, target < 2 min)
- npx @the-bearded-bear/bear-craft install --auto
- # Install from a team config URL (Gist or internal endpoint)
- npx @the-bearded-bear/bear-craft install --from=https://org.example/cc-team.json
- # Add a community skill from npm (bear-craft-skill-* convention)
- npx @the-bearded-bear/bear-craft skill add bear-craft-skill-foo
- # Open Claude Code and run your first audit
- claude
- /bear-team:audit
- ```
- That's it. You get an architecture, security, and quality audit of your project in minutes.
- **New to Bear Craft?** Run `/bear-common:getting-started` in Claude Code for a 10-minute guided tour that shows you the 3 most valuable commands for YOUR project.
- > See [Quickstart](docs/QUICKSTART.md) for a step-by-step walkthrough with expected output at each stage.
- ## Why Bear Craft?
- Claude Code is powerful on its own. Bear Craft makes it **consistent and team-ready**:
- - **Standardized rules** -- SOLID, Clean Architecture, TDD enforced across your team, not just suggested
- - **33 default agents + 39 infra agents on-demand** -- reviewers, architects, coaches that know your stack deeply (72 total potentially installable)
- - **82 slash commands across 18 namespaces** -- repeatable workflows for audits, code generation, sprint management
- - **Quality gates** -- automated checks at every stage from PRD to deployment
- - **5 languages** -- English, French, Spanish, German, Portuguese
- ## Supported Technologies
- | Stack | Version | Install Command |
- |-------|---------|-----------------|
- | **Symfony / PHP** | 8.1 / PHP 8.4+ | `--tech=symfony` |
- | **React** | 19.3 + Compiler 1.0 | `--tech=react` |
- | **Flutter / Dart** | 3.47 / Dart 3.13 | `--tech=flutter` |
- | **Python** | 3.15 / 3.14+ / FastAPI | `--tech=python` |
- | **Angular** | 22 | `--tech=angular` |
- | **Vue.js** | 3.5+ (3.6 RC Vapor) | `--tech=vuejs` |
- | **Vite** _(community)_ | 8.3 | `--tech=vite` |
- | **Vercel** _(community)_ | 65.14.0 | `--tech=vercel` |
- | **Tauri** _(community)_ | 2.12 (desktop + mobile) | `--tech=tauri` |
- | **WordPress** _(community)_ | 7.1 (plugins + block themes, WooCommerce opt-in) | `--tech=wordpress` |
- | **React Native** | 0.88 (New Architecture) | `--tech=reactnative` |
- | **C# / .NET** | 10 LTS / C# 14 | `--tech=csharp` |
- | **Laravel** | 13.x / PHP 8.3+ (8.5 recommandé) | `--tech=laravel` |
- | **PHP** | 8.5 | `--tech=php` |
- | **Ruby / Rails** | Rails 8.1 / Ruby 4.0 | `--tech=ruby` |
- | **Rust / Axum** | Axum 0.8 / Rust 1.99 | `--tech=rust` |
- | **Paperclip** | 2026.1106.0 | `--tech=paperclip` |
- | **Docker** | 29.9.3 | `--tech=docker` |
- | **Coolify** | v4.7.5 | `--tech=coolify` |
- | **Kubernetes** | 1.37.2 | `--tech=kubernetes` |
- | **OpenTofu** | 1.13.9 | `--tech=opentofu` |
- | **Ansible** | 2.22.0 | `--tech=ansible` |
- | **Hcloud** | provider 1.70+ / CLI 1.70.2 | `--tech=hcloud` |
- | **PgBouncer** | 1.26.1 (security fixes over 1.26.0) | `--tech=pgbouncer` |
- | **FrankenPHP** | 1.13.5 (PHP2Shell and later security fixes) | `--tech=frankenphp` |
- See [Technologies](docs/TECHNOLOGIES.md) for full details.
- ## What's Included
- | Category | Count | Examples |
- |----------|-------|---------|
- | **Agents** | 31 default (+ 39 infra on-demand) | `@tdd-coach`, `@api-designer`, `@symfony-reviewer`, `@kubernetes-architect`, `@hcloud-architect` |
- | **Commands** | 82 across 18 namespaces (135 total with infra/project) | `/bear-workflow:init`, `/bear-team:audit`, `/bear-react:generate-component` |
- | **Skills** | 55 | Architecture, testing, security, DDD best practices |
- | **Templates** | 21 | Code generation patterns, BMAD project templates |
- | **Checklists** | 10 | Commit, feature, release quality gates |
- See [Agents](docs/AGENTS.md) | [Commands](docs/COMMANDS.md) | [Skills](docs/SKILLS.md)
- ## Workflow Tracks
- Bear Craft adapts to your project complexity with three development tracks:
- | Track | Setup | Phases | Best For |
- |-------|-------|--------|----------|
- | **Quick Flow** | < 5 min | Implementation only | Bug fixes, hotfixes |
- | **Standard** | < 15 min | Plan > Design > Implement | New features, refactoring |
- | **Enterprise** | < 30 min | Analyze > Plan > Design > Implement | Platforms, migrations |
- ```bash
- /bear-workflow:init # Auto-detects complexity
- /bear-workflow:init --quick # Bug fix mode
- /bear-workflow:init --enterprise # Full methodology
- ```
- See [BMAD Practical Guide](docs/BMAD-PRACTICAL-GUIDE.md) for the complete project management framework.
- ## Key Commands
- These are the commands you'll use most:
- | Command | What It Does |
- |---------|-------------|
- | `/bear-workflow:init` | Start a development workflow (auto-detects track) |
- | `/bear-team:audit` | Full project audit (architecture, security, quality) |
- | `/bear-gate:check commit` | Validate before committing |
- | `/bear-project:backlog next story` | Get next story ready for development |
- | `/bear-qa:tdd` | Test-Driven Development flow |
- | `/bear-gate:check story` | Check story meets Definition of Done |
- | `/{tech}:check <axis>` | Audit architecture, code-quality, security, testing, or all (scored) |
- | `/{tech}:generate-*` | Generate code following project patterns |
- | `/bear-common:ralph-run "task"` | Run Claude in continuous loop until task is done |
- | `/bear-qa:recette` | Automated acceptance testing via Chrome |
- See [CLI Reference](docs/CLI-REFERENCE.md) for all 82 commands across 18 namespaces (135 total including infra and project management).
- ## Installation
- > **Platform:** Linux and macOS. Windows is not tested and not officially supported.
- ### NPX (Recommended)
- ```bash
- npx @the-bearded-bear/bear-craft install ~/my-project --tech=symfony --lang=en
- ```
- ### What `bear-craft install` does (10.0)
- It installs the `bear-*` plugins **in project scope through Claude Code** (so `claude` must be installed: no fallback) and copies only what plugins cannot carry — `.claude/rules`, `.claude/references`, `CLAUDE.md`, `AGENTS.md`, `settings*.json`, `.github/`, `Tools/AgentTeams/lib`, `project-management/`. The marketplace of your language is copied to `.bear-craft/marketplace/` (versioned with your project, works offline) and recorded in `.bear-craft/install.json`, under a marketplace name unique to the project (`bear-craft-<8 hex>`) so projects on the same machine never share plugins. Commands, agents and skills therefore have the same names (`/bear-react:check`, `bear-common:tdd-coach`) whether you install through the CLI or the plugin marketplace. After a `git clone`, run `bear-craft sync` once per machine. Community skills added with `bear-craft skill add` are plain copies under `.claude/skills/community/` and are **not** `bear-` prefixed.
- ```bash
- bear-craft install ~/my-project --tech=react,symfony --infra=docker,kubernetes --lang=fr --hooks=full
- bear-craft sync # after a clone: re-register the marketplace and plugins on this machine
- bear-craft update # new version: refresh the marketplace, rules and plugins; migrate old copies
- ```
- ### Claude Code plugin
- One plugin per command namespace and per stack, each prefixed with `bear-` so commands never clash with project commands or other plugins (`/bear-react:check`, `/bear-workflow:init`):
- ```
- /plugin marketplace add TheBeardedBearSAS/bear-craft
- /plugin install bear-common@bear-craft # shared agents, skills, rules and checklists
- /plugin install bear-hooks@bear-craft # default safety hooks (also: bear-hooks-full, bear-hooks-memory)
- /plugin install bear-docker@bear-craft # infrastructure (also: bear-coolify, bear-kubernetes, bear-opentofu, bear-ansible, bear-hcloud, bear-pgbouncer, bear-frankenphp)
- /plugin install bear-workflow@bear-craft # BMAD sprint workflow (also: bear-team, bear-qa, bear-uiux, bear-gate, bear-project)
- /plugin install bear-react@bear-craft # a stack: bear-react, bear-symfony, bear-flutter, bear-python, …
- ```
- Plugins live in [`marketplaces/<lang>/plugins/`](marketplaces/) — one marketplace per language (`en`, `fr`, `es`, `de`, `pt`; same plugin names, marketplaces `bear-craft`, `bear-craft-fr`, …) — and are generated from the installers (`npm run plugins:generate`). The repository root marketplace is the English one.
- **Pick a single channel for hooks:** the `bear-hooks*` plugins *or* hooks merged into `settings.json` by the CLI — using both runs every
- guard twice ([docs/HOOKS.md](docs/HOOKS.md#shipping-the-hooks-as-plugins)).
- ### Clone + Makefile
- ```bash
- git clone https://github.com/TheBeardedBearSAS/bear-craft.git
- cd bear-craft
- make install-symfony TARGET=~/my-project RULES_LANG=en
- ```
- ### YAML Configuration (Monorepos)
- ```yaml
- # claude-projects.yaml
- projects:
- - name: "my-monorepo"
- root: "~/Projects/my-monorepo"
- lang: "fr"
- modules:
- - path: "frontend"
- tech: react
- - path: "backend"
- tech: symfony
- ```
- ```bash
- make config-install PROJECT=my-monorepo
- ```
- See [Installation Guide](docs/INSTALLATION.md) | [Configuration](docs/CONFIGURATION.md)
- ## Use Bear Craft Without Claude Code
- Bear Craft's principles and rules are available as pre-built bundles for other AI surfaces. No installation required — paste and go.
- | Surface | Bundle | Doc |
- |---------|--------|-----|
- | ChatGPT / GPT-5 | `bundles/chatgpt/bear-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |
- | Claude.ai (Web) / Claude Projects | `bundles/claude/bear-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |
- | Gemini / Cursor / Windsurf | `bundles/gemini/bear-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |
- | Codex CLI / other agents | `bundles/claude/bear-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |
- See [`bundles/README.md`](bundles/README.md) for platform-specific installation instructions and token budgets.
- ### What Gets Installed
- ```
- your-project/.claude/
- CLAUDE.md # Minimal config (~200 tokens, auto-loaded)
- INDEX.md # Quick reference summaries
- references/ # Full documentation (loaded on-demand via @)
- agents/ # AI specialist definitions
- commands/ # Slash commands
- skills/ # Best practices
- checklists/ # Quality gates
- templates/ # Code generation patterns
- hooks/ # Pre/Post tool execution scripts
- mcp/ # MCP server templates
- ```
- Context usage is optimized: ~3,500 tokens always loaded vs ~70,000 if everything were inline (95% reduction).
- ## Documentation
- | Document | Description |
- |----------|-------------|
- | [Quickstart](docs/QUICKSTART.md) | Get results in 10 minutes |
- | [**Tutorial: Complete Workflow**](docs/guides/en/10-complete-workflow.md) | End-to-end narrated walkthrough: idea → backlog → sprint → ship |
- | [**Which path?**](docs/guides/en/11-which-path.md) | Decision page: greenfield, brownfield, bugfix or autonomous sprint |
- | [Learning Paths](docs/LEARNING-PATHS.md) | Beginner → Intermediate → Advanced progression |
- | [Installation](docs/INSTALLATION.md) | All installation methods |
- | [Configuration](docs/CONFIGURATION.md) | Project configuration |
- | [CLI Reference](docs/CLI-REFERENCE.md) | Full CLI documentation |
- | [Commands](docs/COMMANDS.md) | All 82 commands |
- | [Agents](docs/AGENTS.md) | All 31 default agents (+ 39 infra on-demand) |
- | [Skills](docs/SKILLS.md) | Best practices reference |
- | [Technologies](docs/TECHNOLOGIES.md) | Stack-specific guides |
- | [BMAD Guide](docs/BMAD-PRACTICAL-GUIDE.md) | Project management framework |
- | [Hooks](docs/HOOKS.md) | Pre/Post tool execution |
- | [MCP](docs/MCP.md) | Model Context Protocol integration |
- | [Ecosystem](docs/ECOSYSTEM.md) | Curated third-party token/context/review tools |
- | [Privacy Policy](PRIVACY.md) | Data protection and GDPR compliance |
- | [FAQ](docs/FAQ.md) | Common questions |
- | [Troubleshooting](docs/TROUBLESHOOTING.md) | Problem solving |
- | [Migration Guide](docs/MIGRATION.md) | Format migration + version-upgrade index (v3→v8) |
- | [Migration v6→v7](docs/MIGRATION-v7.md) | Upgrade from v6 to v7 |
- | [Migration v7→v8](docs/MIGRATION-v7-to-v8.md) | Upgrade from v7 to v8 |
- | [Agent Teams Guide](docs/AGENT-TEAMS-GUIDE.md) | Multi-agent team orchestration |
- | [Cheat Sheet](docs/CHEAT-SHEET.md) | Quick command reference card |
- | [Skills Publishing](docs/SKILLS-PUBLISHING.md) | Guide for publishing skills |
- | [Compatibility](.claude/COMPATIBILITY.md) | Claude Code version compatibility |
- ### User Guides (Multilingual)
- Step-by-step tutorials available in 5 languages:
- | Guide | EN | FR | ES | DE | PT |
- |-------|----|----|----|----|-----|
- | Getting Started | [EN](docs/guides/en/01-getting-started.md) | [FR](docs/guides/fr/01-getting-started.md) | [ES](docs/guides/es/01-getting-started.md) | [DE](docs/guides/de/01-getting-started.md) | [PT](docs/guides/pt/01-getting-started.md) |
- | Feature Development | [EN](docs/guides/en/03-feature-development.md) | [FR](docs/guides/fr/03-feature-development.md) | [ES](docs/guides/es/03-feature-development.md) | [DE](docs/guides/de/03-feature-development.md) | [PT](docs/guides/pt/03-feature-development.md) |
- | Bug Fixing | [EN](docs/guides/en/04-bug-fixing.md) | [FR](docs/guides/fr/04-bug-fixing.md) | [ES](docs/guides/es/04-bug-fixing.md) | [DE](docs/guides/de/04-bug-fixing.md) | [PT](docs/guides/pt/04-bug-fixing.md) |
- [All guides](docs/guides/index.md) | [Project Creation](docs/guides/en/02-project-creation.md) | [Tools Reference](docs/guides/en/05-tools-reference.md) | [Troubleshooting](docs/guides/en/06-troubleshooting.md) | [Backlog Management](docs/guides/en/07-backlog-management.md)
- ## Project Governance & Sustainability
- Bear Craft is maintained by [The Bearded Bear](https://the-bearded-bear.com), a solo founder with deep involvement in the AFUP and Symfony French ecosystem.
- | Item | Status |
- |------|--------|
- | **Funding model** | Bootstrapped, community-driven — no VC. 100% open-source MIT, sustained by community contributions. |
- | **Maintenance commitment** | Active development since 2026-01. Targeting weekly minor releases, monthly minor versions. |
- | **Bus factor** | Currently 1 (solo maintainer). [Co-maintainer search open](CHARTER.md) — looking for one tech lead from the AFUP / Symfony / Flutter / React community. |
- | **Succession plan** | Documented in [CHARTER.md](CHARTER.md). MIT license guarantees indefinite community fork rights if maintainer disappears. |
- | **Roadmap visibility** | [GitHub Issues](https://github.com/TheBeardedBearSAS/bear-craft/issues) + [CHANGELOG.md](CHANGELOG.md) + recurring `audit/YYYY-MM-DD-*` reports |
- | **Decision process** | RFC via GitHub Discussions for breaking changes. ADRs in `docs/adr/` for architectural choices. |
- | **Security disclosure** | See [SECURITY.md](SECURITY.md). 90-day disclosure timeline, GPG-signed advisories. |
- | **License** | MIT (free, perpetual). Bear Craft is and remains 100% open-source — no commercial, enterprise, or proprietary tier. See [CHARTER.md](CHARTER.md). |
- ## Contributing
- Contributions are welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
- ## License
- This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
- ### Warranty Disclaimer
- THIS SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. See [LICENSE](LICENSE) for full terms.
- ---
- Built for [Claude Code](https://claude.ai/code) by Anthropic. Inspired by Clean Architecture and Domain-Driven Design principles.
Dev/i18n/base/Common/hooks/scripts/guard-network.sh · Bundled script · 58 lines · 1 finding marked
- #!/usr/bin/env bash
- # PreToolUse(Bash) : bloque l'exécution directe d'un script téléchargé.
- # 1. interpréteur nourri par une substitution : bash <(curl …), sh -c "$(curl …)", eval
- Note: Runs a downloaded script through process substitution (bash <(curl …))
- Line 3 on GitHub
- # 2. téléchargement suivi d'un interpréteur dans le même pipeline : curl … | [sudo] sh
- # 3. interpréteur lancé sur un fichier qui vient d'être téléchargé : curl -O …/i.sh && bash i.sh
- # Les commandes ne sont reconnues qu'en position de commande (après sudo/env/VAR=…),
- # donc `2>/dev/null`, `grep -o`, un domaine `.pl` ou un message de commit ne comptent pas.
- # Télécharger un fichier (`curl -o`) reste du ressort des permissions, pas de ce hook.
- set -u
- # shellcheck source=lib/hook-io.sh
- . "$(dirname "${BASH_SOURCE[0]}")/lib/hook-io.sh"
- hook_require_parser
- hook_input
- CMD=$(hook_get tool_input.command)
- [[ -n "$CMD" ]] || exit 0
- # Corps de heredoc retirés, puis un segment par ligne (hook_shell_segments) : le texte
- # cité est une donnée, sauf après sh -c / eval et dans $(…) / `…`. Un segment "|"
- # prolonge le pipeline courant ; un segment "(" est le contenu de la substitution
- # portée (__SUB__) par le dernier segment parent.
- verdict=$(printf '%s\n' "$CMD" | hook_strip_heredocs | hook_shell_segments | awk '
- function base(t) { sub(/[?#].*$/, "", t); sub(/.*\//, "", t); return t }
- function is_interp(c) {
- return c == "." || c ~ /^(sh|bash|zsh|dash|ksh|fish|python[0-9.]*|perl|ruby|node|deno|bun|php|pwsh|source|eval)$/
- }
- {
- sep = substr($0, 1, 1)
- if (sep != "|") piped = 0
- nt = split(substr($0, index($0, "\t") + 1), t); i = 1; pre = 0; first = ""; hassub = 0
- for (j = 1; j <= nt; j++) if (t[j] == "__SUB__") hassub = 1
- while (i <= nt) {
- if (t[i] ~ /^(sudo|doas|env|nohup|command|exec|time|nice|xargs)$/) { pre = 1; i++; continue }
- if (pre && t[i] ~ /^-/) { i++; continue }
- if (t[i] ~ /^[A-Za-z_][A-Za-z0-9_]*=/) { i++; continue }
- if (first == "") first = base(t[i])
- if (base(t[i]) ~ /^(sh|bash|zsh|dash|ksh)$/ && i < nt && t[i + 1] ~ /^-[a-z]*c$/) { i += 2; pre = 0; continue }
- break
- }
- cmd = i <= nt ? base(t[i]) : ""
- if (sep == "(" && subint && (cmd == "curl" || cmd == "wget")) { print "sub"; exit }
- if (hassub) subint = is_interp(first)
- if (cmd == "curl" || cmd == "wget") {
- piped = 1
- for (j = i + 1; j <= nt; j++) if (t[j] !~ /^-/ && base(t[j]) != "") dl[base(t[j])] = 1
- next
- }
- if (!is_interp(cmd)) next
- if (piped) { print "pipe"; exit }
- for (j = i + 1; j <= nt; j++) if (t[j] !~ /^-/) { if (base(t[j]) in dl) { print "file"; exit } break }
- }')
- case "$verdict" in
- sub) hook_block "Feeding a download into an interpreter is not allowed" ;;
- pipe) hook_block "Piping a download into an interpreter is not allowed" ;;
- file) hook_block "Executing a freshly downloaded script is not allowed" ;;
- esac
- exit 0
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.