Claude 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 Claude 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) | /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 | /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 Claude 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.
A comprehensive framework for AI-assisted development with Claude Code. Install standardized rules, agents, and commands for your projects across multiple technology stacks — 33 specialized agents (+39 infra agents on-demand), 143 commands across 18 namespaces, 55 skills, all token-optimized via context: fork and sub-agent model routing.
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.
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.
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 /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.
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 /tauri:check <axe> dans les 5 langues. Détails : CHANGELOG.
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 /rust:check <axe>. Détails : CHANGELOG.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
