{"id":37672528,"url":"https://github.com/thebeardedbearsas/claude-craft","last_synced_at":"2026-07-03T07:00:51.018Z","repository":{"id":327393603,"uuid":"1109103275","full_name":"TheBeardedBearSAS/claude-craft","owner":"TheBeardedBearSAS","description":" Supercharge Claude Code with Expert Knowledge  A comprehensive framework for AI-assisted development. Install standardized rules, agents, and commands for your projects across multiple technology stacks.","archived":false,"fork":false,"pushed_at":"2026-06-24T19:02:35.000Z","size":16826,"stargazers_count":98,"open_issues_count":6,"forks_count":7,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-06-24T21:02:33.090Z","etag":null,"topics":["agents","ai-tools","bmad","claude-code","clean-architecture","ddd","developer-tools","framework","multi-language","tdd"],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TheBeardedBearSAS.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":"docs/ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"docs/AGENTS.md","dco":null,"cla":".github/CLA.md"}},"created_at":"2025-12-03T10:44:37.000Z","updated_at":"2026-06-24T19:00:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"f490bbb7-3d3f-4e57-9636-8fe8d75104e9","html_url":"https://github.com/TheBeardedBearSAS/claude-craft","commit_stats":null,"previous_names":["thebeardedbearsas/claude-craft"],"tags_count":134,"template":false,"template_full_name":null,"purl":"pkg:github/TheBeardedBearSAS/claude-craft","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheBeardedBearSAS%2Fclaude-craft","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheBeardedBearSAS%2Fclaude-craft/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheBeardedBearSAS%2Fclaude-craft/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheBeardedBearSAS%2Fclaude-craft/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TheBeardedBearSAS","download_url":"https://codeload.github.com/TheBeardedBearSAS/claude-craft/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheBeardedBearSAS%2Fclaude-craft/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35075805,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-03T02:00:05.635Z","response_time":110,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai-tools","bmad","claude-code","clean-architecture","ddd","developer-tools","framework","multi-language","tdd"],"created_at":"2026-01-16T12:07:50.180Z","updated_at":"2026-07-03T07:00:50.989Z","avatar_url":"https://github.com/TheBeardedBearSAS.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Claude Craft — Sprint workflow, multi-stack reviewers, and browser QA for Claude Code teams\n\n\u003e **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.**\n\n## Why teams pick Claude Craft\n\nFour things Claude Code + an Anthropic cookbook **won't** give you — they're workflow and orchestration, not prompts:\n\n| Differentiator | What it does |\n|----------------|--------------|\n| 🏆 **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. |\n| 🚀 **BMAD v6 sprint workflow** | Analyze → Plan → Design → Implement → QA, executed by Claude Code directly with quality gates. Quick Flow \u003c 5 min, Standard \u003c 15 min, Enterprise \u003c 30 min. |\n| 🔁 **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. |\n| ⚡ **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. |\n\nPlus **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.\n\n\u003e **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.\n\n\n\n[![npm version](https://img.shields.io/npm/v/@the-bearded-bear/claude-craft)](https://www.npmjs.com/package/@the-bearded-bear/claude-craft)\n[![npm downloads](https://img.shields.io/npm/dm/@the-bearded-bear/claude-craft)](https://www.npmjs.com/package/@the-bearded-bear/claude-craft)\n[![Claude Code 2.1.97+](https://img.shields.io/badge/Claude%20Code-2.1.97%2B-blue)](https://code.claude.com)\n[![CI](https://github.com/TheBeardedBearSAS/claude-craft/actions/workflows/npm-publish.yml/badge.svg)](https://github.com/TheBeardedBearSAS/claude-craft/actions/workflows/npm-publish.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Mutation testing badge](https://img.shields.io/endpoint?style=flat\u0026url=https%3A%2F%2Fbadge-api.stryker-mutator.io%2Fgithub.com%2FTheBeardedBearSAS%2Fclaude-craft%2Fmain)](https://dashboard.stryker-mutator.io/reports/github.com/TheBeardedBearSAS/claude-craft/main)\n\nA comprehensive framework for AI-assisted development with [Claude Code](https://claude.ai/code). Install standardized rules, agents, and commands for your projects across multiple technology stacks — **31 specialized agents (+39 infra agents on-demand), 126 commands across 15 namespaces (220 total), 55 skills**, all token-optimized via `context: fork` and sub-agent model routing.\n\n## What's New in v8.18.0\n\n**Nouvelle commande `/workflow:auto-sprint` (2026-06-27, v8.18.0) :**\n\n- **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 `/team:sprint`).\n- **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`).\n- **5 langues** (`Dev/i18n/{en,fr,es,de,pt}`) ; compteurs réalignés **126 core / 220 total** commandes.\n\n## What's New in v8.17.2\n\n**Revue documentation (2026-06-26, v8.17.2) :**\n\n- **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`.\n- **Fraîcheur** : compteurs et versions réalignés sur le SSOT (125 core / 219 total commandes, 70 agents, 55 skills, 11 stacks ; Claude Code 2.1.97 min / 2.1.193 rec ; Flutter 3.44, RN 0.85, Symfony 8.1). Suppression de `/bmad:init` (→ `/workflow:init`).\n- **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.\n\n## What's New in v8.17.1\n\n**Correctifs tests (2026-06-26, v8.17.1) :**\n\n- **`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`.\n\n**Audit exhaustif multi-agents + mises à jour 2026-06-24 (v8.17.0) :**\n\n- **Versions infra** : Docker 29.6.1, OpenTofu 1.12.2, Ansible 2.21.1, Helm 4.2.2, Node.js 24.x Active LTS.\n- **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).\n- **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 suspendus (directive export-control US, 2026-06-12) — retirés des recommandations.\n- **CLI** : `/goal`, `/usage`, `/workflows` documentés dans CLI-REFERENCE.md.\n- **Optimisation tokens** : `ENABLE_PROMPT_CACHING_1H` et `fallbackModel` activés dans `settings.json` distribué.\n- **Docs** : compteur commandes corrigé (133 → 125 core / 219 total) ; TROUBLESHOOTING, FAQ, CHEAT-SHEET, COMPETITIVE-ANALYSIS enrichis.\n\n**Dépendances et supply chain (v8.16.0 / v8.16.1) :**\n\n- **Trivy action** : `aquasecurity/trivy-action` mis à jour (v8.16.0) — scan CVE supply chain.\n- **Download artifact** : `actions/download-artifact` bumped de 4.2.1 à 8.0.1 (v8.16.0).\n- **CodeQL action** : `github/codeql-action` mis à jour (v8.16.0) — analyse SAST.\n- **Playwright** : `@playwright/test` mis à jour de 1.60.0 à 1.61.0 dans `/website` (v8.16.0).\n- **Patch de stabilité** : correctifs de dernière minute (v8.16.1).\n\n**Refonte du design de l'interface web Kanban (v8.15.0) :**\n\n- **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'`).\n- **Panneau Tweaks** : code couleur des cartes (statut / priorité / TDD / epic), accent et densité, persistés en `localStorage`.\n- **Les 6 vues restylées** (board, backlog, sprints, burndown, deps, docs) ; drag\u0026drop, navigation clavier, `\u003cdialog\u003e` natifs et a11y préservés. Coloration en helpers JS purs testés.\n\n**Interface web Kanban — accès à tous les artefacts BMAD v6 (v8.14.0) :**\n\n- **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`).\n- **Docs élargis** : les corps markdown des EPIC, US, sprint-goal/board/review/retro sont désormais navigables dans le DocsView.\n- **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.\n\n**Corrections de l'interface web Kanban (v8.13.1) :**\n\n- **Dashboard Kanban réparé** : 4 bugs corrigés en TDD sur le SPA Svelte 5 (`claude-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`.\n\n**Fiabilité BMAD + distribution AgentTeams (v8.13.0) :**\n\n- **`/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`).\n- **Scripts AgentTeams livrés** : `Tools/AgentTeams/lib/*.sh` désormais installés automatiquement avec les commandes `/team:*` (fini le warning « scripts MISSING » ; dashboard coût et `--ralph-mode` disponibles out-of-the-box). Install/refresh manuel : `make install-agentteams TARGET=.`.\n\n**Audit exhaustif + durcissement (v8.12.0) :**\n\n- **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.\n- **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).\n- **Optimisation tokens** : templates `settings.json` distribués corrigés (IDs de modèles valides + `CLAUDE_CODE_FORK_SUBAGENT`).\n- **988 Vitest tests** green, mutation testing bloquant sur PRs.\n\n**Kanban BMAD v6 integration (v8.11.0):**\n\n- **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.\n\n**Releases 8.8.x → 8.10.x :**\n\n- **MIT-only strict (v8.8.0)** -- Claude Craft est 100 % open-source MIT, aucune licence commerciale ou enterprise. Stratégie open-core abandonnée.\n- **Parité i18n stricte (v8.8.2)** -- la CI bloque désormais si un fichier traduit est à \u003c 80 % de la taille de l'anglais. Dette i18n résorbée (gap 101 → 0).\n- **Branding the-bearded-bear.com (v8.10.1)** -- migration complète des domaines vers `the-bearded-bear.com`, normalisation de l'organisation GitHub.\n- **126 commandes sur 15 namespaces** (220 total avec infra/projet) -- namespace `/paperclip:*` (8 commandes) ajouté, 55 skills disponibles.\n- **Claude Code 2.1.193** -- version recommandée (Opus 4.8, Artifacts, `claude mcp login`, `/cd`, sous-agents imbriqués, `effort: ultracode`).\n\n\u003e ← Versions antérieures (v8.0 → v8.7) : voir le [CHANGELOG](CHANGELOG.md) et [.claude/COMPATIBILITY.md](.claude/COMPATIBILITY.md).\n\n## Install and First Result\n\n```bash\n# Install to your project (picks your tech stack interactively)\nnpx @the-bearded-bear/claude-craft\n\n# Or install directly\nnpx @the-bearded-bear/claude-craft install ~/my-project --tech=react --lang=en\n\n# Zero-prompt install (auto-detects your stack + locale, target \u003c 2 min)\nnpx @the-bearded-bear/claude-craft install --auto\n\n# Install from a team config URL (Gist or internal endpoint)\nnpx @the-bearded-bear/claude-craft install --from=https://org.example/cc-team.json\n\n# Add a community skill from npm (claude-craft-skill-* convention)\nnpx @the-bearded-bear/claude-craft skill add claude-craft-skill-foo\n\n# Open Claude Code and run your first audit\nclaude\n/team:audit\n```\n\nThat's it. You get an architecture, security, and quality audit of your project in minutes.\n\n**New to Claude Craft?** Run `/common:getting-started` in Claude Code for a 10-minute guided tour that shows you the 3 most valuable commands for YOUR project.\n\n\u003e See [Quickstart](docs/QUICKSTART.md) for a step-by-step walkthrough with expected output at each stage.\n\n## Why Claude Craft?\n\nClaude Code is powerful on its own. Claude Craft makes it **consistent and team-ready**:\n\n- **Standardized rules** -- SOLID, Clean Architecture, TDD enforced across your team, not just suggested\n- **31 default agents + 39 infra agents on-demand** -- reviewers, architects, coaches that know your stack deeply (70 total potentially installable)\n- **126 slash commands across 15 namespaces** -- repeatable workflows for audits, code generation, sprint management\n- **Quality gates** -- automated checks at every stage from PRD to deployment\n- **5 languages** -- English, French, Spanish, German, Portuguese\n\n## Supported Technologies\n\n| Stack | Version | Install Command |\n|-------|---------|-----------------|\n| **Symfony / PHP** | 8.1 / PHP 8.4+ | `--tech=symfony` |\n| **React** | 19.2 + Compiler 1.0 | `--tech=react` |\n| **Flutter / Dart** | 3.44 / Dart 3.12 | `--tech=flutter` |\n| **Python** | 3.14+ / FastAPI | `--tech=python` |\n| **Angular** | 22 | `--tech=angular` |\n| **Vue.js** | 3.5+ (3.6 beta Vapor) | `--tech=vuejs` |\n| **React Native** | 0.85 (New Architecture) | `--tech=reactnative` |\n| **C# / .NET** | 10 LTS / C# 14 | `--tech=csharp` |\n| **Laravel** | 13.x / PHP 8.3+ (8.5 recommandé) | `--tech=laravel` |\n| **PHP** | 8.5 | `--tech=php` |\n| **Paperclip** | 2026.609.0 | `--tech=paperclip` |\n\n| **Docker** | 29.6.1 (CVE-2026-33997) | `--tech=docker` |\n| **Coolify** | v4.1.2 | `--tech=coolify` |\n| **Kubernetes** | 1.36.1 | `--tech=kubernetes` |\n| **OpenTofu** | 1.12.2 | `--tech=opentofu` |\n| **Ansible** | 2.21.1 | `--tech=ansible` |\n| **Hcloud** | 1.61+ | `--tech=hcloud` |\n| **PgBouncer** | 1.25.2 (CVE-2026-6664/6665/6666/6667 patched) | `--tech=pgbouncer` |\n| **FrankenPHP** | 1.12.4 (CVE-2026-45062 patched) | `--tech=frankenphp` |\n\nSee [Technologies](docs/TECHNOLOGIES.md) for full details.\n\n## What's Included\n\n| Category | Count | Examples |\n|----------|-------|---------|\n| **Agents** | 31 default (+ 39 infra on-demand) | `@tdd-coach`, `@api-designer`, `@symfony-reviewer`, `@kubernetes-architect`, `@hcloud-architect` |\n| **Commands** | 126 across 15 namespaces (220 total with infra/project) | `/workflow:init`, `/team:audit`, `/react:generate-component` |\n| **Skills** | 55 | Architecture, testing, security, DDD best practices |\n| **Templates** | 21 | Code generation patterns, BMAD project templates |\n| **Checklists** | 10 | Commit, feature, release quality gates |\n\nSee [Agents](docs/AGENTS.md) | [Commands](docs/COMMANDS.md) | [Skills](docs/SKILLS.md)\n\n## Workflow Tracks\n\nClaude Craft adapts to your project complexity with three development tracks:\n\n| Track | Setup | Phases | Best For |\n|-------|-------|--------|----------|\n| **Quick Flow** | \u003c 5 min | Implementation only | Bug fixes, hotfixes |\n| **Standard** | \u003c 15 min | Plan \u003e Design \u003e Implement | New features, refactoring |\n| **Enterprise** | \u003c 30 min | Analyze \u003e Plan \u003e Design \u003e Implement | Platforms, migrations |\n\n```bash\n/workflow:init              # Auto-detects complexity\n/workflow:init --quick      # Bug fix mode\n/workflow:init --enterprise # Full methodology\n```\n\nSee [BMAD Practical Guide](docs/BMAD-PRACTICAL-GUIDE.md) for the complete project management framework.\n\n## Key Commands\n\nThese are the commands you'll use most:\n\n| Command | What It Does |\n|---------|-------------|\n| `/workflow:init` | Start a development workflow (auto-detects track) |\n| `/team:audit` | Full project audit (architecture, security, quality) |\n| `/common:pre-commit-check` | Validate before committing |\n| `/sprint:next-story` | Get next story ready for development |\n| `/qa:tdd` | Test-Driven Development flow |\n| `/gate:validate-story` | Check story meets Definition of Done |\n| `/{tech}:check-architecture` | Verify architecture compliance |\n| `/{tech}:generate-*` | Generate code following project patterns |\n| `/common:ralph-run \"task\"` | Run Claude in continuous loop until task is done |\n| `/qa:recette` | Automated acceptance testing via Chrome |\n\nSee [CLI Reference](docs/CLI-REFERENCE.md) for all 126 commands across 15 core namespaces (220 total including infra and project management).\n\n## Installation\n\n\u003e **Platform:** Linux and macOS. Windows is not tested and not officially supported.\n\n### NPX (Recommended)\n\n```bash\nnpx @the-bearded-bear/claude-craft install ~/my-project --tech=symfony --lang=en\n```\n\n### Clone + Makefile\n\n```bash\ngit clone https://github.com/TheBeardedBearSAS/claude-craft.git\ncd claude-craft\nmake install-symfony TARGET=~/my-project RULES_LANG=en\n```\n\n### YAML Configuration (Monorepos)\n\n```yaml\n# claude-projects.yaml\nprojects:\n  - name: \"my-monorepo\"\n    root: \"~/Projects/my-monorepo\"\n    lang: \"fr\"\n    modules:\n      - path: \"frontend\"\n        tech: react\n      - path: \"backend\"\n        tech: symfony\n```\n\n```bash\nmake config-install PROJECT=my-monorepo\n```\n\nSee [Installation Guide](docs/INSTALLATION.md) | [Configuration](docs/CONFIGURATION.md)\n\n## Use Claude Craft Without Claude Code\n\nClaude Craft's principles and rules are available as pre-built bundles for other AI surfaces. No installation required — paste and go.\n\n| Surface | Bundle | Doc |\n|---------|--------|-----|\n| ChatGPT / GPT-5 | `bundles/chatgpt/claude-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |\n| Claude.ai (Web) / Claude Projects | `bundles/claude/claude-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |\n| Gemini / Cursor / Windsurf | `bundles/gemini/claude-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |\n| Codex CLI / other agents | `bundles/claude/claude-craft-bundle.md` | [Multi-IDE Guide](docs/guides/MULTI-IDE.md) |\n\nSee [`bundles/README.md`](bundles/README.md) for platform-specific installation instructions and token budgets.\n\n### What Gets Installed\n\n```\nyour-project/.claude/\n  CLAUDE.md           # Minimal config (~200 tokens, auto-loaded)\n  INDEX.md            # Quick reference summaries\n  references/         # Full documentation (loaded on-demand via @)\n  agents/             # AI specialist definitions\n  commands/           # Slash commands\n  skills/             # Best practices\n  checklists/         # Quality gates\n  templates/          # Code generation patterns\n  hooks/              # Pre/Post tool execution scripts\n  mcp/                # MCP server templates\n```\n\nContext usage is optimized: ~3,500 tokens always loaded vs ~70,000 if everything were inline (95% reduction).\n\n## Documentation\n\n| Document | Description |\n|----------|-------------|\n| [Quickstart](docs/QUICKSTART.md) | Get results in 10 minutes |\n| [**Tutorial: Complete Workflow**](docs/guides/en/10-complete-workflow.md) | End-to-end narrated walkthrough: idea → backlog → sprint → ship |\n| [Learning Paths](docs/LEARNING-PATHS.md) | Beginner → Intermediate → Advanced progression |\n| [Installation](docs/INSTALLATION.md) | All installation methods |\n| [Configuration](docs/CONFIGURATION.md) | Project configuration |\n| [CLI Reference](docs/CLI-REFERENCE.md) | Full CLI documentation |\n| [Commands](docs/COMMANDS.md) | All 126 commands |\n| [Agents](docs/AGENTS.md) | All 31 default agents (+ 39 infra on-demand) |\n| [Skills](docs/SKILLS.md) | Best practices reference |\n| [Technologies](docs/TECHNOLOGIES.md) | Stack-specific guides |\n| [BMAD Guide](docs/BMAD-PRACTICAL-GUIDE.md) | Project management framework |\n| [Hooks](docs/HOOKS.md) | Pre/Post tool execution |\n| [MCP](docs/MCP.md) | Model Context Protocol integration |\n| [Ecosystem](docs/ECOSYSTEM.md) | Curated third-party token/context/review tools |\n| [Privacy Policy](PRIVACY.md) | Data protection and GDPR compliance |\n| [FAQ](docs/FAQ.md) | Common questions |\n| [Troubleshooting](docs/TROUBLESHOOTING.md) | Problem solving |\n| [Migration Guide](docs/MIGRATION.md) | Format migration + version-upgrade index (v3→v8) |\n| [Migration v6→v7](docs/MIGRATION-v7.md) | Upgrade from v6 to v7 |\n| [Migration v7→v8](docs/MIGRATION-v7-to-v8.md) | Upgrade from v7 to v8 |\n| [Agent Teams Guide](docs/AGENT-TEAMS-GUIDE.md) | Multi-agent team orchestration |\n| [Cheat Sheet](docs/CHEAT-SHEET.md) | Quick command reference card |\n| [Skills Publishing](docs/SKILLS-PUBLISHING.md) | Guide for publishing skills |\n| [Compatibility](.claude/COMPATIBILITY.md) | Claude Code version compatibility |\n\n### User Guides (Multilingual)\n\nStep-by-step tutorials available in 5 languages:\n\n| Guide | EN | FR | ES | DE | PT |\n|-------|----|----|----|----|-----|\n| 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) |\n| 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) |\n| 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) |\n\n[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)\n\n## Project Governance \u0026 Sustainability\n\nClaude Craft is maintained by [The Bearded CTO](https://the-bearded-bear.com), a solo founder with deep involvement in the AFUP and Symfony French ecosystem.\n\n| Item | Status |\n|------|--------|\n| **Funding model** | Bootstrapped, community-driven — no VC. 100% open-source MIT, sustained by community contributions. |\n| **Maintenance commitment** | Active development since 2026-01. Targeting weekly minor releases, monthly minor versions. |\n| **Bus factor** | Currently 1 (solo maintainer). [Co-maintainer search open](CHARTER.md) — looking for one tech lead from the AFUP / Symfony / Flutter / React community. |\n| **Succession plan** | Documented in [CHARTER.md](CHARTER.md). MIT license guarantees indefinite community fork rights if maintainer disappears. |\n| **Roadmap visibility** | [GitHub Issues](https://github.com/TheBeardedBearSAS/claude-craft/issues) + [CHANGELOG.md](CHANGELOG.md) + recurring `audit/YYYY-MM-DD-*` reports |\n| **Decision process** | RFC via GitHub Discussions for breaking changes. ADRs in `docs/adr/` for architectural choices. |\n| **Security disclosure** | See [SECURITY.md](SECURITY.md). 90-day disclosure timeline, GPG-signed advisories. |\n| **License** | MIT (free, perpetual). Claude Craft is and remains 100% open-source — no commercial, enterprise, or proprietary tier. See [CHARTER.md](CHARTER.md). |\n\n## Contributing\n\nContributions are welcome! Please read our [Contributing Guide](CONTRIBUTING.md).\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n### Warranty Disclaimer\n\nTHIS 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.\n\n---\n\nBuilt for [Claude Code](https://claude.ai/code) by Anthropic. Inspired by Clean Architecture and Domain-Driven Design principles.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthebeardedbearsas%2Fclaude-craft","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthebeardedbearsas%2Fclaude-craft","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthebeardedbearsas%2Fclaude-craft/lists"}