By m07o
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
Enable or disable hookify rules interactively
Get help with the hookify plugin
Create hooks to prevent unwanted behaviors from conversation analysis or explicit instructions
List all configured hookify rules
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
عبارة عن proxy بيترجم بين Anthropic Messages API و OpenAI Chat Completions API، عشان تشتغل بـ Claude Code على Groq API وموديلات محلية بدل Anthropic API.
يسمح للمستخدمين باستخدام Claude Code مع:
| موديل Claude | موديل Groq | السرعة | السعر لـ 1M token |
|---|---|---|---|
claude-opus-4 | meta-llama/llama-4-scout-17b-16e-instruct | 594 TPS ⚡ | $0.11 / $0.34 |
claude-3-5-sonnet | llama-3.3-70b-versatile | 394 TPS | $0.59 / $0.79 |
claude-3-5-haiku | llama-3.1-8b-instant | 840 TPS 🚀 | $0.05 / $0.08 |
claude-local-1b | llama3.2:1b (محلي) | ∞ | مجاني |
الأفضل للبرمجة: meta-llama/llama-4-scout - 594 TPS + سعر منخفض 💰
1. استنساخ المستودع
git clone https://github.com/m07o/claude-code.git
cd claude-code
2. تعيين متغيرات البيئة
set GROQ_API_KEY=your_actual_key_here
set LOCAL_MODEL_URL=http://localhost:11434/v1/chat/completions
set LOCAL_MODEL_NAME=llama3.2:1b
3. التشغيل
Start.batnpm run proxy أو node package/proxy.cjsCtrl+Shift+B → "Start Proxy Server"| الملف | الفائدة |
|---|---|
Start.bat | تشغيل المشروع |
Open-Terminal.bat | فتح VS Code |
Open-Dashboard.bat | فتح الداشبورد |
Stop.bat | إيقاف المشروع |
npm run proxy # تشغيل عادي
npm run proxy:debug # مع DEBUG=1
npm run proxy:test # اختبار الاتصال
Ctrl+Shift+BOpen-ClaudeCode/
├── package/
│ ├── proxy.cjs # الـ proxy الرئيسي (Node.js)
│ ├── cli.js # CLI من Anthropic
│ ├── package.json # npm scripts
│ └── ...
├── .vscode/
│ ├── tasks.json # VS Code tasks
│ └── launch.json # Debug configurations
├── Start.bat # تشغيل (Windows)
├── Stop.bat # إيقاف (Windows)
├── Open-Terminal.bat # فتح VS Code
├── Open-Dashboard.bat # فتح الداشبورد
├── README.md # هذا الملف
├── READMEen.md # English docs
└── package.json # (root)
الحل: الـ proxy بيضغط الـ payload تلقائياً (يحذف tools، يقطع system prompt > 28KB).
الحل: تأكد أن الـ proxy شغال:
curl http://localhost:3002/health
الحل: تحقق من اسم الموديل في Ollama:
ollama list
جدِّث LOCAL_MODEL_NAME في proxy.cjs بالاسم الصحيح.
الحل: تحقق من GROQ_API_KEY:
echo %GROQ_API_KEY%
يجب أن يظهر المفتاح (بدون ترك خالي).
الحل: تأكد أن Ollama شغال:
ollama serve
في terminal منفصل.
npm run proxy # تشغيل الـ proxy
npm run proxy:debug # مع DEBUG logging
npm run proxy:test # اختبار الصحة
# Local model
curl -X POST http://localhost:3002/v1/messages \
-H "Content-Type: application/json" \
-d '{"model":"claude-local-1b","max_tokens":50,"messages":[{"role":"user","content":"Hello"}]}'
# Groq API
curl -X POST http://localhost:3002/v1/messages \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-4","max_tokens":50,"messages":[{"role":"user","content":"Hello"}]}'
# Health status
curl http://localhost:3002/health
| الخدمة | العنوان | ملاحظات |
|---|---|---|
| Proxy | http://localhost:3002 | Messages API + Dashboard |
| Groq API | https://api.groq.com | خارجي |
| Ollama | http://localhost:11434 | محلي (اختياري) |
npx claudepluginhub m07o/claude-code --plugin hookifyMigrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.
Frontend design skill for UI/UX implementation
Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Claude Agent SDK Development Plugin
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.