Claude Secure Coding Rules

Claude Secure Coding Rules

**Open-source security rules that guide Claude Code to generate secure code by default.**

[](https://opensource.org/licenses/MIT) [](docs/CONTRIBUTING.md)

Overview

This repository provides comprehensive security rules for Claude Code, covering web applications, AI/ML systems, and agentic AI. When you include these rules in your project, Claude Code will automatically apply security best practices, refuse to generate vulnerable code patterns, and suggest secure alternatives.

Key Features

• OWASP Top 10 2025 - Complete coverage of modern web security risks
• OWASP MCP Top 10 2025 - Model Context Protocol security for AI assistants and tools
• AI/ML Security - Rules for machine learning systems using NIST AI RMF, MITRE ATLAS, and Google SAIF
• Agentic AI Security - Specialized rules for autonomous AI systems with tool use
• 100+ Rule Sets - Covering 12 languages, 5 backend frameworks, 11 AI/ML frameworks, 5 frontend frameworks, 51 RAG tools, IaC (Terraform/Pulumi), containers (Docker/K8s/Helm), and CI/CD (GitHub Actions/GitLab CI)
• Enforcement Levels - Strict, warning, and advisory modes for different risk levels

Quick Start

1. Clone the Repository

git clone https://github.com/yourusername/claude-secure-coding-rules.git
cd claude-secure-coding-rules

2. Copy Rules to Your Project

**Option A: Copy specific rules you need**

# Core rules (recommended for all projects)
cp rules/_core/*.md /path/to/your/project/.claude/

# Language-specific (e.g., Python)
cp rules/languages/python/CLAUDE.md /path/to/your/project/

# Framework-specific (e.g., FastAPI)
cp rules/backend/fastapi/CLAUDE.md /path/to/your/project/backend/

# RAG-specific (e.g., LlamaIndex + Pinecone)
cp -r rules/rag/_core /path/to/your/project/.claude/rag-core/
cp rules/rag/o