project-codeguard
Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides compr
What is project-codeguard?
Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides comprehensive security rules that guide AI assistants to generate more secure code automatically.
Overview of project-codeguard
What it is
Project CodeGuard is an open-source, model-agnostic security framework that embeds secure-by-default practices into AI coding agent workflows. It provides comprehensive security rules that guide AI assistants to generate more secure code automatically.
Key features
- AI model-agnostic security coding agent skills framework and ruleset
- Ships core security skills and rules, translators for popular coding agents, and validators to test skills and rule compliance
- Covers essential security domains: cryptography, input validation, authentication, authorization, supply chain, cloud security, platform security, and data protection
- Includes an MCP server that exposes all CodeGuard security rules as tools over streamable HTTP
- Designed to integrate before, during, and after code generation
Use cases
- Before code generation: use skills and rules for product design and spec-driven development to steer models toward secure patterns from the start
- During code generation: help AI agents prevent security issues as code is being written
- After code generation: AI agents like Cursor, GitHub Copilot, Codex, Windsurf, Devin, and Claude Code can use the rules for code review
Getting started
See the repository README for detailed instructions.
License and pricing
The license is not stated in the provided metadata or README. The project is listed as open source.
Based on the project's public README and repository metadata.