1,485 projects whose own agent configuration covers security. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.
All projects Building agents7,450Claude Code6,586Data and AI3,698Backend and APIs3,488Languages3,402Planning3,191Git and workflow3,129Code review2,728Memory and context2,353Testing2,330DevOps and cloud2,293Research2,288
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| JinNing6/CyberHuaTuo-Plugin AI Agent Error Doctor: paste MCP / LangChain / CrewAI tracebacks, get root cause, exact fi | 3 | Claude Code, Codex, OpenCode | 4 | 156 tok |
| getmcpm/cli npmjs.com MCP security guard + package manager. Block prompt injection, tool poisoning and rug-pulls | 3 | Claude Code | 1 | 46,941 tok |
| cunicopia-dev/gmail-mcp Multi-account Gmail MCP server — unified search/read/draft/labels across N Google accounts | 3 | Claude Code | 1 | 3,556 tok |
| mishoko/solidity-auditor-pulse x.com A benchmark harness that measures how well Claude Code skills perform at smart-contract se | 3 | Claude Code | 1 | 3,752 tok |
| bokiko/KyZN kyzn.dev Autonomous code improvement CLI powered by Claude Code | 3 | Claude Code | 1 | 2,105 tok |
| chtnnh/know-code kc.chtnnhfoundation.org k(no)w-code - your agents dont push until you know exactly whats changed | 3 | Claude Code, Codex, OpenCode | 3 | 362 tok |
| matanryngler/deployshield 🛡️ Production safety guardrails for Claude Code and Gemini CLI. Intercepts and blocks dan | 3 | Claude Code | 1 | 903 tok |
| MuhammedZohaib/patchman Defensive AI security audit skill for Claude and Codex. Reviews codebases and web apps for | 3 | Claude Code, Codex, OpenCode | 2 | 250 tok |
| chris-peterson/ClaudeWatch chris-peterson.github.io bridge.ai/ClaudeWatch: screen dangerous shell commands/scripts | 3 | Claude Code, Codex, OpenCode | 4 | 2,951 tok |
| punt-labs/beadle Claude Code via e-mail based on an addressbook with UNIX style rwx permissions per interac | 3 | Claude Code, Codex, OpenCode | 4 | 2,678 tok |
| Edmonds-Commerce-Limited/claude-code-hooks-daemon Daemon-based hooks system for Claude Code with lazy startup, auto-shutdown, and project-le | 3 | Claude Code | 32 | 12,352 tok |
| Luxvil/ai-coding-rules luxvil.github.io 🤖 Enhance AI coding assistants with battle-tested rules for reliability, predictability, | 3 | Claude Code | 1 | 1,894 tok |
| gw0/docker-claude-code Dockerized Claude Code Sandbox | 3 | Claude Code | 1 | 894 tok |
| combinatrix-ai/agenv nvm / pyenv for AI coding agents | 3 | Claude Code | 5 | 290 tok |
| kristiyan-velkov/ai-security-rules Security rules and best practices for common applications, focused on real-world threats a | 3 | Claude Code, Cursor | 1 | — |
| cloudbees-oss/devops-agent-kit Turn your AI coding assistant into a DevOps-specialized agent using the CloudBees Unify MC | 3 | Claude Code | 2 | 1,522 tok |
| hidetsugu-miya/claude-plugins | 3 | Claude Code, Codex, OpenCode | 6 | 1,318 tok |
| a8cteam51/claude-code-plugins Claude Code plugins by Automattic's Special Projects team for WordPress development, secur | 3 | Claude Code | 1 | 889 tok |
| SecondLifes/delphi-expert An opinionated ecosystem of rules, skills and steerings to elevate Delphi development to s | 3 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 4 | 11,182 tok |
| balasriharsha/shieldbot Shieldbot is an AI-powered security scanner that runs directly inside Claude Code. It comb | 3 | Claude Code | 1 | — |
| an0malous/mcp-custos npmjs.com Secure-coding guardian for AI agents — official CWE/NIST/ASVS guidance in-context, enforce | 3 | Claude Code | 1 | 748 tok |
| sixees/mcp-curl Simple MCP server to execute cURL commands - ideal for Desktop AI Clients (Claude / ChatGP | 3 | Claude Code, GitHub Copilot | 2 | 1,681 tok |
| simonrueba/tripwire Context injection for AI agents, triggered by the codebase itself | 3 | Claude Code | 2 | — |
| Chorozion/Sophia-Stack Self contained mCP web development platform | 3 | Claude Code | 10 | 1,120 tok |
| Suzu-Testing/metasploit-cursor-harness Agentic penetration testing harness bridging Cursor AI agents with Metasploit Framework vi | 3 | Claude Code, Codex, Cursor, OpenCode | 63 | 2,469 tok |
| jmcentire/signet-eval Claude Code policy enforcement hook — deterministic authorization for AI agent tool calls | 3 | Claude Code | 1 | 1,659 tok |
| Nosmoht/talos-mcp-server MCP server for Talos Linux cluster management via the native gRPC API | 3 | Claude Code, Codex, OpenCode | 18 | 9,678 tok |
| nifrajs/nifra nifra.dev Full-stack TypeScript framework built for AI agents: typed server and client with no codeg | 3 | Claude Code, Codex, OpenCode | 2 | 2,352 tok |
| sukoji/loadout npmjs.com 🎯 Loadout — profile your project and gear up Claude Code with the right skills, MCP serve | 3 | Claude Code, Codex, OpenCode | 6 | 791 tok |
| Shad0wMazt3r/The-Scaffolding Solve CTF challenges, find bugs, better accuracy. Plug and play with any agent. | 3 | Claude Code, Codex, OpenCode | 2 | 1,137 tok |
| s977043/river-review river-review.the3396.com Turn reviews into organizational decision assets. Review Judgment as Code for AI-assisted | 3 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 10 | 9,600 tok |
| m0rvayne/mcp-redteam Active red-teaming for MCP servers. Source analysis + live exploitation + auto-fix. Claude | 3 | Claude Code | 1 | 8,266 tok |
| Mearman/agent-permissions Cross-agent permission policy for AI coding agents. MCP sync daemon, CLI, codecs, and eval | 3 | Claude Code, Codex, OpenCode | 2 | 4 tok |
| ASK191225/bugbounty-kit Production bug bounty operations kit — LLM brain, token scanner, HackerOne MCP, RAG pipeli | 3 | Claude Code | 2 | 5,395 tok |
| alphacrack/iac-scanner An agentic AI–powered IaC scanner that evaluates cloud infrastructure against security and | 3 | Claude Code | 1 | 1,699 tok |
| snyk-labs/snyk-vulnbench | 3 | Claude Code, Codex, OpenCode | 12 | 2,521 tok |
| brovar/10x-pentest 10x pentest workflow build on agentic skills | 3 | Claude Code, Codex | 20 | — |
| HermeticOrmus/linux-sysadmin-skills A Claude Code skill bundle for Linux system administration — security, performance, diagno | 3 | Claude Code | 1 | 432 tok |
| Enovatr-Labs/SpecRoute Open source framework for spec-driven agentic software engineering. PRDs, prompts, agents, | 3 | Claude Code, Codex, Gemini CLI, OpenCode | 7 | 3,090 tok |
| MMoMM-org/miyo-kado Where AI meets your vault, on your terms... Obsidian Vault MCP Server | 3 | Claude Code, Codex, OpenCode | 3 | 1,884 tok |
| badchars/steganography-mcp npmjs.com 128-tool MCP server for steganography analysis — LSB detection, chi-square steganalysis, R | 3 | Claude Code | 1 | 422 tok |
| paichart/paichart AI-native service orchestration platform. Discover MCP services by capability, chain multi | 2 | Claude Code | 46 | 8,874 tok |
| Skyrxin/sast-mcp-server | 2 | Claude Code, Gemini CLI | 2 | 3,768 tok |
| barateza/mcp-plesk-dev-docs A unified MCP server that indexes and retrieves Plesk documentation using vector embedding | 2 | Claude Code, Codex, GitHub Copilot | 7 | 2,967 tok |
| matematicsolutions/mcp-saos matematicsolutions.com MCP server for Polish common and Supreme Court case law via the SAOS API - verifiable cita | 2 | Claude Code, Codex, OpenCode | 3 | 1,183 tok |
| psyb0t/docker-pibox ciprian.51k.eu pi-coding-agent inside an aicodebox container. One image, five ways in: interactive shell, | 2 | Claude Code | 1 | — |
| thehesiod/costco-mcp MCP server for Costco warehouse receipts and online orders (multi-account, Azure AD B2C au | 2 | Claude Code | 1 | 2,043 tok |
| AUTHENSOR/AUTHENSOR authensor.com We audit the instruments the AI industry measures itself with — and file every fix upstrea | 2 | Claude Code, Codex, Cursor, OpenCode | 3 | 2,309 tok |
| Pantrist-dev/pantrist-mcp Model Context Protocol server wrapping the Pantrist REST API | 2 | Claude Code | 1 | — |
| KalinYorgov/AI-agent-security-MCP A Model Context Protocol (MCP) server that provides security functionality for AI agents, | 2 | Claude Code | 1 | 593 tok |