1,980 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 agents7,374Claude Code6,573Data and AI3,706Backend and APIs3,486Languages3,398Planning3,181Git and workflow3,100Code review2,701Memory and context2,354Testing2,311Research2,292DevOps and cloud2,282
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| kstenerud/yoloai yoloai.dev Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right | 210 | Claude Code, Codex, OpenCode | 5 | 4,163 tok |
| spire-studio/cloakbot A privacy-first AI agent that sanitizes your prompts locally with a local LLM before forwa | 209 | Claude Code, Codex, OpenCode | 2 | 770 tok |
| akiselev/ghidra-cli Automate Ghidra reverse engineering from the command line — headless analysis, decompilati | 208 | Claude Code, Codex, OpenCode | 4 | 767 tok |
| Garudex-Labs/caracal caracal.run 🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can | 206 | Claude Code, GitHub Copilot | 19 | 4,434 tok |
| sjkim1127/Reversecore_MCP A security-first MCP server that empowers AI agents to perform automated reverse engineeri | 200 | Codex, OpenCode | 1 | 2,563 tok |
| cynative/cynative cynative.com Open-source framework for security agents with live, read-only access to your infrastructu | 197 | Claude Code, Codex, OpenCode | 2 | 5,994 tok |
| Dicklesworthstone/coding_agent_account_manager Sub-100ms auth switching for AI coding CLIs (Claude Code, Codex, Gemini): swap subscriptio | 197 | Codex, OpenCode | 1 | 8,804 tok |
| MCP-Manager/MCP-Checklists mcpmanager.ai | 195 | Claude Code | 1 | 4,505 tok |
| chaitin/OctoBus chaitin.github.io A secure local gateway for AI agents to reliably call approved enterprise APIs, tools, and | 195 | Codex, OpenCode | 1 | 739 tok |
| rileyhilliard/rr Easily sync code to a remote machine and run commands there. That's it. | 195 | Claude Code | 2 | — |
| supermemoryai/install-mcp npmjs.com A simple CLI to install MCP servers into any client - auth included! | 194 | Codex, OpenCode | 1 | 2,867 tok |
| lennney/mcp-slim-guard take-a-deep-breath0.com Context compression for MCP. Same upstream call, exact results recoverable. | 192 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 1,224 tok |
| nizos/probity TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI | 190 | Claude Code | 3 | 396 tok |
| erans/lunaroute LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, Ope | 188 | Claude Code | 1 | — |
| databricks-industry-solutions/security-analysis-tool databricks-industry-solutions.github.io Security Analysis Tool (SAT) analyzes customer's Databricks account and workspace security | 186 | Claude Code, Codex, OpenCode | 3 | 8,442 tok |
| cso1z/claude-ip-guard A Claude Code hook plugin for IP-based access control · Prevents Claude account bans · Cla | 186 | Claude Code | 3 | — |
| freema/openclaw-mcp tomasgrasl.cz 🦞 MCP server for OpenClaw - secure bridge between Claude.ai and your self-hosted OpenClaw | 184 | Claude Code | 1 | 1,001 tok |
| ykdojo/safeclaw The easiest way to run multiple Claude Code sessions, each in its own container, with a da | 183 | Claude Code | 1 | 865 tok |
| Sergei-thinker/vpn-setup Multi-layer VPN (VLESS Reality + Yandex Cloud Relay + WebRTC) for bypassing Russian intern | 182 | Claude Code | 5 | 2,498 tok |
| postrv/narsil-mcp narsilmcp.com Rust MCP server for comprehensive code intelligence - 90 tools, 32 languages, security sca | 181 | Claude Code | 8 | — |
| step-security/dev-machine-guard stepsecurity.io Scan your dev machine for AI agents, MCP servers, IDE extensions, and suspicious packages | 175 | Codex, OpenCode | 1 | 11,328 tok |
| enspirit/elo A purely functional expression language for No-Code tools | 173 | Claude Code | 7 | 1,073 tok |
| QuentinCody/interlinked-cli The harness for your harness. Local hooks, taste enforcement, and developer observability | 171 | Claude Code, Codex, OpenCode | 2 | 22,056 tok |
| sigbit/mcp-auth-proxy MCP Auth Proxy is a secure OAuth 2.1 authentication proxy for Model Context Protocol (MCP) | 170 | Codex, OpenCode | 1 | 528 tok |
| OracleNep/Nday-Exploit-Plan A collection of detailed information and exploitation methods for historical vulnerabiliti | 167 | Codex, OpenCode | 1 | 585 tok |
| derv82/wifit3 Wifite but USB-only & cross-platform. | 163 | Claude Code, Codex, OpenCode | 3 | 1,643 tok |
| safedep/gryph safedep.io Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, | 161 | Claude Code, Codex, OpenCode | 5 | 1,036 tok |
| marchev/claudit MCP server for searching Solodit smart contract security findings | 157 | Claude Code | 1 | — |
| Vortiago/mcp-outline A Model Context Protocol (MCP) server enabling AI assistants to interact with Outline docu | 155 | Claude Code | 4 | 4,623 tok |
| Paresh-Maheshwari/morphe-ai Morphe's AI-powered Android APK patching workspace — multi-agent pipeline for APK analysis | 155 | Codex, Kiro, OpenCode | 14 | 1,643 tok |
| DataDog/pathfinding.cloud pathfinding.cloud An AWS IAM Privilege Escalation Path Library | 152 | Claude Code | 6 | 3,837 tok |
| stephnangue/warden wardengateway.com The secure gateway connecting AI agents to enterprise systems. | 152 | Codex, OpenCode | 1 | 1,063 tok |
| AnastasiyaW/codex-claude-code-config Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and w | 149 | Claude Code, Codex, OpenCode | 2 | 9,949 tok |
| lanbaoshen/mcp-jenkins pypi.org The Model Context Protocol (MCP) is an open-source implementation that bridges Jenkins wit | 148 | Codex, OpenCode | 1 | 856 tok |
| wellwelwel/lagune lagune.ai 🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether yo | 147 | Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode | 5 | 2,636 tok |
| agentfront/frontmcp docs.agentfront.dev TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed co | 146 | Claude Code, Codex, OpenCode | 2 | 6,238 tok |
| KryptosAI/mcp-observatory CI-native security testing for MCP servers. Attack simulation, schema drift detection, and | 146 | Codex, OpenCode | 1 | 524 tok |
| antropos17/Aegis aegisprotect.vercel.app OS-level monitor for AI agents: observes processes, file access, and network activity on t | 145 | Claude Code, Codex, OpenCode | 2 | 4,188 tok |
| padamson/playwright-rust playwright-rust.dev Rust language bindings for Microsoft Playwright | 145 | Claude Code | 5 | 3,446 tok |
| forefy/.context forefy.com AI Agent Skills, Goals and Dynamic Workflows for Security Auditing, Pentesting and Researc | 144 | Claude Code, GitHub Copilot | 2 | 249 tok |
| LF-Decentralized-Trust-labs/gitmesh GitMesh: Policy-as-Code Engine for Open Source AI Agent Orchestration | 143 | Claude Code, Codex, OpenCode | 3 | 1,266 tok |
| shivasurya/code-pathfinder codepathfinder.dev Static Code Analysis for security teams with Inter file taint analysis. Built for finding | 140 | Claude Code | 1 | 3,473 tok |
| TikiTribe/claude-secure-coding-rules Secure Coding Rules for Claude Code with a particular emphasis on AIML projects | 140 | Claude Code | 1 | 2,599 tok |
| ChuprinaDaria/Vibecode-Cleaner-Fartrun Not another AI reviewing AI. Rust-powered code scanner that actually reads your codebase — | 140 | Claude Code | 1 | 113 tok |
| CyberStrategyInstitute/ai-safe2-framework cyberstrategyinstitute.com The Universal Governance, Risk, Compliance (GRC) Operating System with Integrated Security | 139 | Codex, OpenCode | 1 | 1,030 tok |
| mazrean/kessoku Next-generation google/wire with parallel dependency injection for Go | 139 | Claude Code, Codex, OpenCode | 2 | 1,676 tok |
| marmot-protocol/marmot The Marmot Protocol is a messaging protocol that specifies how to do efficient end-to-end | 138 | Claude Code, Codex, OpenCode | 2 | 865 tok |
| glitchedgitz/grroxy grroxy.com A cyber security toolkit blending manual testing with AI Agents | 137 | Claude Code | 1 | 2,932 tok |
| evdenis/cvehound Check linux sources dump for known CVEs. | 137 | Claude Code, Codex, OpenCode | 3 | 3,053 tok |
| trilwu/secskills trilwu.github.io Transform Claude Code into your personal security engineer | 137 | Claude Code | 2 | — |