975 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 agents7,410Claude Code6,578Data and AI3,695Backend and APIs3,487Languages3,404Planning3,188Git and workflow3,106Code review2,712Memory and context2,351Testing2,325Research2,289DevOps and cloud2,283
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| eriknewton/sanctuary-framework sanctuaryprotocol.ai Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, key | 8 | Claude Code, Codex, OpenCode | 2 | 5,815 tok |
| bestagentkits/cloud-harness-mcp harness.agentkit.best Remote coding harness exposed as a secure Streamable HTTP MCP server | 8 | Claude Code, Codex, OpenCode | 3 | 1,743 tok |
| nbiish/mcp-calc-tools | 8 | Codex, OpenCode | 1 | 3,864 tok |
| inoX-Network/claude-code-safety-guard 3-level override system for Claude Code - prevents destructive system operations. Born fro | 8 | Claude Code, Codex, OpenCode | 2 | 1,224 tok |
| whshang/herdr-mcp whshang.github.io Stable MCP/OAuth edge for remote web planners to control local Herdr with gated fs/git/exe | 8 | Codex, OpenCode | 1 | 2,352 tok |
| snapsynapse/skill-provenance skillprovenance.dev Version identity and integrity verification for Agent Skills. Tracks versions, detects sta | 7 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 2,306 tok |
| L-X-T/ng-agentic A practical Angular workspace starter with modern best practices, AI-ready tooling, and sc | 7 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 4 | 2,522 tok |
| steve-magne/hookstack hookstack.app Claude Code hooks catalogue — production-ready hooks for Claude Code, OpenAI Codex & GitHu | 7 | Claude Code, Codex, OpenCode | 28 | 9,006 tok |
| ABMJ/tenable-sc-mcp-server Production-ready MCP server for Tenable Security Center with intelligent caching. 90% toke | 7 | Codex, OpenCode | 1 | 1,269 tok |
| taniwhaai/arai arai.taniwha.ai Your AI assistant reads CLAUDE.md and ignores it anyway. Ārai makes instruction files enfo | 7 | Claude Code, Codex, OpenCode | 11 | 4,831 tok |
| tb0hdan/wass-mcp Web Application Security Scanner MCP Server | 7 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 191 tok |
| frootai/frootai frootai.dev From the Roots to the Fruits ! | 7 | Claude Code, Codex, GitHub Copilot, OpenCode | 8 | 9,604 tok |
| Diplomat-ai/diplomat-agent diplomat.run What can your AI agent do to the real world? Scan your code. See which tool calls have zer | 7 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 1,004 tok |
| raunakkathuria/buildwright Approve intent, ship autonomously. Agent-first autonomous development workflow for Claude | 7 | Claude Code, Codex, OpenCode | 2 | 1,579 tok |
| actual-software/actual-cli cli.actual.ai | 7 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 1,269 tok |
| P4ST4S/mcp-audit A transparent Go proxy that intercepts, signs, and audits all MCP tool calls between any c | 7 | Claude Code, Codex, OpenCode | 2 | 2,446 tok |
| aplaceforallmystuff/mcp-threatintel MCP server for unified threat intelligence - AlienVault OTX, AbuseIPDB, GreyNoise, and abu | 7 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 538 tok |
| night4me/pfsense-mcp-server night4me.github.io A security-first MCP server for pfSense — READ-only today by design; WRITE is staged behin | 7 | Codex, OpenCode | 1 | 2,371 tok |
| shenjingnan/haimen Enter through this door, exit through that door. | 7 | Claude Code, Codex, OpenCode | 7 | 2,038 tok |
| erlef-cna/varsel Varsel is the software behind the EEF CNA. | 7 | Claude Code, Codex, OpenCode | 2 | 22,996 tok |
| ramboz/jig A Claude Code and Codex plugin that scaffolds AI-native development practices into new pro | 6 | Claude Code, Codex, OpenCode | 8 | 6,703 tok |
| ArmisSecurity/armis-appsec-mcp AI-powered security scanning MCP plugin for Claude Code | 6 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 6,233 tok |
| suyogpawar88/Threat-Model suyogpawar88.github.io | 6 | Claude Code, Codex, OpenCode | 1 | 1,275 tok |
| FavioVazquez/mollify Deterministic codebase intelligence for Python | 6 | Claude Code, Codex, Cursor, Gemini CLI, OpenCode | 24 | 4,352 tok |
| mtnyilmaz/agents | 6 | Claude Code, Codex, OpenCode | 57 | 2,391 tok |
| morooka-akira/aicm | 6 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 10 | 9,770 tok |
| PoulpYBifle/NCF-Coding-Best-Practices | 6 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 7,859 tok |
| Contoso-State/red-team-agent-orchestration | 6 | Claude Code, Codex, OpenCode | 47 | 2,697 tok |
| nerviq/nerviq nerviq.net Your agent docs lie. Nerviq finds the lies in 30 seconds — stale references, permission ex | 6 | Claude Code, Codex, OpenCode | 15 | 2,959 tok |
| egarcia74/warp-sql-server-mcp egarcia74.github.io 🗄️ Model Context Protocol (MCP) server for SQL Server integration with Warp terminal. Exe | 6 | Codex, GitHub Copilot, OpenCode | 3 | 1,575 tok |
| RenatoMignone/From-LLMs-to-Secure-Agents renatomignone.github.io A visual, source-grounded guide from agent architecture to secure agentic AI systems. | 6 | Codex, OpenCode | 1 | 503 tok |
| omkhar/vulnerability-validation-skill | 6 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 5 | 3,231 tok |
| fonsecafns/sentinela Um auditor de segurança que vive dentro do seu agente de IA. Varre o projeto inteiro, usa | 6 | Codex, Gemini CLI, OpenCode | 2 | 17,496 tok |
| lucaspressi/claudekit-engineer | 6 | Claude Code, Codex, Gemini CLI, OpenCode | 10 | 2,006 tok |
| mrgnhnt96/sip A command-line tool to manage Dart mono-repos. | 5 | Claude Code, Codex, OpenCode | 7 | 2,533 tok |
| pleasedodisturb/llm-safe-haven One-liner for AI solo developers to fasten the security bolts on their systems | 5 | Claude Code, Codex, OpenCode | 2 | 2,287 tok |
| jlevy/supply-chain-hardening Supply-chain payloads run at install, import, or repo-open time. Copy-pasteable hardening | 5 | Claude Code, Codex, OpenCode | 6 | 1,947 tok |
| jmagar/swag-mcp SWAG reverse proxy configuration management via MCP. Create, edit, view, and manage nginx | 5 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 2,374 tok |
| olanokhin/agent-security-skill Native Claude Code + Codex skills for AI security review. Also ships instruction files for | 5 | Codex, OpenCode | 1 | 140 tok |
| yunsii/wezdeck A flight deck for your AI agents — multi-agent terminal platform built on WezTerm + tmux + | 5 | Claude Code, Codex, OpenCode | 4 | 4,379 tok |
| Sandeeprdy1729/timps timps-website.vercel.app The AI memory layer with 17 intelligence tools — catches contradictions, predicts burnout, | 5 | Claude Code, Codex, OpenCode | 2 | 24,407 tok |
| xChechi/xche-ai-app-security-pack stefannasev.dev Free security guardrails for apps built with AI coding tools (Claude Code, Cursor, Lovable | 5 | Claude Code, Codex, OpenCode | 2 | 1,527 tok |
| TyrusRC/praetor Agentic pentest & red-team harness via Burp Suite MCP toolkit | 5 | Claude Code, Codex, OpenCode | 2 | 8,151 tok |
| danygiguere/audit-skills Language- and framework-agnostic audit checklists for AI coding agents — security, correct | 5 | Claude Code, Codex, OpenCode | 2 | 2,553 tok |
| TheSethRose/Vulnerability-Scanning sethrose.dev Local-first vulnerability and supply-chain scanning for agent runtimes. | 5 | Codex, OpenCode | 1 | 978 tok |
| zebbern/pocmap zebbern.github.io MCP-native CVE, PoC & exploit discovery toolkit (Metasploit, Nuclei, GitHub & more) | 5 | Claude Code, Codex, OpenCode | 2 | 4,679 tok |
| jiezeng2004-design/PatchWarden patchwarden-showcase-redesign.yistart.chatgpt.site Turn your ChatGPT conversations into safe, auditable local execution. PatchWarden lets you | 5 | Codex, OpenCode | 1 | 539 tok |
| HanZephyr/AI-Data-Access-Gateway An open-source secure data access gateway for AI agents. It provides database safety acces | 5 | Codex, OpenCode | 1 | 372 tok |
| zessu/samson-ai Your personal fitness trainer. Get fitness recommendations daily through email/SMS | 5 | Codex, OpenCode | 1 | 1,449 tok |
| Nikita3005/taintgate Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK | 5 | Codex, OpenCode | 1 | 259 tok |