1,117 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 agents8,341Claude Code6,834Data and AI3,598Backend and APIs3,548Git and workflow3,537Languages3,456Planning3,300Code review2,870Testing2,611DevOps and cloud2,441Writing and docs2,433Memory and context2,375
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| whenpoem/aiscientist An AI-driven research workflow for generating ideas, running experiments, and writing scie | 10 | Claude Code, Codex, OpenCode | 6 | 1,865 tok |
| L-X-T/ng-agentic angulararchitects.io A practical Angular workspace starter with modern best practices, AI-ready tooling, and sc | 10 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 4 | 2,522 tok |
| raunakkathuria/buildwright Approve intent, ship autonomously. Agent-first autonomous development workflow for Claude | 10 | Claude Code, Codex, OpenCode | 2 | 108 tok |
| JairoTorregrosa/jaiskills All my agent skills as one Claude Code plugin: agents checking agents (insistir), verifica | 10 | Claude Code, Codex, OpenCode | 1 | 2,167 tok |
| sunglasses-dev/sunglasses sunglasses.dev Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, i | 10 | Claude Code, Codex, OpenCode | 2 | 1,679 tok |
| erlef-cna/varsel Varsel is the software behind the EEF CNA. | 10 | Claude Code, Codex, OpenCode | 2 | 26,790 tok |
| ukorvl/web-of-flaws A structured library of web security flaws for humans and coding agents with vulnerable ex | 9 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 923 tok |
| Juwon1405/agentic-dart findevil.devpost.com Agentic-DART — autonomous detection & response agent. Architecture-first, not prompt-first | 9 | Claude Code, Codex, OpenCode | 2 | 2,541 tok |
| KumaBase/agent-base | 9 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 7 | 3,029 tok |
| CaseyLabs/kc-secure-repo-template Security-hardened GitHub repository template, designed to prevent supply-chain attacks. In | 9 | Claude Code, Codex, OpenCode | 2 | 1,825 tok |
| chenghit/aws-waf-rules-reviewer An Agent Skill that reviews AWS WAF Web ACL configurations for security issues, misconfigu | 9 | Claude Code, Codex, OpenCode | 2 | 7,124 tok |
| brandondees/code-quality-atlas From-first-principles research toward a standalone agent skill suite for code review & mai | 9 | Claude Code, Codex, OpenCode | 48 | 5,176 tok |
| IvanBBaev/servicenow-mcp-ai ivanbbaev.github.io ServiceNow MCP server — 67 tools over the full REST surface, with plan-and-apply write saf | 9 | Codex, GitHub Copilot, OpenCode | 12 | 6,941 tok |
| MadaBurns/bv-mcp blackveilsecurity.com DNS, email-authentication, TLS and exposure scanning for AI agents: 81 MCP tools, scored 0 | 9 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 20 | 10,311 tok |
| fastrevmd-lab/fwskillsshare mechub.org 31 skills for firewall and network security work — Juniper SRX design, NAT, VPN, and MNHA | 9 | Codex, OpenCode | 1 | 948 tok |
| acartag7/mcp-sso OAuth 2.1 and enterprise SSO for remote MCP servers without API keys in client configs. | 9 | Claude Code, Codex, OpenCode | 4 | 4,794 tok |
| eriknewton/sanctuary-framework sanctuaryprotocol.ai Open source security for AI agents: an OS-enforced egress wall on macOS, and on Ubuntu 24. | 9 | Claude Code, Codex, OpenCode | 2 | 6,599 tok |
| aplaceforallmystuff/mcp-threatintel MCP server for unified threat intelligence - AlienVault OTX, AbuseIPDB, GreyNoise, and abu | 9 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 538 tok |
| inoX-Network/claude-code-safety-guard 3-level override system for Claude Code - prevents destructive system operations. Born fro | 9 | Claude Code, Codex, OpenCode | 2 | 1,224 tok |
| microsoft/github-advisory-mcp MCP tools for semantic search in github/advisory-database | 9 | Codex, OpenCode | 1 | 1,159 tok |
| shuaiqideyu/SecAtlas Structured Chinese web penetration knowledge base: technical cards, topics, case studies, | 9 | Codex, OpenCode | 1 | 1,604 tok |
| SafetyMP/Autonomous-EHS-Management autonomous-ehs-management.vercel.app Self-hosted incident to verified CAPA, with a TRIR that uses annual hours when the month g | 9 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 24 | 2,203 tok |
| nirholas/onchain-agent-wallets nirholas.github.io Give an AI agent a real Solana wallet without giving it your money. The agent gets a spend | 9 | Claude Code, Codex, OpenCode | 2 | 412 tok |
| SamErde/TheCleaners day3bits.com PowerShell module to clean the loose ends from your Windows Servers. | 9 | Codex, GitHub Copilot, OpenCode | 2 | 1,470 tok |
| aplaceforallmystuff/mcp-pihole MCP server for Pi-hole v6 API - control DNS blocking from Claude Code | 8 | Claude Code, Codex, Gemini CLI, OpenCode | 4 | 357 tok |
| creatornader/atrib atrib.dev Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signat | 8 | Claude Code, Codex, OpenCode | 4 | 20,384 tok |
| ChangooLee/mcp-kr-legislation A Model Context Protocol (MCP) server integrating the Korean Ministry of Government Legisl | 8 | Codex, Cursor, OpenCode | 2 | 7,528 tok |
| S3DFX-CYBER/Claude-Skills-Security A production-grade security triage skill for AI agents. | 8 | Codex, OpenCode | 1 | 1,494 tok |
| agentverus/agentverus-scanner agentverus.ai Trust, but verify. Security scanner for AI agent skills. Detects prompt injection, data ex | 8 | Codex, OpenCode | 1 | 2,548 tok |
| berkcangumusisik/repo-seatbelt npmjs.com A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, | 8 | Claude Code, Codex, OpenCode | 2 | 1,503 tok |
| wangdongzuopin/sentinel-skill Sentry, guarding code security. Code auditing, penetration testing, and CTF. | 8 | Codex, OpenCode | 1 | 342 tok |
| vepo/issues Sistema de Gestão de Mudanças | 8 | Claude Code, Codex, Cursor, OpenCode | 25 | 4,153 tok |
| SylphxAI/filesystem-mcp npmjs.com ARCHIVED non-primary. Prefer Citra/Iris/Cue/Prism/Spine/Lookout. | 8 | Codex, OpenCode | 1 | 455 tok |
| nbiish/mcp-calc-tools | 8 | Codex, OpenCode | 1 | 3,864 tok |
| ABMJ/tenable-sc-mcp-server Production-ready MCP server for Tenable Security Center with intelligent caching. 90% toke | 8 | Codex, OpenCode | 1 | 1,269 tok |
| tb0hdan/wass-mcp Web Application Security Scanner MCP Server | 8 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 191 tok |
| snyk/saw-mcp | 8 | Claude Code, Codex, OpenCode | 2 | 1,968 tok |
| actual-software/actual-cli cli.actual.ai Architecture questions, answered from your ADRs. | 8 | 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 | 8 | Claude Code, Codex, OpenCode | 5 | 2,890 tok |
| trueoriginlabs/vibatchium pypi.org Stealth browser automation for AI agents — unattended, headless, N parallel persistent log | 8 | Codex, OpenCode | 1 | 15,899 tok |
| BashaarJavaid/MCP-Sentinel bashaarjavaid.github.io PortunusMCP Sentinel: build-time security scanning for MCP servers. | 8 | Codex, OpenCode | 1 | 2,929 tok |
| purinzan/gx3-cli-mcp zenn.dev Trace a GX Works3 ladder without opening GX Works3 — read-only CLI + MCP server so anyone | 8 | Codex, OpenCode | 1 | 358 tok |
| 0xHoneyJar/loa-freeside Platform layer of the Loa protocol | 8 | Claude Code, Codex, OpenCode | 11 | 5,343 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 | 2,382 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 |
| 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 | 5,060 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 |
| ramboz/jig A Claude Code and Codex plugin that scaffolds AI-native development practices into new pro | 7 | Claude Code, Codex, OpenCode | 8 | 6,940 tok |
| WasmAgent/wasmagent-js wasmagent.github.io Embedded agent runtime compliance layer — WASM sandbox, MCP firewall, capability manifests | 7 | Claude Code, Codex, OpenCode | 2 | 3,963 tok |