2,139 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 |
|---|---|---|---|---|
| ruaan-deysel/unraid-management-agent Go-based Unraid plugin monitor and control your Unraid system via REST API, WebSocket, MCP | 65 | Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode | 20 | 10,246 tok |
| lirantal/agent-rules Rules and instructions for agentic coding tools like Cursor, Claude CLI, Gemini CLI, Qodo, | 65 | Codex, GitHub Copilot, Gemini CLI, OpenCode | 8 | 8,139 tok |
| pensar-x/argus-validation-benchmarks Self-contained, Dockerized offensive security challenges for evaluating AI-powered penetra | 64 | Claude Code | 1 | 8,584 tok |
| rfunix/tengu AI-powered penetration testing MCP server | 64 | Claude Code | 1 | 6,055 tok |
| pabpereza/kali-mcp AI Agent implementation to automate ethical hacking tasks. Use it with responsibility. | 63 | Claude Code, Codex, OpenCode | 8 | 3,420 tok |
| QWED-AI/qwed-verification docs.qwedai.tech Open-source AI verification infrastructure for deterministic verification of LLM outputs, | 63 | GitHub Copilot | 1 | 155 tok |
| frendysanusi/claude-pentest-skills AI-powered web application penetration testing skills with Claude Code | 63 | Claude Code | 1 | 2,118 tok |
| solanabr/auditor-skill auditor-attest.vercel.app Claude Code / agentic security skill for Solana programs and software. Full audit-firm lif | 62 | Claude Code, Codex, OpenCode | 1 | 1,608 tok |
| runbear-io/beardrive Google Drive for AI agents — share files with your team, share context across your agents. | 61 | Claude Code | 12 | 10,897 tok |
| luminarylane/fal-mcp-server luminarylane.github.io MCP server for Fal.ai - Generate images, videos, music and audio with Claude | 61 | Claude Code | 5 | 993 tok |
| badchars/osint-mcp-server OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Ce | 61 | Claude Code | 1 | 1,238 tok |
| ykdojo/cc-safe Security scanner for Claude Code settings files. Scans for dangerous patterns in your appr | 61 | Claude Code | 1 | 74 tok |
| clidey/deptrust deptrust is a CLI that checks package versions for known vulnerabilities across npm, PyPI, | 61 | Claude Code, Codex, OpenCode | 3 | 1,309 tok |
| arcaputo3/mcp-server-whisper An MCP Server for audio transcription using OpenAI | 60 | Claude Code | 1 | 432 tok |
| Eljaja/BibaVPN DPI-resistant SOCKS5/HTTP tunnel over TLS+WebSocket for self-hosted single-VPS setups | 60 | Codex, OpenCode | 1 | 10,424 tok |
| Mindburn-Labs/helm-ai-kernel helm.docs.mindburn.org Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatibl | 60 | Claude Code, Codex, OpenCode | 2 | 1,666 tok |
| greenpau/go-authcrunch authcrunch.com AuthCrunch provides Authentication, Authorization, and Accounting (AAA) Security Functions | 60 | Codex, OpenCode | 45 | 992 tok |
| CarbeneAI/Talon Penetration Testing MCP for Claude Code. AI-assisted security testing with automated recon | 59 | Claude Code | 1 | 479 tok |
| cai-layer/cai getcai.app Press ⌥C on anything. Transform with AI, scripts, and shortcuts on any selection. 100% loc | 59 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 6,135 tok |
| mastepanoski/claude-skills UX/UI evaluation, AI governance, and AI security skills for AI coding assistants. Audit in | 59 | Claude Code | 1 | 1,866 tok |
| spacehendrix/clauder > CLAUDER - a safer and supercharged Claude Code | 58 | Claude Code | 22 | — |
| enkryptai/secure-mcp-gateway enkryptai.com Secure MCP Gateway - Setup Admin level gateway functionality for MCP servers - with guardr | 58 | Claude Code | 1 | 13,326 tok |
| navikt/copilot ki-utvikling.nav.no All things Copilot, Agents, MCPs, Skills, and coding related AI features for the Norwegian | 58 | Codex, GitHub Copilot, OpenCode | 6 | 5,654 tok |
| ByamB4/find-cve-agent CVE hunting harness for Claude Code - 20 skills, 5-agent team, systematic vulnerability re | 58 | Claude Code | 1 | 3,971 tok |
| defuse/auditician-temp Automated security audits with Claude Code | 57 | Claude Code | 13 | — |
| SquidSec/SquidC5 squidoffense.com Security-first AI-native C5 teamserver (Command · Control · Cognitive · Collaborative · Co | 57 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 5,922 tok |
| delphicleancode/delphi-spec-kit inovefast.com.br An opinionated ecosystem of rules, skills, and steerings to elevate Delphi development to | 57 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 9,608 tok |
| Pantani/tdmcp pantani.github.io TouchDesigner MCP server, describe a visual to Claude, Cursor or Codex and it builds a rea | 57 | Claude Code, Codex, OpenCode | 3 | 7,962 tok |
| longzhi/clawhive Lightweight, Rust-native AI Agent platform. Security sandbox from day one. | 56 | Claude Code, Codex, OpenCode | 2 | 3,177 tok |
| CuriousLearnerDev/Online_Tools-AI An AI Agent platform for web-based desktop security testing, integrating reconnaissance, a | 56 | Claude Code | 1 | 344 tok |
| RedHatProductSecurity/prodsec-skills Security skills for AI coding assistants and agentic systems | 56 | Codex, OpenCode | 1 | 1,360 tok |
| sayanarijit/cottage cottage-cli.pages.dev A modern git based age-encrypted secrets manager for teams. | 56 | Claude Code | 4 | — |
| Nextron-Labs/surface-watch surface-watch monitors the authorized external attack surface of an organization over time | 55 | Codex, OpenCode | 1 | 3,196 tok |
| SkeneTechnologies/skene-cookbook 700+ AI skills for Claude and Cursor — PLG, marketing, security, DevEx, and more. One comm | 55 | Codex, Cursor, OpenCode | 2 | 3,860 tok |
| tutur3u/platform tuturuuu.com Tuturuuu is an AI-native, open-source workspace that unifies tasks, scheduling, and team c | 55 | Claude Code, Codex, Gemini CLI, OpenCode | 61 | 5,327 tok |
| CDSecurity/cdsecurity-skills Claude Code skills for smart contract security — by CD Security | 55 | Claude Code | 1 | 322 tok |
| OWASP/Agent-Security-Regression-Harness owasp.community Executable security regression testing for agentic applications and MCP-integrated systems | 55 | Codex, OpenCode | 1 | 927 tok |
| kubeflow/mcp-server MCP Server for AI-Assisted Development with Kubeflow Tools | 55 | Codex, GitHub Copilot, OpenCode | 2 | 2,807 tok |
| microsoft/azure-devops-skills Sample skills and prompt patterns demonstrating how to use the Azure DevOps MCP Server wit | 55 | Claude Code, Codex | 7 | — |
| SumonMSelim/agentguard Universal security guardrails and workflow policies for AI coding agents. | 54 | Claude Code | 1 | 4,774 tok |
| prowler-cloud/prowler-studio Prowler Studio an AI workflow that ensures Claude Code follows Prowler's guardrails to del | 54 | Codex, OpenCode | 1 | 6,255 tok |
| wangbooth/Claude-Code-Guardrails Protective hooks for Claude Code that prevent accidental code loss through branch protecti | 54 | Claude Code | 6 | 1,171 tok |
| cybozu/prompt-hardener Prompt Hardener analyzes prompt-injection-originated risk in LLM-based agents and applicat | 54 | Claude Code, Codex, OpenCode | 3 | 1,192 tok |
| wbrown/janus-datalog An embeddable Datalog database that is Datomic-inspired written in Golang | 54 | Claude Code | 6 | 21,474 tok |
| gl0bal01/malware-analysis-claude-skills gl0bal01.com Complete Claude skills toolkit for professional malware analysis. 5 specialized skills cov | 54 | Claude Code | 1 | 1,697 tok |
| QuantumClaw/QClaw Open-source AI agent runtime with a knowledge graph for a brain. Runs anywhere. | 53 | Codex, OpenCode | 1 | 595 tok |
| caspel26/django-ninja-aio-crud django-ninja-aio.com Async dynamic CRUD framework for Django Ninja — built-in auth, filtering, pagination, auto | 53 | Claude Code | 1 | 3,591 tok |
| aws-samples/sample-agent-skills-for-builders A curated collection of ready-to-use agent skills covering AWS development, security scann | 53 | Claude Code, Codex, OpenCode | 2 | 1,303 tok |
| benchjack/benchjack AI agent benchmark hackability scanner — find evaluation vulnerabilities before they under | 53 | Claude Code | 2 | 614 tok |
| brandhaug/b2b-saas-starter b2b-saas-starter-web.brandhaug.workers.dev Cloudflare-first B2B SaaS monorepo starter. TanStack Start, Effect v4, Drizzle on D1, Bett | 53 | Claude Code, Codex, OpenCode | 2 | 1,237 tok |