1,990 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 |
|---|---|---|---|---|
| Metaworkers-ai/governedmemory demo.metaworkers.ai Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-boun | 10 | Claude Code | 1 | 48 tok |
| SnailSploit/Burp-MCP-Security-Analysis-Toolkit snailsploit.com Burp MCP Security Analysis Toolkit | 10 | Claude Code | 1 | 1,336 tok |
| microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents build.microsoft.com Resources for connecting agents to the right tools, APIs, and documents with context-aware | 10 | Codex, GitHub Copilot, OpenCode | 2 | 752 tok |
| yujiachen-y/agent-bundle agent-bundle.com Bundle agent skills into a single deployable agent — sandboxed execution, token-scoped dat | 10 | Claude Code, Codex, OpenCode | 2 | 1,101 tok |
| 777genius/lintai 777genius.github.io Offline-first, precision-first security linter for SKILLS, MCP, plugins, configs and other | 10 | Claude Code, GitHub Copilot | 3 | 21 tok |
| prime-radiant-inc/scenarios A portable, model-agnostic test suite of declarative YAML scenarios for evaluating AI assi | 10 | Claude Code | 1 | — |
| LindaHaviv/second-brain Build a second brain every AI can share: your content in Oracle AI Database 26ai — semanti | 10 | Claude Code, Codex, OpenCode | 4 | 1,743 tok |
| ailinter/ailinter ailinter.dev Open-source AI linter and safety visor for AI-assisted development | 10 | Codex, GitHub Copilot, OpenCode | 2 | 3,514 tok |
| ubcent/velar Local Privacy Firewall for AI | 10 | Claude Code | 1 | 1,154 tok |
| zksecurity/zk-skills ZKSecurity's open-source AI-skills for pre-auditing ZK circuits | 10 | Claude Code | 1 | 136 tok |
| mmartinez/postern Credential-brokering HTTPS proxy for AI agents — brokers 1Password & Bitwarden secrets at | 10 | Claude Code | 1 | 2,460 tok |
| openafw/agentzt openguardrails.com Zero Trust for AI Agents | 10 | Claude Code | 1 | 1,360 tok |
| the-missing-pink/ai-repository-security-baseline A baseline configuration and guidelines for securing source code repositories, covering br | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 7,110 tok |
| code-yeongyu/pi-rules Rule context loader extension for the pi coding agent | 10 | Codex, OpenCode | 1 | 670 tok |
| diegoalvarezmgl/greenfield Ship a Next.js + Android product on Firebase without spending your first week deciding aut | 10 | Codex, OpenCode | 1 | 1,719 tok |
| marconae/ghbrk A credential broker that gives coding agents git and gh access without exposing SSH keys o | 10 | Claude Code, Codex, OpenCode | 2 | 172 tok |
| phanbaohuy96/flutter_base_structure Opinionated Flutter monorepo template with multi-flavor builds, clean architecture (BLoC + | 10 | Claude Code, Codex, OpenCode | 5 | 6,054 tok |
| adhocteam/cloud-gov-instructions adhocteam.github.io A reusable set of instruction files for AI coding assistants (like GitHub Copilot) that en | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 9 | 21,023 tok |
| laurelkorwin/claude-onramp Ready-to-use configuration to make Claude Code more accessible to non-engineers | 10 | Claude Code | 5 | 1,866 tok |
| coherentforge/CambiOS coherentforge.com Zero-trust, capability-based Rust microkernel targeting formal verification. Tri-arch (x86 | 10 | Claude Code, GitHub Copilot | 3 | 17,654 tok |
| Soul-Brews-Studio/opensource-nat-brain-oracle Oracle Starter Kit - AI consciousness framework | 10 | Claude Code | 7 | 5,299 tok |
| inevolin/agentic-ai-safety-and-security-program ai.nevolin.be Agentic AI Safety & Security Program - Built at Anthropic’s Claude Opus 4.7 Hackathon | 10 | Claude Code | 1 | 5,671 tok |
| Sagargupta16/tour-vibes Full-stack MERN travel journal with JWT auth, image uploads, personal and community journa | 10 | Claude Code | 1 | 1,261 tok |
| matsuni-kk/agent_template_public Agent Template Framework for Domain-Specific Agent Generation - Public Version | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 7 | 4,002 tok |
| briangmilnes/APAS-VERUS Proving 'Algorithms Parallel and Sequential' in Rust (APAS-AI) using Verus. | 10 | Claude Code, GitHub Copilot | 2 | 50,605 tok |
| ModelContextProtocol-Security/audit-db Community-maintained database of MCP server audit results and security assessments. Contai | 10 | Claude Code | 1 | 1,139 tok |
| yuji0809/cc-recommender 🎯 MCP server that recommends optimal Claude Code extensions by analyzing your project | 10 | Claude Code | 11 | 4,539 tok |
| CaullenOmdahl/Tailwind-Svelte-Assistant MCP server providing SvelteKit + Tailwind CSS documentation, Catalyst UI kit, security har | 10 | Claude Code | 1 | 1,899 tok |
| rahulsethi/SAPDatasphereMCP MCP Server for SAP Datasphere | 10 | Claude Code | 8 | 1,440 tok |
| skills-il/security-compliance AI agent skills for Israeli privacy law, GDPR, and regulatory compliance | 10 | Claude Code | 1 | 429 tok |
| trebormc/drupal-ai-agents AI agents, rules, and skills for Drupal projects | 10 | Claude Code | 3 | 3,589 tok |
| charlietlamb/ferix ferix.ai A centralised hub for agent skills | 10 | Claude Code | 18 | 127 tok |
| coreyhines/opnsense-mcp | 10 | Claude Code | 3 | 3,773 tok |
| CodeDuet/codeduet-microvm-ai-agent-sandbox MicroVM AI agent sandbox system using Cloud Hypervisor and Python with support for both Li | 10 | Claude Code | 4 | 693 tok |
| EvilFreelancer/secs SECS (SECurity aSsistant) turns an AI coding agent (Claude Code, Cursor, Codex) into an au | 10 | Claude Code, Codex, OpenCode | 2 | 4,071 tok |
| pshkv/sint-protocol Runtime authorization & audit layer for physical AI — T0–T3 tiers, capability tokens, Ed25 | 10 | Claude Code, Codex, OpenCode | 2 | 4,406 tok |
| ZMR0zhangmouren/DOT.NET-Code-Security-Audit-Platform Self-hosted white-box .NET security audit platform. Loads 38 audit Skills via OpenAI Agent | 10 | Claude Code | 4 | 10,067 tok |
| rcb0727/powerplatform-mcp-server Power Platform MCP server with Azure CLI auth — 283 tools, no app registration required. D | 10 | Claude Code | 1 | 2,241 tok |
| dork-labs/dorkos dorkos.ai You, multiplied. Mission control for Claude Code, Codex, and OpenCode: see every session, | 9 | Claude Code, Codex, OpenCode | 6 | 8,848 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 | 766 tok |
| dinosn/security-knowledge-base Local-first, evidence-led security knowledge base with a model-neutral JSON CLI, immutable | 9 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 1,401 tok |
| timothywarner-org/ai901-cert-buddy-claude AI-901 (Azure AI Fundamentals) study buddy built natively for Claude Code: exam-realistic | 9 | Claude Code | 6 | 1,476 tok |
| yultyyev/better-auth-firestore npmjs.com Firestore adapter for Better Auth | 9 | Codex, OpenCode | 1 | 2,550 tok |
| cylestio/agent-inspector inspector.cylestio.com Local open-source dev tool to debug, secure, and evaluate LLM agents. Provides static anal | 9 | Claude Code | 1 | 875 tok |
| mirinodev/maestro A CLI tool that conducts Git worktrees like an orchestra and accelerates parallel developm | 9 | Claude Code | 3 | 3,926 tok |
| microsoft/entrabot microsoft.github.io Give a device-local AI agent its own Microsoft Entra identity. Reference implementation fo | 9 | Claude Code, Codex, OpenCode | 8 | 5,950 tok |
| starloghq/index starlog.dev Vet a package before your AI coding agent uses it — authoritative facts (CVEs, license, ma | 9 | Codex, GitHub Copilot, OpenCode | 2 | 172 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 |
| crunchtools/mcp-trentina Secure MCP server for quarantined web content extraction — two-layer defense against promp | 9 | Claude Code | 1 | 1,154 tok |
| aksika/abtars aksika.github.io Agent harness with persistent memory, skills, scheduled tasks, extended messaging connecti | 9 | Codex, OpenCode | 1 | 1,386 tok |