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 |
|---|---|---|---|---|
| mindcockpit-ai/cognitive-core multivac42.ai A vendor-agnostic, biomimetic skill framework for AI agents | 11 | Claude Code | 38 | 1,377 tok |
| baseballyama/eslint-plugin-postgresql baseballyama.github.io An ESLint plugin for PostgreSQL files. Enforces best practices for SQL style, performance, | 11 | Claude Code | 1 | 3,374 tok |
| iselegant/cchb Fast TUI tool to browse, search, and resume your Claude Code session history | 11 | Claude Code | 8 | 709 tok |
| akasecurity/claude-tools akasecurity.io The clean slate a fresh Claude Code should start from — clean context, locked credentials, | 11 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 793 tok |
| taoq-ai/ziran taoq-ai.github.io ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous t | 11 | Claude Code | 1 | 4,939 tok |
| ailinter/ailinter ailinter.dev Open-source AI linter and safety visor for AI-assisted development | 11 | Codex, GitHub Copilot, OpenCode | 2 | 3,514 tok |
| ubcent/velar Local Privacy Firewall for AI | 11 | Claude Code | 1 | 1,154 tok |
| mmartinez/postern Credential-brokering HTTPS proxy for AI agents — brokers 1Password & Bitwarden secrets at | 11 | Claude Code | 2 | 2,726 tok |
| openafw/agentzt openguardrails.com Zero Trust for AI Agents | 11 | Claude Code | 1 | 1,360 tok |
| LayZeeDK/angular-typechecker A type-checker (no build/emit) for Angular projects, including libraries. Perfect for Agen | 11 | Claude Code, Codex, OpenCode | 5 | 16,893 tok |
| marconae/ghbrk A credential broker that gives coding agents git and gh access without exposing SSH keys o | 11 | Claude Code, Codex, OpenCode | 2 | 172 tok |
| AAAAAln1/XiangXiong An experimental cognitive runtime for exploring object-centered autonomous agents. | 11 | Claude Code | 2 | 3,569 tok |
| CaullenOmdahl/Tailwind-Svelte-Assistant MCP server providing SvelteKit + Tailwind CSS documentation, Catalyst UI kit, security har | 11 | Claude Code | 1 | 1,899 tok |
| rahulsethi/SAPDatasphereMCP MCP Server for SAP Datasphere | 11 | Claude Code | 8 | 1,440 tok |
| trebormc/drupal-ai-agents AI agents, rules, and skills for Drupal projects | 11 | Claude Code | 3 | 3,589 tok |
| coreyhines/opnsense-mcp | 11 | Claude Code | 3 | 3,773 tok |
| EvilFreelancer/secs SECS (SECurity aSsistant) turns an AI coding agent (Claude Code, Cursor, Codex) into an au | 11 | Claude Code, Codex, OpenCode | 2 | 4,071 tok |
| crunchtools/mcp-trentina MCP gateway between AI agents and their tools, the web and Matrix: three-layer prompt-inje | 11 | Claude Code | 2 | 10,610 tok |
| pshkv/sint-protocol Runtime authorization & audit layer for physical AI — T0–T3 tiers, capability tokens, Ed25 | 11 | Claude Code, Codex, OpenCode | 2 | 4,406 tok |
| shrec/AIWorkHub shrec.github.io Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP | 11 | Claude Code, Codex, GitHub Copilot, OpenCode | 6 | 5,009 tok |
| night4me/pfsense-mcp-server night4me.github.io A security-first MCP server for pfSense — READ-only today by design; WRITE is staged behin | 11 | Codex, OpenCode | 1 | 2,371 tok |
| FavioVazquez/mollify Deterministic codebase intelligence for Python | 11 | Claude Code, Codex, Cursor, Gemini CLI, OpenCode | 40 | 4,352 tok |
| Community-VyProjects/VyMCP MCP server for VyOS routers, powered by VyManager — lets AI agents read and manage routers | 11 | GitHub Copilot | 1 | 479 tok |
| agentic-threat-modeling/MAESTRO agentic-threat-modeling.github.io OWASP MAESTRO Threat Modeling Playbook | 11 | Claude Code | 1 | 4,581 tok |
| elfa-ai/skills Agent skill for the Elfa AI | 11 | Claude Code, Codex, OpenCode | 2 | 359 tok |
| on1659/memradar memradar.vercel.app Stories told by your AI conversations — Fun retrospective viewer for AI coding assistant c | 11 | Claude Code | 8 | 786 tok |
| kaltinril/Kernsmith Cross-platform .NET library + CLI tool for generating bitmap fonts for games from TTF/OTF/ | 11 | Claude Code | 23 | 1,974 tok |
| tse-wei-chen/hs-sql-agent sql-agent.net .NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded | 10 | Codex, OpenCode | 1 | 825 tok |
| Huan-zhaojun/mcp-safe-proxy npmjs.com Lightweight MCP annotation proxy — intercepts tools/list responses and rewrites tool annot | 10 | Claude Code | 1 | 833 tok |
| tomDeprez/-CyberPentest-Plugin-Claude-Code Plugin de pentest offensif intégré à Claude Code. Lance nmap, sqlmap, nuclei, gobuster et | 10 | Claude Code | 3 | 406 tok |
| lulaide/fofa-mcp npmjs.com An MCP (Model Context Protocol) tool server for the FOFA search engine, enabling AI assist | 10 | Claude Code | 1 | 854 tok |
| wei/mymlh-mcp-server mymlh-mcp.git.ci Model Context Protocol Server for MyMLH API v4 | 10 | Codex, OpenCode | 1 | 1,899 tok |
| secretgate/secretgate pypi.org Security proxy for AI coding agents — intercepts outbound traffic and redacts secrets befo | 10 | Claude Code | 1 | 1,850 tok |
| pranee54/AgentDoctor npmjs.com Codebase intelligence, repository analysis, safety controls, and MCP tools for developers | 10 | Cursor | 4 | — |
| muzafferkadir/nextjs-loop-engineering-starter A Next.js starter showing how to run Claude Code / Codex in safe, verified loops — plan → | 10 | Claude Code, Codex, OpenCode | 4 | 1,479 tok |
| crypdick/pynchy pynchy.ricardodecal.com OpenClaw alternative with strict container isolation for security measures. Connects to Wh | 10 | Claude Code, Codex, OpenCode | 4 | 1,021 tok |
| ChainAware/behavioral-prediction-mcp chainaware.ai AI-powered tools to analyze wallet behaviour prediction,fraud detection and rug pull predi | 10 | Claude Code, Codex, OpenCode | 2 | 13,695 tok |
| teehooai/spidershield spidershield.dev Scan, rate, and harden MCP servers for AI agent safety | 10 | Claude Code, Codex, OpenCode | 2 | 2,869 tok |
| Pro-GenAI/Agent-Action-Guard action-guard.github.io 🛡️ Safe AI Agents through Action Classifier | 10 | Codex, OpenCode | 1 | 6,592 tok |
| 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 |
| 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 | — |
| 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 |
| diegoalvarezmgl/greenfield Ship a Next.js + Android product on Firebase without spending your first week deciding aut | 10 | Codex, OpenCode | 1 | 1,719 tok |
| phanbaohuy96/flutter_base_structure Opinionated Flutter monorepo template with multi-flavor builds, clean architecture (BLoC + | 10 | Claude Code, Codex, OpenCode | 5 | 5,225 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 | 21,131 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 | 19,946 tok |