3,323 projects whose own agent configuration covers planning. 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 agents8,487Claude Code6,881Git and workflow3,602Data and AI3,582Backend and APIs3,555Languages3,486Code review2,891Testing2,679Writing and docs2,477DevOps and cloud2,477Memory and context2,375Research2,318
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| CGSOG-JumpStarts/JumpStart-AutoNav Design thinking agentic engineering framework | 10 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode, Windsurf | 58 | 8,614 tok |
| soulcodex/agentic agentic.soulcodex.link Vendor-agnostic AI agent configs with production-minded architecture. Compose once, deploy | 10 | Codex, OpenCode | 1 | 1,585 tok |
| lensapp/lens-sandbox lns.run Run AI agents, commands, and OCI images locally inside a microVM — control what flows into | 10 | Claude Code, Codex, OpenCode | 9 | 9,272 tok |
| richardblythman/org.md An open format specification for organizational operating systems. Defines the ORG.md stan | 10 | Claude Code | 1 | — |
| BaseInfinity/codex-sdlc-wizard SDLC Wizard adapter for OpenAI Codex CLI. Plan is certified, implementation needed. PRs we | 10 | Claude Code, Codex, OpenCode | 2 | 614 tok |
| eddacraft/anvil-plan-spec Lightweight spec for planning and task authorisation in AI-assisted development. | 10 | Claude Code, Codex, OpenCode | 6 | 1,075 tok |
| AragornZJF/goal-loop Delivery coding skills from clarifying requirements and planning to automated implementati | 10 | Claude Code | 1 | — |
| shrwnsan/clix-dev-flow A simple Gemini CLI extension that brings AI development workflow patterns to your termina | 10 | Codex, Gemini CLI, OpenCode | 2 | 2,317 tok |
| improving/Intro-to-AI-for-Dev-Workshop Contains materials for the Intro to AI for Developers workshop | 10 | Claude Code, Codex, OpenCode | 5 | — |
| companion-inc/introspect Agent self-improvement runtime for Codex, Claude, and OpenCode | 10 | Claude Code, Codex, OpenCode | 2 | 5,753 tok |
| jmsktm/claude-settings | 10 | Claude Code | 1 | 3,981 tok |
| brian-lai/PARA-Programming | 10 | Claude Code, Codex, OpenCode | 2 | 5,540 tok |
| lgqyhm2010/loop-goal Discipline skill for long-running agent tasks — recurring loops and run-until-done goals: | 10 | Codex, GitHub Copilot, OpenCode | 2 | 620 tok |
| rootsli/claude-quickstart-cn A beginner configuration kit for the Chinese version of Claude, including global, project- | 10 | Claude Code | 6 | 860 tok |
| SylvainChabaud/spec-to-code-factory Pipeline automatisé Spec-to-Code pour Claude Code. Transforme un requirements.md en projet | 10 | Claude Code | 6 | 2,500 tok |
| Kellastico/AKA akatheapp.io Local-first, task-driven agnostic ADE built for the desktop experience. | 10 | Claude Code | 1 | 1,101 tok |
| tapesymbolstate/looprinter | 10 | Claude Code | 3 | 970 tok |
| chrisLoweDev/AthleteOS Claude code powered personal trainer to plan, and reflect on workouts for the week | 10 | Claude Code, Codex, OpenCode | 13 | 8,311 tok |
| lovelyJason/mcp-switch A tool integrating Cursor, Windsurf, Claude Code, Codex, Gemini, Antigravity, and other ed | 10 | Claude Code, Codex, Cursor, OpenCode | 11 | 3,133 tok |
| nimble-giant/ailloy The package manager for AI instructions. Author, compile, package, and distribute reusable | 10 | Claude Code, Codex, OpenCode | 11 | 1,180 tok |
| hanjin-kim/redcell Adversarial Red Team for corporate strategy | 10 | Claude Code | 1 | 3,008 tok |
| Mohamedsaleh14/ContextGit contextgit.com Context and requirement Management tool for CLI LLM tools | 10 | Claude Code, Cursor | 3 | 2,701 tok |
| chajus1/proxmox-mcp-enhanced Enhanced Proxmox MCP server with 70+ tools for comprehensive infrastructure management, se | 10 | Claude Code | 53 | 47 tok |
| OpenSIPS/opensips-mcp-server OpenSIPS MCP Server | 10 | Claude Code | 6 | — |
| RohiRIK/claude-code-config Personal Claude Code global config — hooks, agents, skills, commands | 10 | Claude Code, Codex, OpenCode | 2 | 3,024 tok |
| devsuperior/ia-java-spring-2026 devsuperior.com.br Projeto-base Java/Spring Boot para demonstrar fluxo agêntico com GitHub Copilot: MCP, cust | 10 | Claude Code | 4 | — |
| Alberto-Codes/docvet alberto-codes.github.io Comprehensive docstring quality vetting for Python projects | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 65 | 3,803 tok |
| wcgomes/agents-workspace Agents Workspace provides portable skills and a boot policy that guide your assistant to c | 10 | Codex, OpenCode | 1 | 164 tok |
| Obsidian-Owl/specwright obsidian-owl.github.io Craft quality software with AI discipline. Spec-driven development plugin for Claude Code | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 1,755 tok |
| rasatpetabit/masterplan Brainstorm → plan → execute development workflow plugin for Claude Code | 10 | Claude Code, Codex, OpenCode | 2 | 1,835 tok |
| Y0lan/laws-of-software-engineering 56 laws of software engineering as an installable Claude Code skill, paraphrased from laws | 10 | Claude Code | 1 | 1,698 tok |
| linxule/mineru-mcp | 10 | Claude Code, Codex, OpenCode | 3 | 2,500 tok |
| DanielGouveiah/glasses daniskills.vercel.app Put your glasses on. Evidence-first planning and bounded implementation diagnosis for AI c | 10 | Claude Code, Codex, OpenCode | 2 | 73 tok |
| DilawarShafiq/unworldly pypi.org The flight recorder for AI coding agents. Tamper-evident, verifiable audit trails of file | 10 | Claude Code | 14 | 2,892 tok |
| harness-studio/harness-studio Governed, adversarial framework for shipping software with AI agents — the maker never gra | 10 | Claude Code | 50 | 561 tok |
| TheMattBerman/creator-breakout-kit Agent-ready creator strategy kit that turns brand truth and breakout content patterns into | 10 | Claude Code | 1 | 1,542 tok |
| Tankatronic/ynab-mcp-server This is an experimental mcp server I made to try to make it easier to use YNAB without lin | 10 | Claude Code | 54 | — |
| PedroMosquera/squadai The agent config you can verify. Declare it once, apply it to seven agent harnesses, fail | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 41 | 893 tok |
| mohamed-hossam1/nextjs-skills Next.js 16+ caching architecture. Applies to any App Router project regardless of domain. | 10 | Claude Code, Codex, OpenCode | 2 | 2,100 tok |
| Sagargupta16/itr-agent Local-first MCP server for Indian income tax: deterministic tax computation, regime compar | 10 | Claude Code | 1 | 3,116 tok |
| deepshal99/notch-so-good notchsogood.com The world's smallest coworker lives in your Mac's notch. Peek, a tiny 3D character, watche | 10 | Claude Code, Codex, OpenCode | 2 | 1,747 tok |
| ivo-toby/postgram postgram.dev Self-hosted knowledge for humans and agents. | 10 | Claude Code, Codex, OpenCode | 11 | 1,132 tok |
| AtharvaMaik/PromptQueue Dependency-free prompt scheduler for AI rate-limit resets. Queue prompts for Claude, Codex | 10 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 597 tok |
| AlgoVaultLabs/crypto-quant-signal-mcp algovault.com AI trading brain for crypto perps — composite signals, funding rate arb scanning, and mark | 10 | Claude Code, Cursor | 3 | — |
| rokasklive/opengrok-go-mcp opengrok MCP but in Go | 10 | Claude Code, Codex, GitHub Copilot, OpenCode | 35 | 2,055 tok |
| LEO001020/codex-loop-orchestra A control loop that turns Codex subagents into a continuously refilled engineering team—wi | 10 | Claude Code, Codex, OpenCode | 1 | 2,189 tok |
| iolairus/borderlint A tool for mapping where your AI data flows and governing it against your residency and so | 10 | Claude Code, Codex, OpenCode | 30 | 1,718 tok |
| lza6/Agent-skills-code-op A full-stack language development and SaaS product delivery skill that lets one person do | 10 | Claude Code | 10 | — |
| kamiazya/whiteboard kamiazya-whiteboard.pages.dev An collaborative diagramming MCP tool for AI. Use it to align on specs, architecture, work | 10 | Claude Code, Codex, OpenCode | 44 | 3,768 tok |
| stone16/multica-agent-team Public reference operating model for reusable, evidence-driven AI agent teams on Multica. | 10 | Claude Code, Codex, OpenCode | 3 | 4,494 tok |