44,931 repositories keep their own agent configuration in the open: a CLAUDE.md, a rules file, instructions for Copilot, a skill the project runs on itself. These are not mods to install. They are worth reading for what they reveal — what a maintainer thinks an agent gets wrong.
Building agents8,489Claude Code6,881Git and workflow3,605Data and AI3,580Backend and APIs3,556Languages3,486Planning3,323Code review2,893Testing2,681Writing and docs2,477DevOps and cloud2,477Memory and context2,375Research2,318Frontend2,308Security2,170Project management1,960
All Claude Code32,505 Codex24,785 OpenCode23,702 GitHub Copilot3,719 Gemini CLI2,034 Cursor1,771 Windsurf202 Kiro114
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| Baba88611/detroit-ai-player Let Your AI Play Detroit：Become Human | 73 | Claude Code, Codex, OpenCode | 2 | 3,161 tok |
| Srajangpt1/ai-security-crew MCP to put security context while vibe coding | 73 | Claude Code, Codex, OpenCode | 4 | 1,250 tok |
| Servosity/msp-skills msp-skills.compoundingteams.com Free MCP servers + Claude Code Skills for MSP tools - PSA, RMM, backup, M365. Local-first: | 73 | Codex, OpenCode | 1 | 2,894 tok |
| projectmentor/hive-mind hivemind.projectmentor.org Shared memory for your AI agents: a fact one agent writes on one machine is there for the | 73 | Codex, OpenCode | 1 | 165 tok |
| 0xMulight/human-social-copy Writes AI/tools/crypto content as human-style Chinese social media copy. For tweets, X pos | 73 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 3,134 tok |
| zenbase-ai/llml Compose data structures, serialize them to prompts. | 73 | Claude Code | 1 | 1,971 tok |
| SwiftfulThinking/SwiftfulStarterProject swiftful-thinking.com Starter project for VIPER/RIBs in SwiftUI | 73 | Claude Code | 3 | 888 tok |
| BARMPlus/locklens Audit npm, Yarn, and pnpm lockFiles as both an MCP server and a CLI tool. | 72 | Codex, OpenCode | 1 | 2,164 tok |
| pablitofernandez/FamilyNido Self-hosted PWA for a single household — shared calendar, chores, meals, school agenda, he | 72 | Claude Code | 1 | 1,761 tok |
| fvadicamo/dev-agent-skills Claude Code skills plugin for Git, GitHub, and skill authoring workflows | 72 | Claude Code | 1 | 2,745 tok |
| 0x0funky/TermHive Human-driven multi-agent dashboard for Claude Code, Codex, Gemini & OpenCode. Web UI, proj | 72 | Claude Code | 1 | 2,058 tok |
| yokingma/time-mcp ⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities | 72 | Claude Code | 1 | 867 tok |
| elastic/elastic-docs-skills elastic.github.io Instructions for code agents on how to author Elastic docs | 72 | Claude Code | 3 | 875 tok |
| appwrite/mcp appwrite.io Appwrite’s MCP server. Operating your backend has never been easier. | 72 | Claude Code, Codex, OpenCode | 2 | 2,790 tok |
| sunnykgupta/AI-Helpers Bunch of helpers I have built for myself to ensure I do not have to repeat myself for the | 72 | Claude Code, OpenCode | 5 | — |
| wandb/wandb-mcp-server The official implementation of the W&B Models and Weave MCP server. | 72 | Codex | 2 | — |
| sametbrr/llm-wiki-manager Agent Skills plugin for a persistent LLM-managed markdown wiki — ingest, cross-reference, | 72 | Claude Code, Codex, OpenCode | 2 | 340 tok |
| gmickel/sheets-cli Composable Google Sheets CLI for humans and agents. Read, write, update cells by key—with | 72 | Claude Code, Codex, OpenCode | 4 | 2,114 tok |
| kromahlusenii-ops/ham goham.dev (HAM) Memory system for AI coding agents. Cut token usage by 80% by scoping context to dir | 72 | Claude Code | 1 | 332 tok |
| assimovt/productskills Product skills for AI agents — discovery, strategy, prioritization, and PRD writing | 72 | Claude Code | 1 | 936 tok |
| vahiiiid/go-rest-api-boilerplate vahiiiid.github.io 🚀 Production-ready AI-friendly Go REST API boilerplate with Clean Architecture, JWT auth, | 72 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 9,140 tok |
| lovstudio/skills lovstudio.ai Top-level index for the Lovstudio skills ecosystem | 72 | Claude Code | 1 | 3,251 tok |
| 1ch1n/mychatarchive mychatarchive.com Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic | 72 | Claude Code | 1 | 422 tok |
| home-operations/konflate A read-only pull request review tool for Flux using Flate for rendering. | 72 | Claude Code, Codex, OpenCode | 2 | 2,940 tok |
| lemoncrow-lab/lemoncrow lemoncrow.com A Complete faster runtime for coding agents. Optimize the journey, not the hop. Make codin | 72 | Claude Code, Codex, OpenCode | 2 | 1,176 tok |
| laravel/package-skeleton Skeleton for Laravel packages | 72 | Claude Code, Codex, OpenCode | 7 | 556 tok |
| yantrikos/yantrikdb yantrikdb.com Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomou | 72 | Claude Code, Codex, OpenCode | 2 | 512 tok |
| andrianllmm/renux pypi.org A terminal-based bulk file renamer with a TUI | 72 | Claude Code, Codex, OpenCode | 4 | 247 tok |
| PostHog/context-mill PostHog context and skill assembly for AI agents and LLM tasks | 72 | Claude Code, Codex, OpenCode | 3 | 1,788 tok |
| spring-ai-community/spring-ai-agentcore Spring Boot integrations for Amazon Bedrock AgentCore | 72 | Codex, OpenCode | 1 | 1,576 tok |
| khakhasshi/LLM_QUANT_FACTORY Auditable multi-agent A-share factor research, knowledge base, long-only backtesting, Auto | 72 | Codex, OpenCode | 1 | 7,297 tok |
| jmschrei/cherimoya Cherimoya is a lightweight sequence-to-function (S2F) model that is small, fast, and easy | 72 | Claude Code | 1 | 1,098 tok |
| MaxGhenis/openmessage openmessage.ai Local-first Google Messages + WhatsApp inbox for Mac, web, and MCP. | 72 | Claude Code | 2 | 5,005 tok |
| AgentDebugX/AgentDebugX agentdebugx.com 【EMNLP 2026 Demo】A debugging framework for agentic AI systems: diagnose failures, attribut | 72 | Codex, OpenCode | 1 | 197 tok |
| boredape874/mcbejsonuimasterAI JSON UI mastery for AI | 72 | Codex, OpenCode | 1 | 3,172 tok |
| codex-tweaks/codex-tweaks Local interface customization tool for the Codex desktop client | 72 | Codex, OpenCode | 1 | 639 tok |
| mavka-ai/unit-tests-skills mavka.ai AI agent skills for generating high-quality unit tests — Given-When-Then test cases, JUnit | 72 | Claude Code, Codex, OpenCode | 3 | 3,127 tok |
| JanYork/llm-wiki-cli janyork.github.io Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolv | 72 | Codex, OpenCode | 1 | 289 tok |
| xi-zhao/OpenQuantum xi-zhao.github.io Open-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP t | 72 | Codex, OpenCode | 1 | 4,250 tok |
| Arize-ai/arize-skills Agent skills for Arize — datasets, experiments, and traces via the ax CLI | 72 | Codex, OpenCode | 1 | 614 tok |
| ccf/agentcairn agentcairn.dev Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the sourc | 72 | Claude Code | 1 | 1,890 tok |
| HimanshuMohanty-Git24/RakshaQuant youtu.be 🛡️ Agentic paper-trading platform for NSE equities that measures whether AI improves trad | 72 | Claude Code | 1 | 2,881 tok |
| pinecone-io/pinecone-mcp Connect your Pinecone projects to Cursor, Claude, and other AI assistants | 72 | Claude Code, Cursor | 10 | — |
| inercia/MCPShell Use shell scripts as MCP tools | 72 | Codex, OpenCode | 1 | 531 tok |
| laguagu/claude-code-nextjs-skills Claude Code skills for AI apps • Next.js 16 • AI SDK 7 • pgvector • bun | 72 | Claude Code, Codex, OpenCode | 2 | 49 tok |
| t09tanaka/mcp-simple-voicevox | 72 | Claude Code | 1 | 613 tok |
| elahlabs/elah elah.dev Elah is a browser-native video editing framework and toolkit for building high-performance | 72 | Codex, OpenCode | 1 | 2,168 tok |
| frendysanusi/claude-pentest-skills AI-powered web application penetration testing skills with Claude Code | 72 | Claude Code | 1 | 2,118 tok |
| plurigrid/asi everything is topological chemputer! | 72 | Claude Code | 5 | — |
| scylladb/scylla-cluster-tests Tests for Scylla Clusters | 72 | Claude Code, Codex, GitHub Copilot, OpenCode | 7 | 10,379 tok |