1,319 projects whose own agent configuration covers testing. 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 agents7,410Claude Code6,578Data and AI3,695Backend and APIs3,487Languages3,404Planning3,188Git and workflow3,106Code review2,712Memory and context2,351Research2,289DevOps and cloud2,283Writing and docs2,279
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| tacticlaunch/mcp-linear MCP server that enables AI assistants to interact with Linear project management system th | 146 | Claude Code, Codex, GitHub Copilot, OpenCode | 14 | 1,420 tok |
| KryptosAI/mcp-observatory CI-native security testing for MCP servers. Attack simulation, schema drift detection, and | 146 | Codex, OpenCode | 1 | 524 tok |
| calf-ai/calfkit-sdk 🐮 Build distributed, event-driven agents | 146 | Claude Code, Codex | 7 | — |
| buer2233/ai-api-test-skill AI API test automation Skill: for Python + pytest + requests, driving Codex / Claude Code | 144 | Claude Code, Codex, OpenCode | 4 | 3,958 tok |
| nooscraft/tokuin CLI tool – estimates LLM tokens/costs and runs provider-aware load tests for OpenAI, Anthr | 143 | Codex, OpenCode | 1 | 1,235 tok |
| askie/grix grix.im Grix : Work with agents like talking to people. | 143 | Claude Code, Codex, OpenCode | 4 | 525 tok |
| ArchiveBox/abx-dl abx-dl.archivebox.io ⬇️ A simple all-in-one CLI tool to download EVERYTHING from a URL (like youtube-dl/yt-dlp, | 141 | Claude Code, Codex, OpenCode | 2 | 1,251 tok |
| jolliai/jolliai jolli.ai Jolli Memory automatically turns your AI coding sessions into structured development docum | 141 | Claude Code, Codex, OpenCode | 2 | 25,790 tok |
| AgentEvalHQ/AgentEval agenteval.dev AgentEval is the comprehensive .NET toolkit for AI agent evaluation—tool usage validation, | 141 | Claude Code, Codex, GitHub Copilot, OpenCode | 15 | 24,068 tok |
| spearchucker667/kimiko moonshot.ai Bypass all api restraints within Kimi-CLI | 140 | Codex, OpenCode | 1 | 1,096 tok |
| mazrean/kessoku Next-generation google/wire with parallel dependency injection for Go | 139 | Claude Code, Codex, OpenCode | 2 | 1,676 tok |
| openclaw/shellbench huggingface.co The agent benchmark that scores the full stack — harness, config, and model — not just the | 139 | Claude Code, Codex | 2 | — |
| herald-email/herald-mail-app Herald is a terminal email client and inbox cleanup tool with IMAP, AI-assisted triage, MC | 138 | Claude Code, Codex, OpenCode | 8 | 10,502 tok |
| jvm-skills/jvm-skills | 138 | Claude Code, Codex | 20 | — |
| Wholiver/metis Metis is a coding agent that boosts AI/LLM coding performance by 50% | 138 | Codex, OpenCode | 1 | 1,891 tok |
| 1Password/SCAM 1password.github.io SCAM - Security Comprehension Awareness Measure | Open-source benchmark that tests AI agen | 136 | Codex, OpenCode | 1 | 3,027 tok |
| ibuilder/massing massing.build Open, self-hosted, IFC-native AEC platform: web BIM viewer + modeling, a ~100-module GC po | 134 | Claude Code, Codex, OpenCode | 9 | 7,072 tok |
| hidai25/eval-view evalview.com Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in C | 133 | Codex, OpenCode | 1 | 2,634 tok |
| minghinmatthewlam/openbench Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses ( | 133 | Codex, OpenCode | 1 | 2,496 tok |
| kbrdn1/gwm-cli gwm.kbrdn.dev Git worktree manager for the terminal: CLI + TUI in Rust. Creates the worktree, runs your | 132 | Claude Code, Codex, OpenCode | 2 | 4,714 tok |
| Firma-AI/openfirma firma-ai.github.io Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call | 132 | Claude Code, Codex, OpenCode | 20 | 2,313 tok |
| czlonkowski/n8n-mcp-cc-buildier | 132 | Claude Code, Codex, OpenCode | 13 | 4,701 tok |
| jamesmontemagno/ohmyposh-configurator configurator.ohmyposh.dev Design beautiful terminal prompts without touching configuration files | 132 | Claude Code, Codex, GitHub Copilot | 5 | 1,937 tok |
| AlphaLab-USTC/OhMyCode Minimal and Customizable CC-Style Coding Agent | 131 | Claude Code, Codex, OpenCode | 26 | 1,372 tok |
| ikamensh/kodo Orchestrator for AI coding (claude code, cursor, codex, gemini) | 131 | Claude Code, Codex, OpenCode | 2 | 2,244 tok |
| bifrost-proxy/bifrost bifrost-proxy.github.io Bifrost is a high-performance, AI-friendly proxy server written in Rust. It provides power | 131 | Claude Code, Codex, OpenCode | 10 | 16,937 tok |
| GhabiX/SpineCodex SpineCodex: Let your Codex work, evolve, and scale on a SpineTree — up to 10× effective c | 131 | Codex, OpenCode | 15 | 5,182 tok |
| microsoft/AutoGenesis AutoGenesis is an AI-powered automated testing framework based on Model Context Protocol ( | 131 | Claude Code, Codex | 2 | — |
| ctxr-dev/llm-wiki-memory Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. | 130 | Claude Code, Codex, OpenCode | 6 | 2,138 tok |
| one-ie/one template.one.ie Make Your Ideas Real. Build Apps, Websites and AI Agents with Plain English with Astro, Re | 129 | Claude Code, Codex, OpenCode | 4 | 3,237 tok |
| z80dev/lemon BEAM-native platform for LLM agents: OTP-supervised per-run processes, pluggable engines a | 129 | Claude Code, Codex, OpenCode | 4 | 9,017 tok |
| duane1024/l123 | 129 | Claude Code, Codex, OpenCode | 3 | 3,595 tok |
| microsoft/eval-guide A plugin for AI agent evaluation. Plan evals, generate test cases, interpret results for C | 128 | Claude Code, Codex, GitHub Copilot, OpenCode | 3 | 3,504 tok |
| vinta/hal-9000 Opinionated AI coding agent and dev environment automation for macOS | 128 | Claude Code, Codex, OpenCode | 4 | 1,456 tok |
| ryan-yuuu/crypto-trading-arena The open source trading arena | 126 | Claude Code, Codex | 6 | 795 tok |
| ManiruzzamanAkash/wp-react-kit A simple starter kit to work in WordPress with WordPress Rest API, WP-script, React, React | 123 | Claude Code, Codex, OpenCode | 2 | 3,855 tok |
| intent-driven-dev/intent-driven-template intent-driven.dev OpenSpec and OpenCode template for intent-driven development with specs, ADRs, C4 diagrams | 123 | Codex, OpenCode | 1 | 42 tok |
| luongnv89/skills luongnv.com Supercharge your AI agents/bots with reusable skills | 123 | Claude Code, Codex, OpenCode | 6 | 1,877 tok |
| heygen-com/heygen-cli developers.heygen.com Create AI videos from the terminal. Official CLI for the HeyGen video generation API. | 123 | Claude Code, Codex, OpenCode | 4 | 1,760 tok |
| dcb/homeassistant-claude-kit AI-guided Home Assistant setup — automation templates, mobile-first React dashboard, and C | 119 | Claude Code, Codex, OpenCode | 5 | 3,903 tok |
| lsp-client/lsp-skill lsp-client.github.io IntelliSense Designed for Coding Agent | 119 | Claude Code, Codex, OpenCode | 2 | 300 tok |
| mudrii/hermesd TUI monitoring dashboard for Hermes AI agent | 117 | Claude Code, Codex, OpenCode | 3 | 1,408 tok |
| eric-tramel/moraine eric-tramel.github.io Unified realtime agent trace database & search MCP | 117 | Claude Code, Codex, OpenCode | 4 | 2,736 tok |
| krodak/clickup-cli ClickUp CLI for AI agents | 115 | Claude Code, Codex, OpenCode | 4 | 1,959 tok |
| helderberto/dotfiles ⚙️ Setup a macOS environment quickly and easily! | 115 | Codex, OpenCode | 1 | 575 tok |
| spences10/sveltest sveltest.dev Comprehensive Svelte 5 testing examples and patterns using Vitest Browser Mode, Playwright | 113 | Claude Code, Codex, Cursor, OpenCode | 4 | 4,106 tok |
| computesdk/benchmarks computesdk.com Compare startup time-to-interactive for top sandbox providers. | 113 | Claude Code, Codex | 3 | — |
| petrkindlmann/qa-skills qa-skills.com 50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Stan | 113 | Claude Code, Codex, OpenCode | 2 | 2,390 tok |
| bladeofgod/flutter-ai-harness An AI-native engineering harness for production Flutter and hybrid mobile app repositorie | 112 | Claude Code, Codex, OpenCode | 55 | 6,359 tok |
| AMD-AGI/AgentKernelArena AgentKernelArena provides an end-to-end siloed-benchmarking environment where different LL | 112 | Claude Code, Codex, OpenCode | 2 | 1,759 tok |