2,349 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 agents7,510Claude Code6,601Data and AI3,691Backend and APIs3,489Languages3,402Planning3,208Git and workflow3,142Code review2,734Memory and context2,361DevOps and cloud2,296Research2,292Writing and docs2,291
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| PMDevSolutions/Aurelius A Claude Code toolkit for building React apps, from Figma designs to shipped product. Ship | 8 | Claude Code | 3 | 7,530 tok |
| miikkij/aimeat-protocol aimeat.io The Linux of AI - an open, federated, self-hosted AI operating system. Humans, AI agents, | 7 | Claude Code | 18 | 13,411 tok |
| kaisers-io/refs npmjs.com Gives coding agents the real source of your dependencies, not a guess. | 7 | Claude Code, Codex, OpenCode | 2 | 1,342 tok |
| ivanostanin/lucius-mcp ivanostanin.github.io A feature-rich Model Context Protocol (MCP) server and CLI for Allure TestOps TMS. | 7 | Codex, OpenCode | 1 | 374 tok |
| naimkatiman/continuous-improvement continuous-improvement.dev Claude Code that gets sharper every session: runtime discipline and instinct memory (the 7 | 7 | Claude Code, Codex, OpenCode | 2 | 6,159 tok |
| steve-magne/hookstack hookstack.app Claude Code hooks catalogue — production-ready hooks for Claude Code, OpenAI Codex & GitHu | 7 | Claude Code, Codex, OpenCode | 28 | 9,006 tok |
| hslee16/Archy Architectural sensor for Python codebases - keeps structure honest under AI-assisted devel | 7 | Claude Code, Codex, OpenCode | 2 | 3,269 tok |
| gomilesf/convergo Disciplined software engineering for coding agents: plan → review → build loops that actua | 7 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 865 tok |
| paultyng/testagent Deterministic fake of the claude and codex CLIs. Test hooks and orchestrator integrations | 7 | Claude Code, Codex, OpenCode | 5 | 2,201 tok |
| DebugSwift/XcodeBazelMCP xcodebazelmcp.github.io MCP server and CLI for Bazel-based Apple platform development — tools for iOS, macOS, tvOS | 7 | Claude Code, Codex | 7 | — |
| layer1labs/specsmith specsmith.readthedocs.io Lean governance for AI-assisted development: requirements tracking, test enforcement, epis | 7 | Claude Code, Codex, OpenCode | 37 | 883 tok |
| canblmz1/ruleProb Test whether your CLAUDE.md, AGENTS.md and .cursor/rules actually survive AI agent executi | 7 | Claude Code, Codex, OpenCode | 2 | 2,881 tok |
| lqwdtech/SaturnZap lqwdtech.github.io Bitcoin Lightning wallet CLI built for autonomous AI agents. | 7 | Claude Code, GitHub Copilot | 3 | 1,782 tok |
| ksgisang/AI-Watch-Tester ai-watch-tester.vercel.app AI-powered automated E2E testing. Just enter a URL — AI generates and runs test scenarios. | 7 | Claude Code, Codex, OpenCode | 2 | 6,408 tok |
| oguzc/playwright-wizard-mcp MCP server providing Playwright test generation wizard with intelligent prompts and best p | 7 | GitHub Copilot | 1 | 590 tok |
| BlackLeg15/desafio_bloc_1 Flutter Playground app | 7 | Codex, Cursor, OpenCode | 4 | 846 tok |
| burgebj/claude_everything | 7 | Claude Code, Codex, Kiro | 58 | — |
| btafoya/mailsandbox MailSandbox is a fast, zero-dependency email testing tool & API with a web UI, SMTP server | 7 | Claude Code | 1 | 1,392 tok |
| bharath03-a/GitCortex bharath03-a.github.io Branch-aware code knowledge graph for Git repos — indexes your codebase on every commit vi | 7 | Claude Code, Codex, OpenCode | 25 | 764 tok |
| kirkchen/beat Agent-driven BDD workflow plugin for Claude Code | 7 | Claude Code | 1 | 3,899 tok |
| gemyago/atlacp Bitbucket MCP server | 7 | Claude Code, Codex, Gemini CLI, OpenCode | 4 | 1,723 tok |
| josefbacik/kerneldev-mcp A MCP server for configuring, building, booting, and testing kernels | 7 | Claude Code | 1 | 1,725 tok |
| jafreck/Lore Code intelligence MCP for AI Agents | 7 | Claude Code, Codex | 3 | 611 tok |
| BjornMelin/dev-skills AgentSkills library: reusable skills for AI coding agents (AI SDK, Codex, LangGraph, Supab | 7 | Codex, OpenCode | 1 | 4,549 tok |
| davebream/claude-of-alexandria Claude plugin for rigorous biblical study. TDD-built to prevent AI failures: psychologizin | 7 | Claude Code | 2 | 5,437 tok |
| anivar/jest-skill skills.sh AI agent skill for Jest 29/30 — 28 rules: mocks, async, timers, snapshots, CI. Works with | 7 | Codex, OpenCode | 1 | 5,070 tok |
| gosha70/code-copilot-team Project templates with multi-agent team configurations for AI code copilots. Includes read | 7 | Claude Code, GitHub Copilot | 20 | 31,183 tok |
| cekura-ai/cekura-skills Claude Plug-Ins & Skills for Cekura | 7 | Claude Code, Gemini CLI | 2 | 14,813 tok |
| garoon/garoon-mcp-server Garoon official MCP server | 7 | Claude Code, GitHub Copilot | 5 | 1,832 tok |
| joshsmithxrm/power-platform-developer-suite joshsmithxrm.github.io Pro-grade tooling for Power Platform developers | 7 | Claude Code, GitHub Copilot | 30 | 1,152 tok |
| archimedes-run/omniHarness archimedes.run OmniHarness is an open-source super agent harness that orchestrates sub-agents, persistent | 7 | Claude Code, Codex, GitHub Copilot | 12 | 1,717 tok |
| agno-agi/agentos-docker docs.agno.com AgentOS: Serve agents over API, MCP, and chat interfaces like Slack | 7 | Claude Code, Codex, OpenCode | 11 | 15,226 tok |
| LinkedInLearning/playwright-ai-automating-tests-with-mcp-copilot-and-chatgpt-7263000 This is a repo for the LinkedIn Learning course: Playwright and AI: Automating Tests with | 7 | Claude Code, GitHub Copilot | 6 | 712 tok |
| jstoup111/ai-conductor | 7 | Claude Code, Codex, OpenCode | 8 | 10 tok |
| jasonrr/herdr-tally Project-scoped todos & scratchpads for you and your agents. | 7 | Claude Code, Codex, OpenCode | 3 | 2,010 tok |
| alilee/cranelisp Statically typed, jit compiled, pure functional lisp | 7 | Claude Code, Codex, GitHub Copilot, OpenCode | 18 | 6,595 tok |
| JacobCoffee/debug-toolbar debug-toolbar.scriptr.dev Debuggability elevated. Debug toolbar for ASGI applications. | 7 | Claude Code | 12 | 2,236 tok |
| CiscoDevNet/essentials ciscodevnet.github.io 🔮 Essential packages to build, release, and run great software in the cloud - bots, cards | 7 | Claude Code, Cursor | 3 | — |
| TryGhost/Deploy Shipit plugin that deploys internal Ghost projects to servers over SSH | 7 | Claude Code, Codex, OpenCode | 2 | 1,307 tok |
| Hafeok/product-cli A CLI for managing a products features, test cases and ADRs - and a bit more. | 6 | Claude Code, GitHub Copilot | 9 | 9,778 tok |
| DYAI2025/Plumbline dyai2025.github.io Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. | 6 | Claude Code | 7 | 12,434 tok |
| mohamedzhioua/agent-done-or-not npmjs.com Catch your AI agent lying about "done" A one-file proof-gate for Claude Code, Cursor & Cod | 6 | Claude Code, Codex, Cursor, OpenCode | 3 | 807 tok |
| dgenio/ChainWeaver Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictab | 6 | Claude Code, Codex, GitHub Copilot, OpenCode | 7 | 6,086 tok |
| greglas75/zuvo zuvo.dev Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills | 6 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 5,672 tok |
| onorbumbum/sand onuruzunismail.com Sand is a Swift CLI for Apple silicon Macs. It creates small named Linux environments. Eac | 6 | Codex, OpenCode | 1 | 2,293 tok |
| elastic/jingra Competitive Benchmarking Framework | 6 | Claude Code, Codex, OpenCode | 2 | 390 tok |
| nayasuda/phantom-template 🕵️ Multi-agent AI system template powered by Gemini CLI — automate daily ops with 10 spec | 6 | Claude Code, Gemini CLI | 11 | — |
| flanliulf/cord CORD is a document relationship graph engine for AI-assisted development. It uses determin | 6 | Claude Code, Codex, OpenCode | 56 | 697 tok |
| vlad-ryzhkov/ai-context-engineering-for-qa AI Context Engineering for QA | 6 | Claude Code, Codex, OpenCode | 27 | 1,237 tok |
| lukasmetzler/agenteval Lint, benchmark, and score your AI coding instructions. Stop guessing, start measuring. | 6 | Claude Code, GitHub Copilot | 3 | 1,309 tok |