Testing

1,494 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 agents8,369Claude Code6,848Data and AI3,594Git and workflow3,550Backend and APIs3,545Languages3,459Planning3,305Code review2,872DevOps and cloud2,444Writing and docs2,443Memory and context2,373Research2,311

Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro

ProjectStarsConfiguresFilesAlways loaded
VibeTechnologies/vibe-mcp vibebrowser.app MCP server that drives your real, logged-in Chrome from any MCP client - including agents 3 Claude Code, Codex, OpenCode 3 2,113 tok
kensaurus/mushi-mushi kensaur.us 🦖Know why your AI-built app broke — plain-English diagnosis + ready fix, in your editor. 3 Codex, Cursor, OpenCode 7 25,939 tok
seldonframe/reelier reelier.com Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, r 3 Claude Code, Codex, OpenCode 3 13,870 tok
willbytee-sudo/android-qa-kit Make your coding agent test the Android app you just compiled: installs the APK on a real 3 Claude Code, Codex, OpenCode 2 2,867 tok
yurakawa/mskills npmjs.com mskills is a CLI tool to manage "Agent Skills" for various AI agents. 3 Codex, GitHub Copilot, OpenCode 5 3,477 tok
juwonllee2024-dotcom/rulesync The ESLint & Babel for AI Agent Rules — Compile, lint, optimize, and sync instructions acr 3 Claude Code, Codex, GitHub Copilot, OpenCode, Windsurf 4 882 tok
grnbtqdbyx-create/trace-to-skill Codex Issue Radar and maintainer-readiness tooling for AI coding agents. 3 Codex, OpenCode 1 258 tok
ColdBox/coldbox-cli coldbox.org 💻 The official ColdBox CLI 3 Claude Code, Codex, OpenCode 24 3,351 tok
hly-AI/codingplan 3 Codex, Cursor, OpenCode 7 777 tok
artreimus/software-factory-starter Sample software factory repository with agent contracts, specs, plans, skills, MCP policy, 3 Codex, OpenCode 1 793 tok
loveautomate/ai-qa-agent 3 Claude Code, Codex, OpenCode 2 574 tok
humzakt/dev-starter-kit Production-ready starter repository with CI/CD workflows, issue templates, incident runboo 3 Claude Code, Codex, GitHub Copilot, OpenCode 3 1,704 tok
sopyk/docker-mcpilots Give AI Agents a hand for managing Docker (MCP Server) — manage containers well on Synolog 3 OpenCode 1 —
sandraschi/database-operations-mcp MCP server and webapp for database operations with 15 portmanteau tools supporting SQLite, 3 Claude Code, Codex, GitHub Copilot, Cursor, OpenCode, Windsurf 5 1,472 tok
rc4l/ZandronumMCP Experimental MCP Server for Zandronum. Speeds up modding and engine development. 3 Codex, OpenCode 1 86 tok
openhonest/umbra slopaudit.org Umbra: an apophatic code auditor that reports what your tests are structurally unable to s 3 Codex, OpenCode 1 2,438 tok
Grinv/mal-mcp npmjs.com MyAnimeList MCP server — Tenrai-powered reads plus official MAL personal-list management. 3 Claude Code, Codex, OpenCode 10 3,625 tok
ObscuritySRL/umbriel Drive and inspect a whole Windows machine from Bun — apps, windows, input, screen, OCR, re 3 Claude Code, Codex, OpenCode 2 3,461 tok
Shad0wMazt3r/The-Scaffolding Solve CTF challenges, find bugs, better accuracy. Plug and play with any agent. 3 Claude Code, Codex, OpenCode 2 1,137 tok
MisterBrookT/finreportbench arxiv.org FinReportBench: an expert-grounded benchmark for institution-grade financial report genera 3 Codex, OpenCode 1 88 tok
KashZod/devloop kashzod.github.io A test-driven development loop for agentic coding tools such as Claude Code and Codex: /sp 3 Codex, OpenCode 1 452 tok
ManSio/mscodebase-intelligence Intelligent codebase search & indexing for Zed. Async MCP server featuring LanceDB/BM25 hy 3 Codex, OpenCode 8 9,318 tok
hybridindie/comfyui_mcp Secure MCP server for ComfyUI — workflow inspection, path sanitization, rate limiting, and 3 Claude Code, Codex, OpenCode 2 5,524 tok
logan-suu/Agora The digital town square where AI agents (PM/Architect/Coder/Tester) collaborate via group 3 Claude Code, Codex, OpenCode 29 17,615 tok
babywyrm/mcpnuke MCP red teaming & security scanner — enumerate, probe, and exploit Model Context Protocol 3 Codex, Cursor, OpenCode 6 1,684 tok
RichardGeorgeDavis/Codex-Workspace A local-first multi-repo workspace system with shared runtime control, memory, docs, and a 3 Claude Code, Codex, GitHub Copilot, OpenCode 11 1,610 tok
aram-devdocs/plumb plumb.aramhammoudeh.com Deterministic design-system linter for rendered websites. CLI + MCP server for AI coding a 3 Claude Code, Codex, OpenCode 25 1,103 tok
moonrunnerkc/ruleprobe npmjs.com Translate instruction files into ESLint configs, detect drift, and extract rules 3 Claude Code, Codex, OpenCode 2 2,638 tok
AsiaOstrich/EngramGraph Self-evolving code & knowledge graph memory engine (SAGE + CodeGraph) — Kuzu + tree-sitter 3 Claude Code, Codex, OpenCode 56 1,569 tok
agno-agi/agentos-modal docs.agno.com AgentOS: Serve agents over API, MCP, and chat interfaces like Slack 3 Claude Code, Codex, OpenCode 10 2,338 tok
oumaimah-QA/QIOS Structured QA skill framework for AI agents enabling consistent, risk-aware, and execution 3 Codex, OpenCode 1 488 tok
meleantonio/AC4E_Pavia Participant materials for Agentic Coding for Economists, University of Pavia 2026 3 Claude Code, Codex, OpenCode 12 259 tok
projectbluefin/testsuite projectbluefin.github.io Cloud-native QA pipeline for Project Bluefin — Argo Workflows + KubeVirt + qecore/behave A 3 Claude Code, Codex, GitHub Copilot, OpenCode 5 2,843 tok
konflux-ci/loadtest Konflux loadtest for per&scale testing the platform 3 Claude Code, Codex, Gemini CLI, OpenCode 6 455 tok
atstaeff/ai-agents atstaeff.github.io A complete, modular, and scalable repository of AI Agents, Skills, Templates, and Referenc 3 Claude Code, Codex, GitHub Copilot, OpenCode 3 945 tok
datarobot-oss/datarobot-agent-tester Generate, test, and improve AGENTS.md files and AI coding skills via the DataRobot LLM Gat 3 Codex, OpenCode 1 691 tok
raptorxde/LaunchProof-Web-Audit Cross-agent website launch-readiness audit skill for Codex, Claude Code, Cursor, and AI co 3 Claude Code, Codex, OpenCode 2 228 tok
vepo/contraponto blogs.commit-mestre.dev Self-hostable multi-author blog platform built with Quarkus, HTMX, and PostgreSQL. Per-use 3 Claude Code, Codex, Cursor, OpenCode 22 3,706 tok
rediche/skills Simple, focused agent skills for planning, implementation flow, and QA. 3 Codex, OpenCode 1 55 tok
akshay5995/agent-skill-evals akshay5995.github.io Agent Skill Evals helps you test agent skills with Promptfoo. 3 Codex, OpenCode 1 663 tok
shenyuexin/mobile-e2e-mcp AI-first mobile E2E MCP orchestration 3 Claude Code, Codex, OpenCode 8 2,053 tok
Archolith/menhir archolith.dev Provenance, governed context, and code-impact analysis for coding agents. 3 Claude Code, Codex, GitHub Copilot, Cursor, OpenCode, Windsurf 5 1,015 tok
forgeopslabs/appstore-mcp MCP server (Rust, rmcp) exposing the Apple App Store Connect API — apps, in-app purchases, 3 Codex, OpenCode 1 817 tok
coval-ai/mcp-server coval.dev MCP server for Coval that enables AI assistants to launch evaluations, manage test sets, a 3 Codex, OpenCode 1 945 tok
Nitjsefnie-Harness-Commons/daedalus Browser bridge for agents: drive a real Chrome instance over HTTP, MCP or CLI 3 Claude Code, Codex, OpenCode 3 4,627 tok
dcc-mcp/dcc-mcp-godot pypi.org Godot 4 MCP editor adapter for AI agents to author scenes, scripts, UI and 2D games, inspe 3 Codex, OpenCode 1 2,147 tok
whoamiTM/bi-mcp MCP server for Blue Iris NVR — exposes the Blue Iris JSON API and .reg config to LLM age 3 Claude Code, Codex, OpenCode 4 9,704 tok
AtlassianPS/JiraAgilePS PowerShell module to interact with Jira's Agile plugin 3 Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode 5 2,263 tok
twohoursonelife/dictator A user management and utility Discord bot specifically built for Two Hours One Life. 3 Codex, OpenCode 1 137 tok
TheFractalyst/QuantConnectMCP QuantConnect/Lean MCP server - 6 tools for docs lookup, code validation, and code generati 2 Codex, OpenCode 1 437 tok