Testing

1,343 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

ProjectStarsConfiguresFilesAlways loaded
Grinv/mal-mcp npmjs.com MyAnimeList MCP server — Tenrai-powered reads plus official MAL personal-list management. 2 Claude Code, Codex, OpenCode 10 3,382 tok
MRNAQA/sourceweave-web-search Fully local MCP server and CLI for web research 2 Claude Code, Codex, OpenCode 3 995 tok
ObscuritySRL/umbriel Drive and inspect a whole Windows machine from Bun — apps, windows, input, screen, OCR, re 2 Claude Code, Codex, OpenCode 2 3,461 tok
benseverndev-oss/goldencheck [Archived] Now part of the Golden Suite monorepo: github.com/benseverndev-oss/goldenmatch 2 Claude Code, Codex, GitHub Copilot, OpenCode 3 6,781 tok
chriswu727/argus yichenwu.dev Autonomous QA MCP that tests web and macOS apps like a real testing engineer—and verifies 2 Codex, OpenCode 1 2,825 tok
stonematt/mcp-obsidian-cli Save chat notes from Claude Desktop to your vault — MCP on Obsidian CLI. Keep what matters 2 Claude Code, Codex, OpenCode 4 1,104 tok
nsphung/mcp-snowflake-server pypi.org MCP Snowflake Server NSP - A Snowflake MCP server — SQL queries, schema exploration, and d 2 Claude Code, Codex 1
MarketcheckHub/marketcheck-api-mcp-apps apps.marketcheck.com Marketcheck MCP UI, embeddable apps showcase 2 Claude Code, Codex, OpenCode 2 333 tok
mcqua007/agents-skeleton A language-agnostic starter repo for AI-powered development. Single-source-of-truth AGENTS 2 Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode 6 908 tok
JarlZhang/claude-presets Have a bunch of API keys and tired of switching between them? Use one setapi command to ch 2 Codex, OpenCode 1 445 tok
aks-builds/quality-skills 107 production-grade QA engineering skills for AI agents — frontend, API, performance, mob 2 Claude Code, Codex, OpenCode 2 2,230 tok
piecioshka/whose-context-wins Poligon do sprawdzania, który plik konfiguracyjny (CLAUDE.md, AGENTS.md, .cursorrules...) 2 Claude Code, Codex, GitHub Copilot, Cursor, OpenCode 5 62 tok
divyanshu-iitian/agent-website-design-skills Verification-first AI agent skills for website design, landing pages, responsive UI QA, ac 2 Codex, OpenCode 1 514 tok
DjFikie25/shipkit Build full-stack Next.js and React Native apps with integrated auth, database, AI chat, an 2 Codex, OpenCode 1 3,842 tok
EmZod/Agent-Focus-Group Test AI tool documentation against multiple models before shipping. Send skill docs to GPT 2 Codex, OpenCode 1 2,284 tok
Coverage-Cat/skills coveragecat.com Public installable skills for Coverage Cat 2 Codex, OpenCode 1 1,046 tok
jpbaking/playwright-fieldkit Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, 2 Claude Code, Codex, OpenCode 2 186 tok
unshDee/proofrag pypi.org Point your agent at your docs and your RAG app; get a golden test set + an LLM-as-judge & 2 Claude Code, Codex, OpenCode 1 348 tok
xFurti/leogriel xfurti.github.io Weave Agent Skills into every workflow — discover, lock, sync, audit, and test across codi 2 Codex, OpenCode 1 607 tok
rdlugs/roborak roborak.pages.dev AI code review from the terminal: local diffs, GitLab MRs, and GitHub PRs. Severity-graded 2 Claude Code, Codex, OpenCode 2 2,505 tok
MisterBrookT/finreportbench arxiv.org FinReportBench: an expert-grounded benchmark for institution-grade financial report genera 2 Codex, OpenCode 1 2,610 tok
mtthsnc/tempest Tempest — a cross-harness software factory: opinionated build & QA workflows as portable A 2 Claude Code, Codex, OpenCode 2 1,012 tok
phenomenoner/ai-agent-thinkroom An on-demand, local-first AI think tank that opens independent lines of inquiry, tests the 2 Codex, OpenCode 1 362 tok
mirekondro/The-Pre-Flight-Check mirekondro.github.io ✈️ Stop your AI coding agent from declaring 'done' on broken code. Fail-fast quality gate: 2 Claude Code, Codex, Gemini CLI, OpenCode 3 3,486 tok
AIwork4me/open-llm-wiki Claude Code skill bundle for building auditable research wikis from papers with independen 2 Codex, OpenCode 1 748 tok
shenli/devtool-ax-kit A local-first toolkit for testing agent experience in Agent-Native developer tools. 2 Codex, OpenCode 1 241 tok
quantsquirrel/claude-forge-smith TDD-based self-improving skills for Claude Code 2 Claude Code, Codex, OpenCode 1 594 tok
uppadhyayraj/dq-awesomeqa uppadhyayraj.github.io QA lifecycle plugin for UI, API, accessibility, and performance testing across coding agen 2 Claude Code, Codex, Gemini CLI, OpenCode 4 1,631 tok
KashZod/devloop kashzod.github.io A test-driven development loop for agentic coding tools such as Claude Code and Codex: /sp 2 Codex, OpenCode 1 452 tok
carmentacollective/carmenta carmenta.ai A heart-centered AI for creating at the speed of thought 2 Claude Code, Codex, OpenCode 25 950 tok
leaf76/session-collab-mcp npmjs.com Provider-agnostic MCP collaboration server: claim files, persist working memory, and preve 2 Claude Code, Codex, OpenCode 2 1,808 tok
hybridindie/comfyui_mcp Secure MCP server for ComfyUI — workflow inspection, path sanitization, rate limiting, and 2 Claude Code, Codex, OpenCode 2 4,166 tok
craftled/openklip openklip.com Agent-native video toolchain. Local-first video editing for agents and humans. CLI and MCP 2 Claude Code, Codex, OpenCode 7 22,953 tok
logan-suu/Agora The digital town square where AI agents (PM/Architect/Coder/Tester) collaborate via group 2 Claude Code, Codex, OpenCode 29 13,797 tok
terraboops/trellis Design agent teams that take ideas from concept to launch. Custom pipelines, sandboxed exe 2 Claude Code, Codex, OpenCode 2 245 tok
babywyrm/mcpnuke MCP red teaming & security scanner — enumerate, probe, and exploit Model Context Protocol 2 Codex, Cursor, OpenCode 6 1,087 tok
vinicq/falsegreen-skill vinicq.github.io LLM skill that finds false-green tests across Python/TS/JS/Robot using the J1-J6 protocol 2 Claude Code, Codex, Gemini CLI, OpenCode 3 11,735 tok
OpenSystemsLab/mcp-cli opensystemslab.com MCP-CLI is a command-line tool for interacting with and testing Model Context Protocol (MC 2 Codex, OpenCode 1 1,025 tok
cipherfoxie/agent-bench sovgrid.org Measure whether an MCP server or skill actually improves your coding agent. A/B arms, dete 2 Codex, OpenCode 1 784 tok
aram-devdocs/plumb plumb.aramhammoudeh.com Deterministic design-system linter for rendered websites. CLI + MCP server for AI coding a 2 Claude Code, Codex, OpenCode 25 1,103 tok
moonrunnerkc/ruleprobe npmjs.com Translate instruction files into ESLint configs, detect drift, and extract rules 2 Claude Code, Codex, OpenCode 2 2,638 tok
xuanhieu2611/Rivet youtu.be Autonomous software engineering platform. Submit an engineering job, watch a sandboxed AI 2 Claude Code, Codex, OpenCode 2 16,354 tok
OrionArchitekton/proctor danmercede.com Proctor: an agent that QAs other agents. UiPath AgentHack 2026, Track 3 (UiPath Test Cloud 2 Codex, OpenCode 1 550 tok
hatyibei/shingan AI Agent Workflow Static Analyzer — detect infinite loops, cost explosions, PII leak paths 2 Claude Code, Codex 3
liuyingxuvka/FlowGuard Executable finite-state models for designing and checking AI-agent workflows, UI flows, an 2 Codex, OpenCode 16 2,987 tok
AsiaOstrich/EngramGraph Self-evolving code & knowledge graph memory engine (SAGE + CodeGraph) — Kuzu + tree-sitter 2 Codex, OpenCode 1 1,144 tok
jmenzies722/shua-labs shua-labs.vercel.app Tools for running AI agents in production — safe, observable, cheap to operate. 2 Claude Code, Codex, Cursor, OpenCode 16 471 tok
agno-agi/agentos-modal docs.agno.com AgentOS: Serve agents over API, MCP, and chat interfaces like Slack 2 Claude Code, Codex, OpenCode 11 15,414 tok
turnkeeper-ai/turnkeeper-js turnkeeper.ai Public Turnkeeper SDK, CLI, MCP server, agent-builder skill, and governed-agent examples. 2 Claude Code, Codex, OpenCode 3 160 tok
MikeManifold/codex-unified GPT + DeepSeek in one Codex: cross-call subagents, share tools, skills, MCP and history vi 2 Codex, OpenCode 15 6,354 tok