Testing

18,346 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

seedgen

793

katareayush/video-captions

Plugin Claude Code

Bundles 1 skill, 1 command · 145 tokens together

Analyze any repo and generate a runnable, schema-aware test-data seed script. Works across web2, web3, Python, and more, with locale/filter support.

not rated 8 1mo ago A tokens not measured original MIT

aiopshwang/verify-regression-tests

Skill Codex

Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…

not rated 8 13d ago A 75 tokens original MIT

devflow

797

AppleCG/devflow

Plugin Claude Code

Bundles 1 skill · 53 tokens together

Full-lifecycle AI development workflow — fuses grill-with-docs (Matt Pocock) + OpenSpec (Fission-AI) + superpowers (obra) into one disciplined pipeline. Three modes: Design (quick-grill → spec-lite), Build (grill → spec → plan → isolate → enhanced-apply → review → archive), Fix (diagnose → apply → verify → archive).

not rated 8 2mo ago A tokens not measured original MIT

validate-artifact

798

forthends/clockwork

Skill Claude CodeCodex

A checking procedure for work products such as project documents. It checks that required sections exist, contain real content, and point to files or references that actually exist.

not rated 8 2mo ago A 0 tokens original MIT

sinatra-test

799

geoffjay/claude-plugins

Command Claude Code needs its repo

Generate comprehensive tests for Sinatra routes, middleware, and helpers using RSpec or Minitest.

not rated 8 10mo ago A 18 tokens original MIT

msbaek-tdd

801

msbaek/msbaek-claude-plugins

Plugin Claude Code

Bundles 28 skills, 10 agents, 2 hooks · 2,564 tokens together

Java + Spring Boot TDD workflow plugin with requirements input drafting, RGB cycle, feature-level autonomous implementation, Cucumber acceptance testing, local tidying, system-wide refactoring, and 18 optional refactoring skills. Plan phase and Web App acceptance/skeleton setup now delegate to dedicated agents instead.

not rated 8 changed 2d ago A tokens not measured

tdd-core

803

morodomi/tdd-skills

Plugin Claude Code

Bundles 13 skills, 14 agents · 1,040 tokens together

TDD 7-phase workflow skills. Language-agnostic test-driven development: INIT → PLAN → RED → GREEN → REFACTOR → REVIEW → COMMIT.

not rated 8 6mo ago A tokens not measured original MIT

development-process

805

vepo/issues

Cursor rule Cursor

Mandatory agentic development process — feature analysis, architecture design, task break, approval, TDD.

not rated 8 1mo ago A 3,938 tokens original Apache-2.0

EmptyRabbit/testcase-generator-mcp

MCP server Claude CodeCodexCursor +2

Testcase Generator MCP Server for generating and managing test cases. Runs locally from the testcase-generator-mcp Python package.

not rated 8 5mo ago A tokens not measured original MIT

godot-forge

807

gregario/godot-forge

MCP server Claude CodeCodexCursor +2

Godot 4 MCP server — test runner, API docs, script analysis, scene parsing, LSP. Runs locally from the godot-forge npm package. Needs 1 environment variable to run.

not rated 8 4mo ago A tokens not measured original MIT

eval-driven-dev

808

yiouli/pixie-qa

Skill Claude CodeCodex

Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals…

not rated 8 +1 4mo ago A 89 tokens copy · 100% MIT

cuj-guardian

809

aiatelie/ai-atelie

Skill Claude Code

Run and triage AI Atelie's Critical User Journey (CUJ) for every PR — the single end-to-end test that proves a user can open the app, create a project, drive the Claude Code agent, and see the canvas render. Before running, gate by inspecting the PR diff for changes that plausibly affect the journey (routes…

not rated 8 +1 3mo ago A 137 tokens original MIT

true-platform-testing

810

katalon-labs/true-skills

Cursor rule Cursor

End-to-end Katalon True Platform testing workflow and lifecycle router. Use when one request spans several stages and no single skill owns all of it, for example analyze a requirement, design and import the cases, build a suite, run it with AI, and report the outcome. Also use to route any testing request across the…

not rated 8 +1 today A 220 tokens original MIT

api-testing-mcp

811

cocaxcode/api-testing-mcp

MCP server Claude CodeCodexCursor +2

MCP server for API testing. 35 tools: HTTP, assertions, flows, OpenAPI, collections. Runs locally from the @cocaxcode/api-testing-mcp npm package.

not rated 8 +1 4mo ago A tokens not measured original MIT

chuk-mcp-ios

812

chrishayuk/chuk-mcp-ios-simulator

MCP server Claude CodeCodexCursor +2

iOS Device Control MCP Server - Comprehensive iOS automation and testing. Runs locally from the chuk-mcp-ios Python package.

not rated 8 +2 1y ago A tokens not measured

bruno-mcp-studio

813

Ostico/bruno-mcp-studio

MCP server Claude CodeCodexCursor +2

Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail. Runs locally from the @ostico/bruno-mcp npm package.

not rated 8 +1 10d ago A tokens not measured original MIT

verify-before-code

814

Morningstar202604/AgentSeed

Skill Claude CodeCodex

Guardrail for coding agents. Loads the SDD contract and the prompt pool before code is written, then calls the agentseed MCP server's verifycode and scanhallucination tools; a task may only be marked complete when both pass and the completion report attaches evidence. Use whenever the agent writes, edits, or claims…

not rated 8 +1 changed 3d ago A 73 tokens

whshang/herdr-mcp

Skill Claude CodeCodex

Reference for designing, changing, debugging, testing, and releasing AI-generated code so failures become durable regression assets and completion is proven across the real delivery boundary.

not rated 8 +1 today A 37 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: