18,481 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.
Skill Claude CodeCodex needs its repo
Evaluate an existing agent skill with Promptfoo-native behavior, routing, or role-play tests. Use when a skill needs executable evidence that its product promise works. Do not use to author the domain skill itself.
Plugin Claude Code
Bundles 1 skill · 105 tokens together
A collection of Claude Code skills for agentic workflows — QA testing, staging validation, security auditing, and more.
Skill Claude Code
A workflow for end-to-end UI testing, which checks complete user journeys across a web application in a browser.
quatico-solutions/agent-skills
Plugin Claude Code
Bundles 18 skills · 1,339 tokens together
Quatico development essentials: commit conventions, PR workflows, TDD, testing, Bitbucket/Jira integration, and team standards.
Skill Claude CodeCodex
Write and run I2C driver validation tests that compare Arduino and CircuitPython I2C transactions for a given sensor/breakout. Use when validating that an Arduino driver and a CircuitPython driver produce equivalent I2C bus traffic for chip ID reads and all configuration register set/get operations.
postindustria-tech/agentic-toolkit
Plugin Claude Code
Bundles 9 skills, 9 agents · 1,605 tokens together
Development practices and workflows for quality-driven software engineering. Provides TDD, session completion, molecular task execution with formula-based atom graphs, multi-agent code review, entity test remediation, obligation-driven test derivation, test source-of-truth auditing, and obligation reclassification.…
Skill Claude CodeCodex
Use when refactoring TypeScript code whose tests require monkey-patching modules, swapping globals, or stubbing imports (vi.mock, jest.mock, sinon) because collaborators (database, HTTP client, clock, RNG, env, logger) are hardcoded inside the unit. Trigger on requests like "I can't test this without mocking the…
ashaykubal/essential-agents-skills
Skill Claude Code
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
Plugin Claude Code
Bundles 5 skills, 9 commands · 383 tokens together
A helper for developing and testing iDempiere REST APIs. iDempiere is an open-source business software system, and REST APIs let other programs communicate with it over the web.
Kacper0199/Opencode-Ultrathinker
Skill Claude CodeCodex
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
Plugin Claude Code
Bundles 13 commands, 5 agents · 377 tokens together
Fully Agentic Multi-Agent Orchestration Framework for Claude Code - Autonomous dev → UAT → QA pipeline with 150k token-budgeted tasks, parallel-first execution, retry limits, and enforcing quality gates.
Skill Claude Code
Automate browser interactions, test web pages and work with Playwright tests.
JensAstrup/claude-plugin-marketplace
Plugin Claude Code
Bundles 2 skills · 97 tokens together
Run linter and write or update tests for staged/unstaged changes or branch changes.
Plugin Claude Code
Bundles 49 skills, 43 commands, 4 agents, 3 MCP servers · 5,993 tokens together
All-in-one QA + quality-management toolkit for Claude Code; commands are namespaced /qa: . Serves QA/QC engineers, QA Managers/Leads and Product Ops. scaffold creates a standard Page Object Model project from scratch (Playwright-Web or Appium-App) — a fresh repo gets a compiling framework + an example login test.
raisedadead/claude-code-plugins
Plugin Claude Code
Bundles 6 skills, 1 agent · 479 tokens together
Engineering-craft skills that sharpen the edge: red-green TDD, flaky-test audit, pre-decision doubt review, merge-conflict resolution, skill linting, and a column budget computed from the staged diff. Each carries a deterministic self-verify.
andrueandersoncs/claude-tla-plus-plugin
Plugin Claude Code
Bundles 1 skill, 6 commands · 116 tokens together
Generate TLA+ specifications, PlusCal algorithms, and TLC model configurations for formal verification of distributed systems, concurrent algorithms, and state machines.
MadeByTokens/claude-code-plugins-madebytokens
Plugin Claude Code
Bundles 4 commands, 3 agents · 90 tokens together
Three-agent adversarial TDD loop: Test Writer (bad cop), Code Writer (suspect), and Reviewer (good cop) work together while keeping each other honest.
Plugin Claude Code
Bundles 1 skill · 47 tokens together
Test coverage feedback loop using undercover gem.
Plugin Claude Code
Bundles 6 skills, 5 commands, 5 agents, 1 hook · 639 tokens together
Go 1.24+ development workflow with TDD, quality gates, and code review. Provides specialized agents, skills, and commands for professional Go development.
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 251 tokens together
Teamscale integration for Claude Code. Detection and resolution of quality issues and test gaps. Change-based test selection to allow running a small set of regression tests.
rand/disciplined-process-plugin
Plugin Claude Code
Bundles 5 skills, 17 commands, 3 agents, 5 hooks, 1 MCP server · 452 tokens together
A disciplined AI-assisted development workflow with specification-first development, test-driven implementation, ADRs, and traceable task management. Inspired by the Rue language development process.
Cursor rule Cursor
BDD testing for ArchiPy apps — Behave, ScenarioContext, testcontainers.
Plugin Claude Code
Bundles 2 skills, 1 agent · 202 tokens together
User Acceptance Testing workflow for web apps via Chrome DevTools MCP. Includes a setup skill for WSL2, a planning skill with auto-review, a tester skill with resume/abort semantics, and a structured bug-report format that hands off to a debugging agent.
Plugin Claude Code
Bundles 2 skills · 216 tokens together
Browser-level end-to-end testing before you open the PR: webapp-e2e for any web app, signalk-server-e2e for a SignalK server/plugin (spin-up, WS deltas, Freeboard) — both gate the change on a green Playwright run and attach it as PR evidence.
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: