18,217 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.
Plugin Claude Code
Bundles 44 commands, 11 agents · 1,641 tokens together
Specification-first AI harness: 11 structural gates, 11 Ouroboros commands, 11 agent personas, and 3-tier architecture enforcement. v2.1: Pair Mode (Navigator-Driver + independent test design + /review command).
ErkanBarin/playwright-agent-mcp-starter
Agent Claude Code
Explores a website, maps user journeys, generates Playwright tests, and detects missing coverage.
KieranHoward646/Adversarial-Testing-Skill
Skill Claude CodeCodex
Multi-AI adversarial testing workflow. Two AI agents collaborate: a Developer AI produces a structured product summary with test targets, then an Adversarial AI safely executes tests and auto-fixes issues. This skill should be used when the user wants to run adversarial testing on any software product, API, or feature…
Skill Claude CodeCodex needs its repo
A release check that tests a change, reports whether it passes, and can run a limited fix-and-retest cycle. A release is the act of making a software version available.
vuralserhat86/antigravity-agentic-skills
Skill Claude CodeCodex
Guide for conducting comprehensive accessibility audits of code to identify WCAG compliance issues and barriers to inclusive design. This skill should be used when reviewing accessibility, ARIA implementation, keyboard navigation, or screen reader compatibility.
Plugin Claude Code
Bundles 3 skills · 97 tokens together
LiveView introspection and accessibility testing skills for Phoenix. Use htmlsnapshot() to capture state at any point, axe-core for WCAG compliance, timeline analysis for debugging.
Skill Claude CodeCodex
Visual reasoning discipline for verifying UI and Three.js work with the SceneProof CLI. Use whenever a change can alter rendered output — components, styles, layout, SVG, canvas, scenes, cameras, lights, materials, animation — or whenever about to claim that something "looks right", "is visible", or "renders…
kenjudy/pdca-agentic-coding-framework
Skill Claude CodeCodex
Guides developers through a human-supervised PDCA framework for AI code generation. Applies analysis, TDD, validation, and retrospection. Activates for sessions requiring systematic quality control.
lizTheDeveloper/solarpunk_utopia
MCP server Claude CodeCodexCursor +2
Model Context Protocol servers for Playwright. Runs locally from the @executeautomation/playwright-mcp-server npm package. Needs 1 environment variable to run.
Skill Claude Code
This skill should be used when the user wants to run code quality checks (linting, formatting, type checking, tests) on the lazyclaude project. Use this skill when asked to "run quality gates", "check the code", "run tests", "lint the code", or verify code quality before committing.
goldbergyoni/test-coverage-mcp
MCP server Claude CodeCodexCursor +2
Analyze test coverage from LCOV files - makes AI agents coverage-aware without wasting tokens. Runs locally from the test-coverage-mcp npm package.
Agent Claude Code
Automated unit test generation for code with comprehensive coverage.
rawveg/skillsforge-marketplace
Skill Claude CodeCodex
Use proactively when you need to implement features or fix bugs using strict Test-Driven Development (TDD) methodology. This agent should be activated for any coding task that requires writing new functionality, refactoring existing code, or ensuring comprehensive test coverage, but should not be used for any…
Plugin Claude Code
Bundles 5 skills, 1 MCP server · 425 tokens together
Create, update, and fix Cypress tests. Connect to Cypress Cloud to see test results and use data to manage your test suite.
opendatahub-io/agent-eval-harness
Plugin Claude Code
Bundles 10 skills · 1,265 tokens together
Agent and skill evaluation harness with MLflow integration.
justfinethanku/cc_chrome_devtools_mcp_skill
Skill Claude CodeCodex
Comprehensive Chrome DevTools automation for performance testing, Core Web Vitals measurement (INP, LCP, CLS), network monitoring, accessibility validation, responsive testing, and browser automation. Uses Chrome DevTools Protocol via MCP to provide professional-grade web application testing, debugging, and analysis…
pixelfrog7523-vgfvu/pr-test-plan
Skill Claude CodeCodex
A tool that turns a pull request description or code-change summary into a practical test plan for reviewers and QA. It lists risks, test cases, setup needs, and regression checks.
Skill Codex
Run a strict repository-native Spec programming loop that keeps requirements, owning decisions, implementation, tests, and current documentation consistent in one bounded change. Use when explicitly invoked; when repository instructions require a Spec, RFC, ADR, proposal, design doc, or decision record for…
Plugin Claude Code
Bundles 1 skill, 3 commands · 245 tokens together
A plugin that provides AI-assisted software testing through an MCP server. It includes 22 testing tools, a bilingual QA knowledge layer, visual challenge solving, API security scanning, and a stream-analysis tool.
mlopscommunity/Coding-Agents-Conference-skills
Skill Claude CodeCodex
Use to comprehensively validate code quality and correctness in a separate context from the coding agent. Catches issues that biased validation would miss, ensures linting, tests, and assumptions are valid before merge.
MCP server Claude CodeCodexCursor +2
MCP server with WebdriverIO for browser and mobile app automation (iOS/Android via Appium). Runs locally from the @wdio/mcp npm package.
nedcodes-ok/cursorrules-collection
Cursor rule Cursor
Refactoring: systematic approach, extract/inline, guard clauses, early returns.
Plugin Claude Code
Bundles 14 skills · 839 tokens together
Spec-Trace-Verify (STV): Traced Development methodology. 7+1-section Vertical Trace (Section 0 Client Surface closes the frontend→dto→api→service→db round trip), 4-category Contract Tests, Decision Gate with Business-Meaning Override, and 4 STV Invariants. Bundle contract {tracepath, scenarioids} for targeted executi.
Cursor rule Cursor
Build standalone external agent binaries for the Entire CLI using E2E-first TDD.
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: