20,069 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 8 skills, 1 MCP server · 226 tokens together
iceDQ data quality operations for Claude: author Validation/Duplicate/Pushdown/Recon/Checksum rules, run rules and workflows and read exception reports, and build schedules — bundled with the iceDQ MCP server so tools and guided skills install together.
Skill Claude Code
Automate browser interactions, test web pages and work with Playwright tests.
starmania7/local-coder-mcp-agent
Skill Claude CodeCodex
Manage coding work through the local-coder MCP worker: decompose tasks, send constrained implementation prompts, review worker changes, and iterate until tests and acceptance criteria pass.
browserstack/browserstack-cursor-plugin
Plugin Cursor
Bundles 3 skills, 1 agent · 155 tokens together
BrowserStack integration for Cursor. Test websites and mobile apps on real devices, run automated tests, debug failures, and manage test cases—all using natural language.
Skill Claude CodeCodex
Build and audit accessible web, mobile web, Android, and iOS interfaces. Covers HTML, CSS, JavaScript, TypeScript, React, Angular, AJAX/SPA, Kotlin/Jetpack Compose, and SwiftUI/UIKit; WCAG 2.2 AA, WCAG2Mobile/WCAG2ICT guidance, careful ARIA and native semantics, focus, touch, screen readers, AI-agent response…
Skill Claude CodeCodex
Build, inspect, drive, and verify Apple simulator apps with XCAutokit, including coordinated simulator work by host-owned agents.
SunrisesIllNeverSee/agent-universe
Skill Claude CodeCodex
The integration gate proven on AQUA M03: builder → independent falsifier → bounded corrections → re-verifier sign-off. Use for any lane that claims an integration, migration, projection, import, auth, or multi-party boundary works. The falsifier never trusts the builder's harness; it invents new counterexamples…
Skill Claude CodeCodex
Use when the question is about a codebase, not a file — locate a symbol, who calls it, what breaks if I change it, review this diff, which tests to run, repo-level flows/risk.
Skill Claude CodeCodex
Set up bounded metric experiments when explicitly requested.
Cursor rule Claude CodeCursor
Base rules for this repo, mirrored from CLAUDE.md (Claude Code's supervisor file).
AbdulDevHub/Agent-Skills-Factory
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude Code
Change a contract of a mneme plugin skill — a rule in plugin/skills//SKILL.md and its replicas in sibling skills — or a check in scripts/check-skill-handoff.mjs, and prove by mutations that the guard goes red on the break. Use when a skill rule is added, reworded or moved, when a replica of a rule is touched, or when…
Qualflare/qualflare-claude-code
Plugin Claude Code
Bundles 7 skills, 1 command, 1 hook · 527 tokens together
Test management & reporting for Claude Code via Qualflare CLI.
MCP server Claude CodeCodexCursor +2
MCP server for crowd-test: unleash a mob of AI virtual users on your website from Claude Desktop, Claude Code, Cursor, or any MCP client. Runs locally from the crowd-test-mcp Python package.
MCP server Claude CodeCodexCursor +2
Test whether AI agents retain critical instructions as conversations grow. Runs locally from the rule-drift npm package.
Plugin Claude Code
Bundles 5 skills · 149 tokens together
Declarative Action Architecture (DAA) — a strict three-layer separation pattern for E2E automation testing. Provides skills for generating, reviewing, and architecting DAA-compliant test code.
MCP server Claude CodeCodexCursor +2
Secure local workspace connector for LaunchLint mobile app checks. Runs locally from the @launchlint/mcp npm package.
Skill Claude CodeCodex
Professional Android automation agent for device interaction, UI testing, and app management. Use for: (1) interacting with Android apps, (2) filling inputs, (3) structural UI inspection via XML/axtree, (4) complex multi-step mobile tasks. Prefer XML/axtree over screenshots — images are expensive tokens.
phoenice-labs/Universal-Test-Framework
Agent Claude Code
Expert Test Architect agent. Generates comprehensive, requirements-driven tests that are fully traceable and strictly follow the 8-section test contract. Works across all languages (Python, TypeScript, JavaScript, Java, Go, C++). Invokes the Universal Test Framework MCP server for all test generation.
Plugin Claude Code
Bundles 1 skill, 4 hooks · 49 tokens together
Detects source changes and guides you to the right test types before you move on — so test planning never slips through the cracks. Ships hooks that watch edits, a /tdd skill, and a language-agnostic map of nine test types.
Skill Claude CodeCodex
Rules for AI-assisted infrastructure testing via mcp-tester-helper MCP server. Activate when the user asks to make HTTP requests to services (REST API), search logs (OpenSearch), or run SQL queries against databases (PostgreSQL) across different stands (environments).
MCP server Claude CodeCodexCursor +2
Playwright integration for ModelContext. Runs locally from the playwright-mcp npm package.
Plugin Claude Code
Bundles 5 commands, 1 MCP server · 74 tokens together
QA brain for your AI coding agent — churn, coverage, and test-mapping signals as MCP tools + slash commands.
secchanu/discord-developer-mcp
MCP server Claude CodeCodexCursor +2
MCP server for verifying Discord bot behavior through a test bot account. Runs locally from the discord-developer-mcp npm package.
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: