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.
Skill Claude CodeCodex
A project-local verification guide that teaches an agent how to start and operate a real application like a user. It can cover web and desktop interfaces, command-line programs, services, libraries, or mobile applications, while recording evidence of the results.
edwardyap90/counterfactual-engineering-skill
Skill Codex
Use when a code change has multiple plausible implementation paths, high regression risk, uncertain root cause, or unclear tradeoffs. Creates isolated candidate implementations, runs comparable verification across each candidate, compares evidence, and applies the best proven approach while preserving user changes.
Skill Claude CodeCodex
Unleash a mob of AI virtual users (impatient shoppers, confused seniors, keyboard-only users, chaos monkeys) on a website to stress-test its UX and hunt bugs. Use when the user asks to "crowd test", "mob test", "send virtual users", or wants persona-based UX/QA feedback on a URL before launch.
Cursor rule Cursor
A test-configuration rule for JavaScript and Rust projects. It places JavaScript tests in tests/ and controls Vitest, Stryker, coverage, mutation testing, and Rust mutation-testing configuration.
MCP server Claude CodeCodexCursor +2
Quality gates for AI-generated code -- TDD enforcement, secret scanning, and audit trails for coding agents. Runs locally from the tribunal Python package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 90 tokens together
MaxoPerf load & browser performance testing — bundles the remote MaxoPerf MCP server connector and the maxoperf agent skill (turn "I have an app" into a real, running test). Skill also stands alone at github.com/MaxoPerf/agent-skill.
MCP server Claude CodeCodexCursor +2
MCP server for James Bloom MockServer - create expectations, verify requests, and manage mock state. Runs locally from the mockserver-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Generate placeholder text — paragraphs, sentences, words. x402 micropayment. Remote server at lorem-ipsum.api.klymax402.com.
Plugin Claude Code
Agent-native API regression verification. Snapshot a known-good baseline, then let the agent check its own edits for broken contracts (removed fields, status changes, failing tests) before reporting done. Deterministic — no LLM judging, no cloud.
Br0ski777/regex-generator-x402
MCP server Claude CodeCodexCursor +2
Test, validate and explain regular expressions with match highlighting. x402 micropayment. Remote server at regex-generator.api.klymax402.com.
ModelBound/modelbound-mcp-server
Skill Claude CodeCodex
Smoke-test skill for ModelBound CI — triggered when validating GitHub Actions skill checks.
MCP server Claude CodeCodexCursor +2
Provar MCP: AI-powered Salesforce test automation. Generate, validate, migrate, and run tests. Runs locally from the @provartesting/provardx-cli npm package.
MCP server Claude CodeCodexCursor +2
Regression-testing CI gate for self-edited Claude Agent Skills (SKILL.md, MEMORY.md): golden-transcript record/replay against a skill's own declared and inferred capability surface, zero hosted infrastructure. Runs locally from the evolveguard-cli Python package.
SemanticDataCharter/sdcvalidator
MCP server Claude CodeCodexCursor +2
SDC4 structural validator with ExceptionalValue recovery — thin wrapper over xmlschema. Runs locally from the sdcvalidator Python package.
MCP server Claude CodeCodexCursor +2
MCP server for managing Apidog test cases, scenarios, suites, and test data. Runs locally from the @acabala/apidog-tests-mcp npm package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for Blip disposable email — create inboxes, receive emails, extract OTP codes. Runs locally from the @useblip/email npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Catch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI. Runs locally from the evidrift npm package.
Plugin Claude Code
Bundles 33 skills, 1 MCP server · 2,497 tokens together
Author verifiable eval records through a draft → review → revise → submit loop with server-enforced graders; compile to JSONL/CSV/Inspect/lm-eval via MCP. STDIO or Streamable HTTP.
Skill Claude CodeCodex
Generate realistic synthetic test data — relational JSON/CSV/SQL fixtures, seed data, and QA datasets — via the MockHero MCP server or REST API. Use when a task needs mock users, orders, invoices, or multi-table seed data with valid foreign keys instead of hand-writing fixtures or faker scripts. Includes a free…
MCP server Claude CodeCodexCursor +2
Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI. Runs locally from the edgegate-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Check whether an AI answer is grounded in its context — deterministic, no LLM judge. Runs locally from the @pharmatools/opengate-mcp npm package.
MCP server Claude CodeCodexCursor +2
AI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat. Remote server at prodpoke.com.
threadlinqs-cmd/Threadlinqs-Security-Detection-MCP
Cursor rule Cursor
The tests: section MUST have valid URLs, NOT placeholder descriptions.
MCP server Claude CodeCodexCursor +2
Your agent built the page. Simulated buyers test it, and Mimiq calls which version to ship. Remote server at mcp.mimiqai.com.
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: