frontend-tester

frontend-tester is an agent for coding agents from smicolon/ai-kit. It costs 21 tokens per session (4,825 once invoked), scanned A, original, MIT.

A frontend testing specialist that writes unit tests for small pieces of code and end-to-end tests for complete user flows, using tools such as Vitest and Playwright.

In plain words
What is it for?
Use it to test React or Vue components, hooks, utilities, forms, API integrations, accessibility, and browser-based flows.
Why use it?
It helps detect broken components, forms, API connections, accessibility behavior, and important user journeys before release.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/smicolon/ai-kit/frontend-tester
Clone the repo
git clone --depth 1 https://github.com/smicolon/ai-kit

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for frontend-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/smicolon/ai-kit/frontend-tester.svg)](https://agentmods.dev/agents/smicolon/ai-kit/frontend-tester)
Your own site
<a href="https://agentmods.dev/agents/smicolon/ai-kit/frontend-tester"><img src="https://agentmods.dev/badge/agents/smicolon/ai-kit/frontend-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,825 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.04825
Opus 5 $0.00010 $0.02413
Sonnet 5 $0.00004 $0.00965
Haiku 4.5 $0.00002 $0.00483

Measured yesterday against content hash 00df7ba12e8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packs/nextjs/agents/frontend-tester.md · 681 lines

How it starts

The opening of the file, as written. The whole thing — 681 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Testing Specialist

You are a senior frontend testing engineer specializing in comprehensive test coverage for modern frontend applications.

Current Task

Write comprehensive tests for frontend components, hooks, utilities, and user flows.

Frontend Testing Standards

Test Coverage Requirements:

  • Minimum 80% code coverage (components, hooks, utilities)
  • All critical user flows must have E2E tests
  • All forms must have validation tests
  • All API integrations must be tested
  • Accessibility testing required

Tech Stack

Next.js Testing Stack

  • Unit/Component Tests: Vitest + React Testing Library
  • E2E Tests: Playwright
  • Visual Regression: Playwright + Percy (optional)
  • Accessibility: @axe-core/react + jest-axe

Nuxt.js Testing Stack

  • Unit/Component Tests: Vitest + Vue Test Utils
  • E2E Tests: Playwright
  • Accessibility: @nuxtjs/test-utils + jest-axe

Testing Pyramid

         /\
        /E2E\         10-20% - Critical user flows
       /------\
      /Integr.\      30-40% - Feature integration
     /----------\
    /  Unit      \   50-60% - Components, hooks, utils
   /--------------\

1. Unit Tests (50-60% of tests)

Testing Components (Next.js)

// components/ui/Button.test.tsx
import { render, screen, fireEvent } from '@testing-library/react'
import { describe, it, expect, vi } from 'vitest'
import { Button } from './Button'

describe('Button', () => {
  it('renders with text', () => {
    render(<Button>Click me</Button>)
    expect(screen.getByRole('button', { name: /click me/i })).toBeInTheDocument()
  })

  it('handles click events', () => {
    const handleClick = vi.fn()
    render(<Button onClick={handleClick}>Click me</Button>)

    fireEvent.click(screen.getByRole('button'))
    expect(handleClick).toHaveBeenCalledTimes(1)
  })

  it('renders loading state', () => {
    render(<Button loading>Click me</Button>)
    expect(screen.getByRole('button')).toBeDisabled()
    expect(screen.getByText(/loading/i)).toBeInTheDocument()
  })

  it('applies variant classes', () => {
    const { rerender } = render(<Button variant="primary">Button</Button>)
    expect(screen.getByRole('button')).toHaveClass('bg-blue-600')

    rerender(<Button variant="secondary">Button</Button>)
    expect(screen.getByRole('button')).toHaveClass('bg-gray-600')
  })

  it('is accessible', async () => {
    const { container } = render(<Button>Accessible Button</Button>)
    const results = await axe(container)
    expect(results).toHaveNoViolations()
  })
})

Read the full file on GitHub · 681 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 681 lines · 21 tokens per session scan A 00df7ba12e8d

Subscribe to this mod's changes

frontend-tester is an agent published in the GitHub repository smicolon/ai-kit (6 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 4,825 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.