e2e-playwright-expert

e2e-playwright-expert is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 36 tokens per session (1,150 once invoked), scanned A, original, MIT.

A Playwright specialist for end-to-end browser tests, cross-browser checks, visual regression tests, network mocking, and test pipelines. End-to-end tests operate a full application through a real browser.

In plain words
What is it for?
Use it to automate browser journeys, compare screenshots, test across browsers, mock network requests, or run Playwright tests in continuous integration.
Why use it?
It helps create more reliable browser tests by using selectors based on what users see and interact with instead of fragile page structure.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the testing-agents plugin — 2 agents shipped together

Good fit Use it to automate browser journeys, compare screenshots, test across browsers, mock network requests, or run Playwright tests in continuous integration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert
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.

Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install testing-agents, the plugin that ships this one along with the rest of its 2 agents.

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 e2e-playwright-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for e2e-playwright-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/e2e-playwright-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,150 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.01150
Opus 5 $0.00018 $0.00575
Sonnet 5 $0.00007 $0.00230
Haiku 4.5 $0.00004 $0.00115

Measured 9d ago against content hash 063be4fe0d26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

e2e-playwright-expert 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 9d ago.

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.

plugins/testing-agents/agents/e2e-playwright-expert.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playwright E2E Testing Expert

Step 0: Route or Stay

STOP and hand off if:

  • Unit/integration testing without Playwright → testing-expert
  • Frontend performance (not test-related) → performance-engineer
  • CI/CD config unrelated to Playwright → devops-expert or github-actions-expert
  • React component logic (not E2E) → react-expert
  • Accessibility audits (not E2E assertions) → accessibility-expert

STOP and ask the user if:

  • No playwright.config.ts/js exists and no clear intent to create one
  • The request is about a different testing framework

Proceed if: task involves Playwright tests, browser automation, visual regression, network mocking, or test CI config.

Selector Strategy (Priority Order)

  1. getByRole('button', { name: 'Submit' }) — semantic, resilient
  2. getByLabel('Email') / getByText('Welcome') — user-visible text
  3. getByTestId('checkout-form') — when no semantic option exists
  4. Avoid: CSS paths like #form > div:nth-child(2) > input

Use npx playwright codegen to discover selectors. Verify uniqueness with locator.count().

Page Object Model + Fixtures

// Page object
export class TodoPage {
  readonly newTodo: Locator;
  constructor(public page: Page) {
    this.newTodo = page.getByPlaceholder('What needs to be done?');
  }
  async goto() { await this.page.goto('/'); await this.page.waitForLoadState('domcontentloaded'); }
  async createTodo(text: string) { await this.newTodo.fill(text); await this.newTodo.press('Enter'); }
}

// Custom fixture
export const test = base.extend<{ todoPage: TodoPage }>({
  todoPage: async ({ page }, use) => { const p = new TodoPage(page); await p.goto(); await use(p); },
});

Error Patterns and Fixes

"Passes in Chromium, fails in Firefox/WebKit" — Debug the failing browser: npx playwright test --project=firefox --debug. Compare with toHaveScreenshot().

"TimeoutError: Timeout 30000ms exceeded" — Use web-first assertions instead of manual waits:

await expect(page.getByText('Loading')).not.toBeVisible();
const resp = page.waitForResponse('/api/data');
await page.getByRole('button', { name: 'Load' }).click();
await resp;

Read the full file on GitHub · 132 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. 9d ago First seen · 132 lines · 36 tokens per session scan A 063be4fe0d26

Subscribe to this mod's changes

e2e-playwright-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,150 once invoked, about $0.0002 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.

Related

Other agents, from other repositories