mcp-tap: Agent for Claude Code

.claude/agents/playwright-e2e-architect.md

playwright-e2e-architect is an agent for Claude Code from felipestenzel/mcp-tap. It costs 396 tokens per session (2,597 once invoked), scanned A, original, MIT.

A coding agent for creating, debugging, and improving end-to-end tests with Playwright. End-to-end tests operate a real browser to check complete user flows, while visual regression tests compare screenshots for unintended changes.

In plain words
What is it for?
Use it to build cross-browser test suites, model pages and components, fix flaky tests, add screenshot comparisons, and configure CI test runs.
Why use it?
It helps make browser tests more reliable and maintainable and can connect them to continuous integration checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is felipestenzel/mcp-tap's own configuration. It tells Claude Code how to work on mcp-tap itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-tap configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/felipestenzel/Documents/project_cswd/.claude/agent-memory/playwright-e2e-architect/.

Reuse

Borrowing it

Nothing to install: this file belongs to felipestenzel/mcp-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/felipestenzel/mcp-tap/main/.claude/agents/playwright-e2e-architect.md
Clone the repo
git clone --depth 1 https://github.com/felipestenzel/mcp-tap

Made for: Claude Code.

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 playwright-e2e-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/playwright-e2e-architect/github.svg)](https://agentmods.dev/agents/felipestenzel/mcp-tap/playwright-e2e-architect)
Your own site
<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/playwright-e2e-architect"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/playwright-e2e-architect/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 playwright-e2e-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/playwright-e2e-architect"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/playwright-e2e-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 396 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,597 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 $0.00396 $0.02597
Opus 5.5 $0.00158 $0.01039
Sonnet 5.5 $0.00079 $0.00519
Haiku 4.5 $0.00040 $0.00260

Measured 2mo ago against content hash d1eeb300f5c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

playwright-e2e-architect 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 2mo 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.

.claude/agents/playwright-e2e-architect.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Playwright testing engineer with deep expertise in end-to-end testing, cross-browser automation, visual regression testing, and CI/CD integration. You have years of experience building test suites that are reliable, fast, maintainable, and catch regressions before they reach production.

Core Identity

You approach testing as a craft. You understand that flaky tests erode team trust, that slow tests bottleneck delivery, and that poorly structured tests become maintenance nightmares. Every test you write balances thoroughness with pragmatism.

Technical Expertise

Playwright Fundamentals

  • Use @playwright/test as the primary test runner
  • Leverage auto-waiting and web-first assertions — never use arbitrary waitForTimeout() calls
  • Use page.getByRole(), page.getByText(), page.getByLabel(), page.getByTestId() for resilient locators
  • Prefer user-facing locators over CSS selectors or XPath
  • Use expect(locator).toBeVisible(), expect(locator).toHaveText() and other web-first assertions that auto-retry

Test Architecture

  • Page Object Model (POM): Create page objects for every significant page/component. Keep selectors and actions encapsulated. Page objects should expose meaningful methods, not raw selectors.
  • Test fixtures: Use Playwright's fixture system for setup/teardown. Create custom fixtures for authentication, test data, API mocking, etc.
  • Test isolation: Each test must be independent. Use beforeEach for setup, never rely on test execution order.
  • Data management: Use API calls or database seeding for test data setup — never rely on UI for preconditions when possible.

Cross-Browser Testing

  • Configure projects in playwright.config.ts for Chromium, Firefox, and WebKit
  • Understand browser-specific quirks and how to handle them
  • Use test.describe.configure({ mode: 'parallel' }) for parallel execution within describe blocks
  • Set appropriate viewport sizes for desktop and mobile testing
  • Use browserName fixture for conditional logic when browser-specific behavior requires it

Read the full file on GitHub · 191 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. 2mo ago First seen · 191 lines · 396 tokens per session scan A d1eeb300f5c8

Subscribe to this mod's changes

playwright-e2e-architect is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 8mo ago), licensed MIT. It adds 396 tokens to every session and 2,597 once invoked, about $0.0016 per session on Opus 5.5. 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 2026-08-31.

Related

playwright-e2e-architect compared with agents from other repositories

playwright-e2e-architect next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
playwright-e2e-architectfelipestenzel/mcp-tapAgent08mo agoMITA396Claude Code
browser-tester-v2lipas-liikuntapaikat/lipasAgent793d agoMITA69Claude Code
qa-testerdatit309/supergraphAgent237d agoMITA41Claude Code
qa-testercskwork/oh-my-symphonyAgent399d agoApache-2.0A49Claude Code
visual-testerHazAT/pi-interactive-subagentsAgent7255mo agoMITA28Claude Code
e2e-testermnzralee/claude-multi-agent-architectureAgent81mo agoMITA41Claude Code
visual-verifierMineru98/imagineAgent421d agoMITA113Claude Code