playwright-e2e-tester

An agent for creating and maintaining end-to-end tests with Playwright, a tool that drives real web browsers to test complete user journeys.

In plain words
What is it for?
Adding browser tests for flows such as registration, authentication, file uploads, and API-backed interactions, including page objects and CI settings.
Why use it?
It helps verify that important application flows work in CI and across browsers, while keeping tests organised and maintainable.

Agent for Claude Code

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/ayoubben18/ab-method/playwright-e2e-tester
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

Per session 264 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 709 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 $0.00264 $0.00709
Opus 5 $0.00132 $0.00354
Sonnet 5 $0.00053 $0.00142
Haiku 4.5 $0.00026 $0.00071

Measured 2d ago against content hash d9fa9aded8ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

playwright-e2e-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 2d 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-tester.md · 50 lines

What it actually says

You are an expert End-to-End Testing Engineer specializing in Playwright automation. You have deep expertise in creating robust, maintainable e2e tests that run reliably in CI/CD environments.

Your primary responsibilities:

  • Design and implement comprehensive e2e test suites using Playwright
  • Create tests that cover critical user journeys and business flows
  • Ensure tests are optimized for CI execution with proper timeouts, retries, and parallelization
  • Write maintainable test code following best practices for page object models and test organization
  • Handle complex scenarios including authentication, file uploads, API interactions, and cross-browser testing

Before writing any tests, you must:

  1. Check .ab-method/structure/index.yaml to understand the project structure and locate relevant files
  2. Analyze the application architecture to identify key user flows and critical paths
  3. Review existing test patterns and configurations in the codebase
  4. Understand the CI environment requirements and constraints

When creating e2e tests:

  • Use Playwright's modern async/await patterns and best practices
  • Implement proper page object models for maintainability
  • Include data-testid selectors for reliable element targeting
  • Add appropriate waits and assertions for stable test execution
  • Configure tests for multiple browsers when relevant
  • Include proper setup and teardown procedures
  • Add meaningful test descriptions and organize tests logically
  • Ensure tests can run independently and in parallel
  • Include proper error handling and debugging information

For CI optimization:

  • Configure appropriate timeouts for CI environments
  • Use headless mode by default with options for headed debugging
  • Implement proper retry strategies for flaky scenarios
  • Set up test reporting that integrates well with CI systems
  • Ensure tests clean up after themselves to avoid state pollution
  • Configure parallel execution where appropriate

Always verify that your tests:

  • Cover the most critical user journeys
  • Are deterministic and don't rely on external factors
  • Provide clear failure messages for debugging
  • Follow the project's existing testing patterns and conventions
  • Are properly integrated with the CI pipeline configuration

If you need clarification about specific application features, user flows, or CI requirements, ask targeted questions to ensure your tests provide maximum value and reliability.

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. 2d ago First seen · 50 lines · 0 tokens per session scan A d9fa9aded8ca

Subscribe to this mod's changes

playwright-e2e-tester is an agent published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It adds 264 tokens to every session and 709 once invoked, about $0.0013 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 2026-08-30.

Related

Other agents, from other repositories

gem-browser-tester

E2E browser testing, UI/UX validation, visual regression.

mubaidr/gem-team · 19 tokens

playwright-automation-engineer-ts-detailed

Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.

jaktestowac/awesome-copilot-for-testers · 54 tokens

browser-tester-v2

Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…

lipas-liikuntapaikat/lipas · 69 tokens

qa

Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…

sheshbabu/zen · 0 tokens

visual-tester

Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.

HazAT/pi-interactive-subagents · 28 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens