playwright-setup

playwright-setup is a skill for Claude Code from FaisalNoman/playwright-skills. It costs 29 tokens per session (8,802 once invoked), scanned A, original, MIT.

A setup assistant for Playwright, a tool that tests web applications in a browser. It reads project files, asks about missing user journeys, proposes a test plan, and can create the test files and configuration after approval.

In plain words
What is it for?
Use it to turn documented or described app flows into end-to-end tests, such as checking sign-in, checkout, or other actions across a web application.
Why use it?
It removes the need to design a browser test suite and its setup from scratch. The approval step helps confirm what should be tested before files are changed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { test, expect } from '../fixtures'; // or '@playwright/test' if no auth fixture.

Part of the playwright-setup plugin — 1 skill shipped together

Good fit Use it to turn documented or described app flows into end-to-end tests, such as checking sign-in, checkout, or other actions across a web application.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/FaisalNoman/playwright-skills
agentmods
npx agentmods add skills/faisalnoman/playwright-skills/playwright-setup

Made for: Claude Code.

Or install playwright-setup, the plugin that ships this one along with the rest of its 1 skill.

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-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/faisalnoman/playwright-skills/playwright-setup.svg)](https://agentmods.dev/skills/faisalnoman/playwright-skills/playwright-setup)
Your own site
<a href="https://agentmods.dev/skills/faisalnoman/playwright-skills/playwright-setup"><img src="https://agentmods.dev/badge/skills/faisalnoman/playwright-skills/playwright-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,802 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 $0.00029 $0.08802
Opus 5 $0.00015 $0.04401
Sonnet 5 $0.00006 $0.01760
Haiku 4.5 $0.00003 $0.00880

Measured 7d ago against content hash c698fe52f6aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

playwright-setup 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 7d 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/playwright-setup/skills/playwright-setup/SKILL.md · 710 lines

How it starts

The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playwright Setup Generator

Goal

Produce a complete, ready-to-run Playwright E2E test suite for any project by:

  1. Mining existing docs and source code for user flows
  2. Interviewing the user to fill gaps and confirm scope
  3. Presenting a test plan for approval
  4. Writing all required files

Do NOT write any files until the user approves the plan.


Phase 0 — Mode Detection

Runs first, before any document scanning. Determine whether this project already has a Playwright suite:

  1. Check whether playwright.config.ts (or .js) exists at the project root, AND at least one *.spec.ts/*.spec.js file exists anywhere under the project.
  2. Config and spec files not BOTH present → fresh-generation mode. This covers three cases: neither exists, only playwright.config.ts exists (a mid-setup or config-only project), or only spec files exist with no config. Proceed to Phase 1 exactly as documented below — nothing about the existing flow changes in shape. If a playwright.config.ts already exists in this fresh-generation path, call this out explicitly in the Phase 3 plan ("Note: this will replace the existing playwright.config.ts") so the approval gate in Phase 3 (Do NOT write any files until approved) gives the user a chance to object before it's overwritten.
  3. Both found → ask the user, in ONE message, which of three things they want (use the AskUserQuestion tool, single-select):
    • Run the existing suite — re-verify what's already there through the fix loop; no new spec files are written. This routes straight to Phase 4.5 (Verify & Fix), skipping Phases 1-4 entirely. This is run-existing mode.
    • Add tests for new/uncovered areas — read the existing suite first, then scan/interview/plan/write only the gaps. This routes through Phases 1-4 with the incremental-mode behavior described in Phase 1 below, then Phase 4.5 as normal. This is add-tests mode.
    • Regenerate from scratch — falls through into fresh-generation mode above; nothing is discarded until Phase 3's approval gate, same as today.

Read the full file on GitHub · 710 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. 7d ago First seen · 710 lines · 29 tokens per session scan A c698fe52f6aa

Subscribe to this mod's changes

playwright-setup is a skill published in the GitHub repository FaisalNoman/playwright-skills (1 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 8,802 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 2026-08-31.

Related

Other skills, from other repositories

ui-aqa-flow

Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.

griddynamics/rosetta · 24 tokens

qa-knowledge

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

griddynamics/rosetta · 32 tokens

browser-check

Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.

jjanczur/tyran · 58 tokens

e2e

Add durable end-to-end tests for user/API-visible behavior. Detect or scaffold the E2E framework, write tests, run the app, and store evidence. Use for E2E, Playwright/Cypress, regression tests, or quality gates. Not exploratory QA.

heliohq/ship · 58 tokens

acceptance

A skill for writing, running, and repairing human-written acceptance checks stored in an `acceptance/ACCEPTANCE.md` file. Acceptance checks are executable tests of whether the finished result matches the requested outcome.

cryndoc/polisade-orchestrator · 129 tokens

fec-testing-strategy

A frontend testing strategy maps different risks to different checks, such as type checking, unit tests, component tests, integration tests, end-to-end tests, accessibility, security, and performance checks. It explains end-to-end testing as testing a complete user journey in a real browser.

bovinphang/frontend-craft · 106 tokens