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.
npx agentmods add skills/stuartshields/claude-setup/playwrightnpx skills add stuartshields/claude-setup --skill playwrightgit clone --depth 1 https://github.com/stuartshields/claude-setupWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.01114 |
| Opus 5 | $0.00013 | $0.00557 |
| Sonnet 5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
playwright 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: playwright
When to Use
Use this skill for browser automation tasks: visual testing, page interaction, form filling, screenshot comparison, and debugging rendered pages. Invoke with /playwright [URL] to navigate to a specific page, or /playwright to start without a URL.
Use $ARGUMENTS as the URL to navigate to. If empty, ask the user what page to work with.
Do NOT use this skill for writing test files or test code. This is for live browser interaction via MCP tools.
Snapshot First, Screenshot Second
The Playwright MCP provides two ways to see page state. Use the right one:
browser_snapshot- Returns the accessibility tree. Use this for planning actions, finding interactive elements, and understanding page structure. Fast, deterministic, token-efficient. Always start here.browser_take_screenshot- Returns a visual image. Use this for visual verification, layout debugging, comparing against Figma designs, and documentation. You cannot perform actions based on screenshots alone. Usebrowser_snapshotfor that.
Default workflow:
browser_snapshotto understand what's on the page- Perform actions (
browser_click,browser_type,browser_fill_form, etc.) browser_snapshotagain to verify the action workedbrowser_take_screenshotonly when visual verification is needed
Visual Verification with Figma
When comparing implementation against Figma designs:
- Call
get_screenshotfrom the Figma MCP for the design reference - Navigate to the implementation with
browser_navigate - Match viewport dimensions to the Figma frame with
browser_resize - Call
browser_take_screenshotto capture the current state - Compare the two images. If they don't match, identify the specific deltas and fix them
- Repeat until visual parity is achieved
Don't declare "looks good" after a single screenshot. Compare carefully. If you can't tell, use browser_evaluate to measure computed styles and compare against the Figma spec values.
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.
- 2d ago First seen · 81 lines · 26 tokens per session scan A 0dc235cce5aa
playwright is a skill published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,114 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.
Other skills, from other repositories
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser…
browser-automation
../../../engineering/skills/browser-automation/SKILL.md.
playwright-skill
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from…
playwright-core
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, assertions, fixtures, network mocking, auth flows, debugging, and framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.
playwright-pom
Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.
playwright-migration
Step-by-step migration guides for moving to Playwright from Cypress or Selenium/WebDriver — command mappings, architecture changes, and incremental adoption strategies.