playwright-cli

playwright-cli is a skill for Claude Code, Codex from app-builders-club/design-builder. It costs 98 tokens per session (3,315 once invoked), scanned A, a copy of playwright-cli, MIT.

A command-line tool for controlling a web browser through Playwright, a browser-testing framework.

In plain words
What is it for?
Taking desktop and mobile screenshots, inspecting rendered page structure and styles, reviewing live pages, and running browser interactions.
Why use it?
It removes repetitive manual browser work when checking how a site looks or behaves.

Skill for Claude CodeCodex

Part of the design-builder plugin — 9 skills, 7 commands, 1 agent, 2 MCP servers shipped together

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 skills/app-builders-club/design-builder/playwright-cli
Any agent
npx skills add app-builders-club/design-builder --skill playwright-cli
Clone the repo
git clone --depth 1 https://github.com/app-builders-club/design-builder

Made for: Claude Code, Codex.

Or install design-builder, the plugin that ships this one along with the rest of its 9 skills, 7 commands, 1 agent, 2 MCP servers.

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-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/app-builders-club/design-builder/playwright-cli.svg)](https://agentmods.dev/skills/app-builders-club/design-builder/playwright-cli)
Your own site
<a href="https://agentmods.dev/skills/app-builders-club/design-builder/playwright-cli"><img src="https://agentmods.dev/badge/skills/app-builders-club/design-builder/playwright-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 80% copy Near-identical to another mod 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 $0.00098 $0.03315
Opus 5 $0.00049 $0.01657
Sonnet 5 $0.00020 $0.00663
Haiku 4.5 $0.00010 $0.00331

Measured 5d ago against content hash c881f575ec68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

playwright-cli 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 5d 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.

Origin

This is a copy

80% identical to playwright-cli — 109 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/playwright-cli/SKILL.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with playwright-cli

How design-builder uses this skill

This skill is consumed by three call sites. In each one, playwright-cli is the runtime; the calling command/agent owns the policy.

1. agents/design-auditor.md — visual acquisition for /review

When /review resolves to a web target with a URL (running dev server or live site), the auditor captures screenshots BEFORE running visual-mode dimensions:

# pick session name = audit so the browser isolates from other plugin work
playwright-cli -s=audit open <url> --browser=chrome

# desktop capture
playwright-cli -s=audit resize 1440 900
playwright-cli -s=audit screenshot --filename=design/screenshots/<slug>.1440x900.png

# mobile capture
playwright-cli -s=audit resize 375 812
playwright-cli -s=audit screenshot --filename=design/screenshots/<slug>.375x812.png

playwright-cli -s=audit close

<slug> is the route without leading / (/index, /pricingpricing). The captured paths feed the auditor's screenshot_paths input — visual mode then runs as if the user uploaded screenshots manually.

2. commands/improve.md — live inspiration_pages capture for --restructure

When /improve --restructure selects an inspiration_pages anchor and the record has a url, capture the live page so the rebuild plan can reference real pixels (not just metadata):

playwright-cli -s=inspo open <inspiration_page.url> --browser=chrome
playwright-cli -s=inspo resize 1440 900
playwright-cli -s=inspo screenshot --filename=design/.cache/inspiration/<page_id>.png
playwright-cli -s=inspo close

Cache only — design/.cache/ is gitignored. Reuse the cached PNG on subsequent invocations with the same page_id.

3. commands/review.md — URL input mode

/review accepts a URL (or comma-separated URL list) as its argument. The command resolves the URLs, hands them to the auditor as urls, and the auditor runs the capture sequence above. No screenshots in design/screenshots/ are required up-front — they get populated as a side-effect.

Read the full file on GitHub · 445 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. 5d ago First seen · 445 lines · 98 tokens per session scan A c881f575ec68

Subscribe to this mod's changes

playwright-cli is a skill published in the GitHub repository app-builders-club/design-builder (4 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 3,315 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to playwright-cli, differing in 109 lines, and is treated as a copy.

Related

Other skills, from other repositories

broken-link-checker

Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".

nowork-studio/notfair-plugin · 72 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens

preview-screens

Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.

microsoft/power-platform-skills · 41 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

document-hunter

Searches and retrieves documents from free public sources using automated browser navigation. Use when research needs primary source documents like court filings, government reports, or public records.

bitwize-music-studio/claude-ai-music-skills · 36 tokens

cloudflare-browser-rendering

Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.

secondsky/claude-skills · 37 tokens