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 skills add vinnie357/claude-skills --skill playwrightgit clone --depth 1 https://github.com/vinnie357/claude-skillsWrote 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.
[](https://agentmods.dev/skills/vinnie357/claude-skills/playwright)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/playwright"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/playwright/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.
<a href="https://agentmods.dev/skills/vinnie357/claude-skills/playwright"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/playwright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 19 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 20 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 89 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 225 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.02035 |
| Opus 5 | $0.00026 | $0.01018 |
| Sonnet 5 | $0.00010 | $0.00407 |
| Haiku 4.5 | $0.00005 | $0.00203 |
Grade A, and why
playwright scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Navigate to a URL and extract content when curl or fetch would be blocked: How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright MCP
The Playwright MCP server gives Claude Code agents direct browser control through 50+ tools that operate on the accessibility tree rather than screenshots. This enables fast, structured web interaction — navigating pages, clicking elements, filling forms, extracting content, and taking screenshots — without requiring vision models.
Installation
Claude Code (recommended)
# Default: bunx (preferred)
claude mcp add playwright -- bunx @playwright/mcp@latest
# Fallback: npx
claude mcp add playwright -- npx @playwright/mcp@latest
Verify the MCP server is connected by running /mcp in a Claude Code session.
Runtime Requirement
Bun or Node.js 18+ must be available. Add to your project or global mise.toml:
[tools]
bun = "latest"
See templates/mise.toml for the full template.
Configuration
Global (all sessions)
Add to ~/.claude.json to make Playwright available in every Claude Code session:
{
"mcpServers": {
"playwright": {
"command": "bunx",
"args": ["@playwright/mcp@latest"]
}
}
}
Per-Project
Add to .mcp.json in the project root for project-scoped configuration:
{
"mcpServers": {
"playwright": {
"command": "bunx",
"args": ["@playwright/mcp@latest"]
}
}
}
Configuration Flags
Pass flags after the package name in the args array or on the CLI:
claude mcp add playwright -- bunx @playwright/mcp@latest --headless --browser chromium
| Flag | Default | Description |
|---|---|---|
--browser |
chrome |
Browser engine: chrome, firefox, webkit, msedge |
--headless |
off (headed) | Run without visible browser window |
--allowed-origins |
none | Semicolon-separated trusted origins |
--blocked-origins |
none | Semicolon-separated blocked origins |
--proxy-server |
none | HTTP proxy (e.g., http://proxy:3128) |
--viewport-size |
browser default | Window size (e.g., 1280x720) |
--device |
none | Emulate device (e.g., iPhone 15) |
--timeout-action |
5000 |
Action timeout in ms |
--timeout-navigation |
60000 |
Navigation timeout in ms |
--user-data-dir |
none | Persistent browser profile path |
--isolated |
off | Use in-memory profile only |
--storage-state |
none | Load saved session state (cookies, localStorage) |
--caps |
core only | Enable optional capabilities (see below) |
--config |
none | Path to configuration file |
--cdp-endpoint |
none | Connect to existing Chrome DevTools Protocol |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 239 lines · 51 tokens per session scan A 243c0b72b8ce
playwright is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 2,035 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…