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/craftos-dev/craftbot/playwright-mcpnpx skills add CraftOS-dev/CraftBot --skill playwright-mcpgit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/craftos-dev/craftbot/playwright-mcp)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/playwright-mcp"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/playwright-mcp.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00035 | $0.01059 |
| Opus 5 | $0.00017 | $0.00530 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
playwright-mcp 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright MCP Skill
Browser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically.
Installation
npm install -g @playwright/mcp
# Or
npx @playwright/mcp
Install browsers (first time):
npx playwright install chromium
Quick Start
Start MCP Server (STDIO mode)
npx @playwright/mcp
Start with Options
# Headless mode
npx @playwright/mcp --headless
# Specific browser
npx @playwright/mcp --browser firefox
# With viewport
npx @playwright/mcp --viewport-size 1280x720
# Ignore HTTPS errors
npx @playwright/mcp --ignore-https-errors
Common Use Cases
1. Navigate and Extract Data
# MCP tools available:
# - browser_navigate: Open URL
# - browser_click: Click element
# - browser_type: Type text
# - browser_select_option: Select dropdown
# - browser_get_text: Extract text content
# - browser_evaluate: Run JavaScript
# - browser_snapshot: Get page structure
# - browser_close: Close browser
2. Form Interaction
1. browser_navigate to form URL
2. browser_type into input fields
3. browser_click to submit
4. browser_get_text to verify result
3. Data Extraction
1. browser_navigate to page
2. browser_evaluate to run extraction script
3. Parse returned JSON data
MCP Tools Reference
| Tool | Description |
|---|---|
browser_navigate |
Navigate to URL |
browser_click |
Click element by selector |
browser_type |
Type text into input |
browser_select_option |
Select dropdown option |
browser_get_text |
Get text content |
browser_evaluate |
Execute JavaScript |
browser_snapshot |
Get accessible page snapshot |
browser_close |
Close browser context |
browser_choose_file |
Upload file |
browser_press |
Press keyboard key |
Configuration Options
# Security
--allowed-hosts example.com,api.example.com
--blocked-origins malicious.com
--ignore-https-errors
# Browser settings
--browser chromium|firefox|webkit
--headless
--viewport-size 1920x1080
--user-agent "Custom Agent"
# Timeouts
--timeout-action 10000 # Action timeout (ms)
--timeout-navigation 30000 # Navigation timeout (ms)
# Output
--output-dir ./playwright-output
--save-trace
--save-video 1280x720
What ships with it
3 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.
- 2d ago First seen · 166 lines · 35 tokens per session scan A 179b2b6335aa
playwright-mcp is a skill published in the GitHub repository CraftOS-dev/CraftBot (378 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,059 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
agent-smoke-test
Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
browser-subagent-task-bounding
How to constrain browser subagents with deterministic stop conditions, step ceilings (max 5-8 steps), and selector-targeted DOM extraction to prevent runaway token costs and infinite navigation loops.
website-change-monitor
Watch important pages and notify when content changes.