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 X-School-Academy/skill-pilot --skill init-playwrightgit clone --depth 1 https://github.com/X-School-Academy/skill-pilotWrote 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/x-school-academy/skill-pilot/init-playwright)<a href="https://agentmods.dev/skills/x-school-academy/skill-pilot/init-playwright"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/init-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/x-school-academy/skill-pilot/init-playwright"><img src="https://agentmods.dev/badge/skills/x-school-academy/skill-pilot/init-playwright.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.01452 |
| Opus 5.5 | $0.00008 | $0.00581 |
| Sonnet 5.5 | $0.00004 | $0.00290 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
init-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 16d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init Playwright CLI
Verify that playwright-cli, Chrome, and the Playwright MCP Bridge extension are ready
before any browser automation is attempted.
When to Use This Skill
- Any task that requires browser automation via playwright-cli
- playwright-cli may not be installed or Chrome may be missing
- The MCP Bridge extension may not be active
Your Roles in This Skill
- SysOps Engineer: Install and validate playwright-cli and Chrome
- QA Engineer: Confirm the browser extension bridge is active end-to-end
Role Communication
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role, and Role-XYZ if you have more roles}, I will {action description}
Other Agent Skills Required
keys-safe-guardplaywright-cli
Workflow Usage Requirement
When this skill is used in a workflow agent node:
- Output result as plain text. If the user asked to save it to a file, write it there.
- Include concise context in the output (what was checked, what is ready, and any blocking issue) so downstream agents can safely continue.
Instructions
Step 1: Check if playwright-cli is installed
playwright-cli --version
If the command is not found:
pnpm install -g @playwright/cli@latest
playwright-cli --version
Step 2: Test browser + extension bridge
playwright-cli open --extension --headed
Treat this as an initialization flow, not a blocking foreground command:
- Start it in a background process.
- Do not wait for the command to sit there until timeout.
- This init command is only for extension setup. Once setup is complete, normal browser automation should use direct commands such as
playwright-cli open --extension --headed.
Interpret the result as follows:
- If it returns quickly with
Browser \default` opened with pid ...`, the browser bridge is ready. - If it returns within about 10 seconds with
Extension connection timeout. Make sure the "Playwright MCP Bridge" extension is installed., go to Step 3 and instruct the user to install the Chrome extension. - If it stays open for more than about 10 seconds with no return, assume the browser is waiting for permission and is showing the extension token page. Go to Step 3 and instruct the user to copy-paste the
PLAYWRIGHT_MCP_EXTENSION_TOKENvalue. - If you get an error that Chrome is not installed, then go to Step 3 to install Google Chrome.
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.
- 16d ago First seen · 178 lines · 19 tokens per session scan A 7ed4a3c4bbc3
init-playwright is a skill published in the GitHub repository X-School-Academy/skill-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,452 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.