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 joaquimscosta/arkhe-claude-plugins --skill playwright-cligit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/playwright-cli)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/playwright-cli"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/playwright-cli/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/joaquimscosta/arkhe-claude-plugins/playwright-cli"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/playwright-cli.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 | $0.00112 | $0.01548 |
| Opus 5.5 | $0.00045 | $0.00619 |
| Sonnet 5.5 | $0.00022 | $0.00310 |
| Haiku 4.5 | $0.00011 | $0.00155 |
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 yesterday.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright CLI
Automate browsers through shell commands via the Bash tool.
Core Workflow
Every interaction follows this pattern:
- Open a page:
playwright-cli open <url> - Snapshot to discover elements:
playwright-cli snapshot - Interact using refs from the snapshot:
playwright-cli click <ref> - Verify the result:
playwright-cli screenshotorplaywright-cli snapshot
Always run snapshot before interacting — element refs come exclusively from
snapshot output and become stale after navigation.
Command Reference
Navigation
| Command | Description |
|---|---|
open <url> |
Open URL in new page |
goto <url> |
Navigate current page |
go-back / go-forward |
Browser back/forward |
reload |
Reload current page |
close |
Close the browser |
Interaction
| Command | Description |
|---|---|
click <ref> |
Click an element |
dblclick <ref> |
Double-click an element |
fill <ref> <text> |
Clear field, then type text |
type <text> |
Type into focused element (appends) |
check <ref> / uncheck <ref> |
Toggle checkbox |
select <ref> <values> |
Select dropdown option(s) |
hover <ref> |
Hover over element |
drag <start> <end> |
Drag between elements |
upload <ref> <paths> |
Upload file(s) to file input |
eval "<js>" |
Evaluate JavaScript on page |
eval "<js>" <ref> |
Evaluate JavaScript on element |
dialog-accept [text] |
Accept dialog (optional prompt text) |
dialog-dismiss |
Dismiss dialog |
resize <w> <h> |
Resize browser window |
Output
| Command | Description |
|---|---|
screenshot [ref] [--filename=f] |
Capture PNG screenshot (page or element) |
snapshot [--filename=f] |
Accessibility tree — structured, token-efficient |
pdf [--filename=f] |
Generate PDF of the page |
Important:
--filenameresolves relative to the working directory, NOToutputDir. When using--filename, always prepend the project'soutputDirvalue (check.playwright/cli.config.json; defaults to.playwright-cli). Example:playwright-cli screenshot --filename=<outputDir>/my-screenshot.png
What ships with it
9 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.
- yesterday First seen · 150 lines · 112 tokens per session scan A 54bc8ec510a5
playwright-cli is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,548 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.
playwright-cursor-rules
Expert guidance for Playwright end-to-end testing with TypeScript and JavaScript best practices.
playwright
Playwright end-to-end testing best practices for web applications, covering test design, locator strategies, and assertion patterns.