# OpenCLI Agent Pack: Playwright

Use this when an AI agent needs to work with `playwright`.

## What this CLI is for
The official CLI from Microsoft. Browser testing, automation, and headless scripts from the terminal.

Best for: browser testing, automation, and headless scripts from the terminal.

## Agent readiness
Usable with guardrails (50/100)
- Supports non-interactive/scripted use.
- Works well in CI or repeatable automation.

## Install
```sh
npm i -D @playwright/test
```

## Verify before real work
```sh
playwright --version
```
Expected signal: playwright responds locally and is ready for the first real command.

## Safe starting commands
```sh
playwright --version
```

```sh
npx playwright test
```

## Guardrails for agents
- Prefer small commands and ask the agent to summarize plain text output.
- Start read-only, then ask before mutations.

## Suggested agent instruction
You may use Playwright (`playwright`) for browser testing, automation, and headless scripts from the terminal.. First install it if missing, then run the verify command. Start with read-only or inspection commands. Summarize what you found before changing anything. Ask for confirmation before commands that mutate remote state, spend money, deploy, delete data, merge code, or expose secrets.

Source: OpenCLI