playwright-cli

A command-line tool for controlling a web browser. It can open pages, click and fill controls, take screenshots, test websites, and extract page data.

In plain words
What is it for?
Use it for web application tests, form filling, screenshots, website navigation, data extraction, login-state reuse, and browser debugging.
Why use it?
It lets you automate browser tasks without writing a separate script. Snapshots show which page elements can be used, reducing errors when interacting with a page.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/zebbern/claude-code-guide/playwright-cli
Any agent
npx skills add zebbern/claude-code-guide --skill playwright-cli
Clone the repo
git clone --depth 1 https://github.com/zebbern/claude-code-guide

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,985 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.01985
Opus 5 $0.00034 $0.00992
Sonnet 5 $0.00013 $0.00397
Haiku 4.5 $0.00007 $0.00198

Measured 2d ago against content hash d9d361b10171, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/playwright/playwright-cli/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with playwright-cli

Comprehensive CLI-driven browser automation — navigate, interact, mock, debug, record, and generate tests without writing a single script file.

Quick Start

# Install and set up
playwright-cli install --skills
playwright-cli install-browser

# Open a browser and navigate
playwright-cli open https://playwright.dev

# Take a snapshot to see interactive elements (refs like e1, e2, e3...)
playwright-cli snapshot

# Interact using element refs from the snapshot
playwright-cli click e15
playwright-cli fill e5 "search query"
playwright-cli press Enter

# Take a screenshot
playwright-cli screenshot

# Close the browser
playwright-cli close

Golden Rules

  1. Always snapshot first — identify element refs before interacting; never guess ref numbers
  2. Use fill for inputs, click for buttonstype sends keystrokes one-by-one, fill replaces the entire value
  3. Named sessions for parallel work-s=name isolates cookies, storage, and tabs per session
  4. Save auth statestate-save auth.json after login, state-load auth.json to skip login next time
  5. Trace before debuggingtracing-start before the failing step, not after
  6. run-code for advanced scenarios — when CLI commands aren't enough, drop into full Playwright API
  7. Clean up sessionsclose or close-all when done; kill-all for zombie processes
  8. Descriptive filenamesscreenshot --filename=checkout-step3.png not screenshot
  9. Mock external APIs only — use route to intercept third-party services, not your own app
  10. Persistent profiles for stateful flows--persistent keeps cookies and storage across restarts

Command Reference

Core Interaction

playwright-cli open [url]                    # Launch browser, optionally navigate
playwright-cli goto <url>                    # Navigate to URL
playwright-cli snapshot                      # Show page elements with refs
playwright-cli snapshot --filename=snap.yaml # Save snapshot to file
playwright-cli click <ref>                   # Click an element
playwright-cli dblclick <ref>                # Double-click
playwright-cli fill <ref> "value"            # Clear and fill input
playwright-cli type "text"                   # Type keystroke by keystroke
playwright-cli select <ref> "option-value"   # Select dropdown option
playwright-cli check <ref>                   # Check a checkbox
playwright-cli uncheck <ref>                 # Uncheck a checkbox
playwright-cli hover <ref>                   # Hover over element
playwright-cli drag <src-ref> <dst-ref>      # Drag and drop
playwright-cli upload <ref> ./file.pdf       # Upload a file
playwright-cli eval "document.title"         # Evaluate JS expression
playwright-cli eval "el => el.textContent" <ref>  # Evaluate on element
playwright-cli close                         # Close the browser

Read the full file on GitHub · 210 lines

Files

What ships with it

10 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.

Changes

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.

  1. 2d ago First seen · 210 lines · 67 tokens per session scan A d9d361b10171

Subscribe to this mod's changes

playwright-cli is a skill published in the GitHub repository zebbern/claude-code-guide (4,596 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 1,985 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

cdb-scan

Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…

Avijit07x/claude-db · 72 tokens

mckinsey-consultant

McKinsey顾问式问题解决系统。从商业问题出发,通过假设驱动的结构化分析方法,生成McKinsey风格研究报告和PPT。融合Problem Solving方法论、MECE原则、Issue Tree拆解、Hypotheses形成、Dummy Page设计、智能数据收集和专业PPT生成能力。.

Mann1988/awesome-claude-skills · 82 tokens

exam-coach

Quiz and coach the user for the Anthropic Claude certification exams using this repository's blueprints and official exam guides. Use when the user asks to practice, be quizzed, drill a domain, take a mock exam, or prepare for the Associate, Developer, or Architect certifications.

Amey-Thakur/CLAUDE-CERTIFICATIONS · 61 tokens

security-claude

Skill "security-claude" from rahozosman/security-claude, covering security architecture & threat modeling intelligence, how this skill is organized (progressive disclosure), 1. pick a mode, 2. core method (applies to every mode) and 3. doing a focused review.

rahozosman/security-claude · 0 tokens

bridger

Coordinate with another Claude Code session over the bridge — discover peers, ask them, answer their questions — INSTEAD of guessing or asking the user. Trigger this the moment the task depends on something another repo's session knows: a dependency/library that changed and this code consumes it, an API or schema…

HoussemDjeghri/bridger · 131 tokens

run-tests

Run the pytest suite, report pass/fail counts and coverage, and identify untested code. Use when the user asks to run tests, check test coverage, or verify that changes didn't break anything.

JSchOBL/agentic-ai-learning-journey · 43 tokens