playwright

A browser automation tool for controlling web pages with Playwright, a framework for driving and testing browsers.

In plain words
What is it for?
It can inspect pages, take screenshots when visual evidence is useful, and support browser test debugging or test generation.
Why use it?
It helps inspect real user interfaces and diagnose browser-based test failures through repeatable browser actions.

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/conn-castle/agent-layer/playwright
Any agent
npx skills add conn-castle/agent-layer --skill playwright
Clone the repo
git clone --depth 1 https://github.com/conn-castle/agent-layer

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,301 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 $0.00059 $0.01301
Opus 5 $0.00030 $0.00651
Sonnet 5 $0.00012 $0.00260
Haiku 4.5 $0.00006 $0.00130

Measured 2d ago against content hash 9d9ed5aebb87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

internal/templates/skills-catalog/playwright/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with playwright-cli

Modified by Conn Castle Studios on 2026-05-26 from the Apache-2.0 playwright-cli skill: reduced duplicated command reference material and tailored the workflow guidance for Agent Layer.

Use globally installed playwright-cli as the browser control surface. This skill provides routing, safety, and workflow rules; installed CLI help provides command syntax.

Defaults

  • Use snapshots and element refs for navigation.
  • Use screenshots only when visual evidence matters.
  • Use references only for Playwright test debugging or test generation.
  • Create no durable artifact unless the task needs one.

Required artifacts

  • No artifact is required for ordinary inspection.
  • Put agent-only scripts, state files, traces, videos, screenshots, and saved snapshots under .agent-layer/tmp/.
  • Report every artifact path created.

Global constraints

  • Run playwright-cli --version before the first playwright-cli command in a session. Stop if it is missing.
  • Run playwright-cli --help before the first playwright-cli command in a session.
  • Run playwright-cli --help <command> before using a non-obvious subcommand or flag.
  • Treat installed CLI help as the source of truth for commands, arguments, flags, and defaults.
  • Keep short help-probe lists as routing hints, not command documentation. Always query live help before using a listed command.
  • If CLI, browser, app, or test setup is missing, stop and report the missing requirement; do not install packages or browsers unless the user asked for setup.
  • Do not run playwright-cli install --skills.
  • Do not hard-code or expose secrets in commands, tests, storage state, traces, videos, screenshots, or logs.

Human checkpoints

  • Ask before installing CLI packages, installing browsers, changing browser configuration, or using a persistent profile outside an explicit user request.
  • Ask before saving or reusing authentication state outside .agent-layer/tmp/.
  • Ask before leaving a browser session running when the user did not request an interactive handoff.

Read the full file on GitHub · 136 lines

Files

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.

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 · 136 lines · 59 tokens per session scan A 9d9ed5aebb87

Subscribe to this mod's changes

playwright is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,301 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 2026-08-31.

Related

Other skills, from other repositories

penguin-harness-manual-test

Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks…

Prism-Shadow/penguin-harness · 77 tokens

browser-testing-with-screenshots

Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.

AgentWorkforce/relay · 32 tokens

tlamatini-daily-chat-test

Run the daily automated Tlamatini chat regression — drive a visible Chrome via Playwright, log into agentpage.html, ask up to 1000 curated safe questions one-by-one (Multi-Turn ON, ACPX/Ask-Execs/Exec-Report/Internet OFF), wait for and qualify each answer (heuristic + LLM judge on failures), then write a dated report…

XAIHT/Tlamatini · 125 tokens

webqa

Use WebQA to test websites, web pages, URLs, login flows, search flows, forms, navigation, and core user journeys with an AI browser QA agent.

MigoXLab/webqa-agent · 36 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

datascienceworld-kan/vinagent · 35 tokens

inspector-workbench

Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…

CopilotKit/CopilotKit · 112 tokens