browser-testing-with-screenshots

A browser-testing guide for controlling Chrome and taking screenshots while checking a web application. It uses browser tools connected through Chrome DevTools Protocol, a way for programs to inspect and control Chrome.

In plain words
What is it for?
Use it to test browser-based user flows, interact with page elements, check layouts, test local applications, and document behavior with screenshots.
Why use it?
It helps verify that web pages work in a real browser and that visual changes appear as expected. Screenshots provide evidence of the page state during testing.

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/agentworkforce/relay/browser-testing-with-screenshots
Any agent
npx skills add AgentWorkforce/relay --skill browser-testing-with-screenshots
Clone the repo
git clone --depth 1 https://github.com/AgentWorkforce/relay

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00032 $0.01891
Opus 5 $0.00016 $0.00945
Sonnet 5 $0.00006 $0.00378
Haiku 4.5 $0.00003 $0.00189

Measured 3d ago against content hash 76188cf6d9ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-testing-with-screenshots scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Simple page content validation (use curl/wget)
.claude/skills/browser-testing-with-screenshots/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Testing with Screenshots

Overview

Automate Chrome browser testing with visual verification using browser-tools. Connect to Chrome DevTools Protocol for navigation, interaction, and screenshot capture to confirm application functionality.

Prerequisites

REQUIRED: Install agent-tools from https://github.com/badlogic/agent-tools

# Clone and install agent-tools
git clone https://github.com/badlogic/agent-tools.git
cd agent-tools
# Follow installation instructions in the repository
# Ensure all executables (browser-start.js, browser-nav.js, etc.) are in your PATH

Verify installation:

# Check that browser tools are available
which browser-start.js
which browser-nav.js
which browser-screenshot.js

All browser-* commands referenced in this skill come from the agent-tools repository and must be properly installed and accessible in your system PATH.

When to Use

Use this skill when:

  • Testing web application UI flows
  • Verifying visual changes or layouts
  • Automating repetitive browser interactions
  • Documenting application behavior with screenshots
  • Testing localhost applications during development
  • Need to interact with elements that require human-like selection

Don't use for:

  • API testing (use direct HTTP calls)
  • Headless testing where visuals don't matter
  • Simple page content validation (use curl/wget)

Quick Reference

Task Command Purpose
Start browser browser-start.js Launch Chrome with debugging
Navigate browser-nav.js http://localhost:5172/dashboard Go to specific URL
Take screenshot browser-screenshot.js Capture current viewport
Pick elements browser-pick.js "Select the login button" Interactive element selection
Run JavaScript browser-eval.js 'document.title' Execute code in page context
Extract content browser-content.js Get readable page content
View cookies browser-cookies.js List session cookies

Read the full file on GitHub · 279 lines

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. 3d ago First seen · 279 lines · 32 tokens per session scan A 76188cf6d9ec

Subscribe to this mod's changes

browser-testing-with-screenshots is a skill published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed 3d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,891 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

computer-use

Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…

kirodotdev/KiroCrew · 105 tokens

tutti-record-agent-session-replay

From a Tutti checkout, run, audit, freshly replay, publish, or diagnose Session Replay cassettes that are driven by case-repository scenario scripts (CDP), not by interactive UI recording. Use for real-Provider capture while a scenario.mjs executes, cassette transport or semantic-state mismatches, fresh replay…

tutti-os/tutti · 127 tokens

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens

pod-e2e

ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Runs end-to-end tests (backend API + frontend Playwright) for a Kiro Crew feature worktree against an ISOLATED throwaway pod…

kirodotdev/KiroCrew · 147 tokens

browser-recording

Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…

kirodotdev/KiroCrew · 85 tokens