Screenshot Testing

Screenshot Testing is a skill for Claude Code from chunlea/screenshot-mcp. It costs 81 tokens per session (1,051 once invoked), scanned A, original, MIT.

A guide for testing user interfaces with screenshots, which are captured images of an application’s screen or window.

In plain words
What is it for?
Use it to capture windows, displays, or selected screen areas and compare screenshots when checking layout or other visual changes.
Why use it?
It provides a repeatable way to check whether a screen looks and behaves as expected, including instructions for where screenshots should be saved.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the screenshot plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to capture windows, displays, or selected screen areas and compare screenshots when checking layout or other visual changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chunlea/screenshot-mcp/screenshot-testing
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.

Any agent
npx skills add chunlea/screenshot-mcp --skill screenshot-testing
Clone the repo
git clone --depth 1 https://github.com/chunlea/screenshot-mcp

Made for: Claude Code.

Or install screenshot, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for Screenshot Testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/chunlea/screenshot-mcp/screenshot-testing/github.svg)](https://agentmods.dev/skills/chunlea/screenshot-mcp/screenshot-testing)
Your own site
<a href="https://agentmods.dev/skills/chunlea/screenshot-mcp/screenshot-testing"><img src="https://agentmods.dev/badge/skills/chunlea/screenshot-mcp/screenshot-testing/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.

agentmods 80×15 button for Screenshot Testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/chunlea/screenshot-mcp/screenshot-testing"><img src="https://agentmods.dev/badge/skills/chunlea/screenshot-mcp/screenshot-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00081 $0.01051
Opus 5 $0.00041 $0.00526
Sonnet 5 $0.00016 $0.00210
Haiku 4.5 $0.00008 $0.00105

Measured 9d ago against content hash 6c4aaf4ae3bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Screenshot Testing 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 9d 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/screenshot-testing/SKILL.md · 150 lines

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.

Screenshot Testing

A guide for conducting effective UI testing using screenshots. This skill covers the screenshot-mcp tools, testing workflows, and comparison strategies for native application testing.

Configuration

Check for plugin settings at .claude/screenshot.local.md before taking screenshots.

Settings file format:

---
default_save_dir: /path/to/screenshots
---

When settings file exists:

  1. Read the file using the Read tool
  2. Parse YAML frontmatter to extract default_save_dir
  3. Use this path as save_dir when user wants to save screenshots
  4. If user specifies a different path, use their path instead

When settings file does not exist:

  • Ask user if they want screenshots saved
  • If yes, ask for save location or suggest creating settings file

Available MCP Tools

The screenshot MCP server provides 5 tools:

Tool Purpose Key Parameters
list_windows Discover all visible windows None
list_displays List all monitors/displays None
screenshot_window Capture specific window window_id or window_title, save_dir
screenshot_screen Capture entire display display_id, save_dir
screenshot_region Capture screen region x, y, width, height, save_dir

Testing Workflow

Step 1: Identify Target Window

Before capturing, identify the correct window:

1. Call list_windows to get all visible windows
2. Find target by app name or title
3. Note the window ID for screenshot_window

Window matching strategies:

  • By app name: Look for app field (e.g., "Electron", "Simulator")
  • By title: Use window_title parameter for fuzzy matching
  • By bounds: Check bounds to identify window by size/position

Step 2: Capture Screenshot

Choose the appropriate capture method:

  • Single window: Use screenshot_window with window ID or title
  • Full screen: Use screenshot_screen for entire display
  • Specific area: Use screenshot_region for precise coordinates

Read the full file on GitHub · 150 lines

Files

What ships with it

2 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. 9d ago First seen · 150 lines · 81 tokens per session scan A 6c4aaf4ae3bf

Subscribe to this mod's changes

Screenshot Testing is a skill published in the GitHub repository chunlea/screenshot-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 81 tokens to every session and 1,051 once invoked, about $0.0004 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

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

test-warp-ui

Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.

warpdotdev/warp · 55 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens

pyats-dynamic-test

Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.

automateyournetwork/netclaw · 61 tokens

test-loop

Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).

HoangNguyen0403/agent-skills-standard · 25 tokens

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens