cloudping: Skill for Claude Code

.ai/skills/take-a-screenshot/SKILL.md

take-a-screenshot is a skill for Claude Code, Codex from internetworklab/cloudping. It costs 82 tokens per session (845 once invoked), scanned A, original, MIT.

A procedure for capturing bright-mode and dark-mode screenshots of a local web application and combining them into one comparison image. It uses a local development server and an automated Chrome browser.

In plain words
What is it for?
It is for checking or documenting a Next.js web application in light and dark mode.
Why use it?
It makes it easier to compare the two colour modes and create visual documentation of the frontend.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is internetworklab/cloudping's own configuration. It tells Claude Code and Codex how to work on cloudping itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cloudping configures →

Reuse

Borrowing it

Nothing to install: this file belongs to internetworklab/cloudping. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/internetworklab/cloudping/master/.ai/skills/take-a-screenshot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/internetworklab/cloudping

Made for: Claude Code, Codex.

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 take-a-screenshot

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/internetworklab/cloudping/take-a-screenshot"><img src="https://agentmods.dev/badge/skills/internetworklab/cloudping/take-a-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 845 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00082 $0.00845
Opus 5.5 $0.00033 $0.00338
Sonnet 5.5 $0.00016 $0.00169
Haiku 4.5 $0.00008 $0.00085

Measured 2mo ago against content hash ffc1278a0d7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

take-a-screenshot 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 2mo 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.

curl -s -o /dev/null -w "%{http_code}" http://localhost:45844
.ai/skills/take-a-screenshot/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Take a Screenshot

Capture side-by-side bright and dark mode screenshots of the Next.js application running on the local dev server.

Prerequisites

  • Node.js and npm
  • Chrome MCP server (stdio transport)
  • ffmpeg for combining images

Step 1: Start the Dev Server

Read web/package.json to confirm the dev port. This project uses next dev -p 45844, so the base URL is http://localhost:45844.

Check if the server is already responding:

curl -s -o /dev/null -w "%{http_code}" http://localhost:45844

If the response is not 200, start it:

cd web && npm run dev

Poll the port until it returns HTTP 200 before proceeding.

Step 2: Capture Screenshots via Chrome MCP

Use the Chrome MCP server (stdio transport) to automate the browser.

Preferred Method: Chrome Launch Flags

Force the color scheme at the browser level by passing Chrome flags when launching the instance. This affects prefers-color-scheme globally without requiring query parameters or page interaction.

Bright mode:

  • Launch Chrome with --force-light-mode
  • Navigate to http://localhost:45844
  • Capture screenshot
  • Save as bright.png

Dark mode:

  • Launch Chrome with --force-dark-mode
  • Navigate to http://localhost:45844
  • Capture screenshot
  • Save as dark.png

If the Chrome MCP server reuses an already-running Chrome instance and cannot relaunch with different flags, use one of the fallbacks below.

Fallback 1: Query Parameters

Append theme-forcing query parameters to the URL:

  • Bright: http://localhost:45844?forceBright=true
  • Dark: http://localhost:45844?forceDark=true

Fallback 2: JavaScript / CDP

If query parameters do not exist in the application, use Chrome DevTools Protocol or execute JavaScript in the page to toggle the theme. For example, inject a script that overrides window.matchMedia or forces MUI/Tailwind into the desired color scheme.

Save both images to a temporary directory (e.g., /tmp/screenshots/).

Step 3: Combine Images

Read the full file on GitHub · 95 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. 2mo ago First seen · 95 lines · 82 tokens per session scan A ffc1278a0d7e

Subscribe to this mod's changes

take-a-screenshot is a skill published in the GitHub repository internetworklab/cloudping (24 stars, last pushed 22d ago), licensed MIT. It adds 82 tokens to every session and 845 once invoked, about $0.0003 per session on Opus 5.5. 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

take-a-screenshot compared with skills from other repositories

take-a-screenshot next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
take-a-screenshotinternetworklab/cloudpingSkill2422d agoMITA82Claude Code, Codex
add-vector-iconchromium/chromiumSkill25kyesterdayBSD-3-ClauseA72Claude Code, Codex
webui-codechromium/chromiumSkill25kyesterdayBSD-3-ClauseA33Claude Code, Codex
browserwing-executorMemTensor/MemOSSkill12k2d agoApache-2.0A42Claude Code, Codex
figma-design-reviewchromium/chromiumSkill25kyesterdayBSD-3-ClauseA59Claude Code, Codex
figma-to-views-jsonchromium/chromiumSkill25kyesterdayBSD-3-ClauseA55Claude Code, Codex
figma-to-webuichromium/chromiumSkill25kyesterdayBSD-3-ClauseA44Claude Code, Codex