human-mcp: Command for Claude Code

.claude/commands/design/screenshot.md

screenshot is a command for Claude Code from mrgoonie/human-mcp. It costs 6 tokens per session (401 once invoked), scanned A, original, MIT.

A command for creating a web design from a screenshot by first analysing its visual details, planning the work, and implementing the result in HTML, CSS, and JavaScript.

In plain words
What is it for?
Use it to recreate layouts, typography, colours, spacing, effects, and motion from a supplied screenshot, then review the result.
Why use it?
It turns a visual reference into an organised design and implementation process instead of relying on an incomplete visual guess.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

This is mrgoonie/human-mcp's own configuration. It tells Claude Code how to work on human-mcp 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 human-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mrgoonie/human-mcp. 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/mrgoonie/human-mcp/main/.claude/commands/design/screenshot.md
Clone the repo
git clone --depth 1 https://github.com/mrgoonie/human-mcp

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrgoonie/human-mcp/screenshot.svg)](https://agentmods.dev/commands/mrgoonie/human-mcp/screenshot)
Your own site
<a href="https://agentmods.dev/commands/mrgoonie/human-mcp/screenshot"><img src="https://agentmods.dev/badge/commands/mrgoonie/human-mcp/screenshot.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 401 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 $0.00006 $0.00401
Opus 5 $0.00003 $0.00200
Sonnet 5 $0.00001 $0.00080
Haiku 4.5 $0.00001 $0.00040

Measured 8d ago against content hash 818ef1719929, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

screenshot 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 8d 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.

.claude/commands/design/screenshot.md · 23 lines

What it actually says

Think hard to plan & start designing follow exactly this screenshot: $ARGUMENTS

Workflow:

  1. Use eyes analyze tool to describe super details of the screenshot (design style, trends, fonts, colors, border, spacing, elements' positions, size, shape, texture, material, light, shadow, reflection, refraction, blur, glow, image, background transparency, transition, etc.)
    • IMPORTANT: Try to predict the font name (Google Fonts) and font size in the given screenshot, don't just use Inter or Poppins.
  2. Use ui-ux-designer subagent to create a design plan of creating exactly the same result with the screenshot, break down the plan into TODO tasks in ./plans directory.
  3. Then implement the plan step by step.
  4. If user doesn't specify, create the design in pure HTML/CSS/JS.
  5. Report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
  6. If user approves the changes, update the ./docs/design-guideline.md docs if needed.

Important Notes:

  • ALWAYS REMEBER that you have the skills of a top-tier UI/UX Designer who won a lot of awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.
  • Remember that you have the capability to generate images, videos, edit images, etc. with Human MCP Server tools. Use them to create the design with real assets.
  • Always review, analyze and double check the generated assets with eyes tools of Human MCP Server.
  • Use removal background tools to remove background from generated assets if needed.
  • Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.
  • Maintain and update ./docs/design-guideline.md docs if needed.
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. 8d ago First seen · 23 lines · 6 tokens per session scan A 818ef1719929

Subscribe to this mod's changes

screenshot is a command published in the GitHub repository mrgoonie/human-mcp (294 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 401 once invoked, about $0.0000 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.