screenshot-design

A command for capturing an image of a screen design and saving it in the product folder for documentation. It requires the Playwright MCP server, a browser-automation tool.

In plain words
What is it for?
Taking screenshots of product screen designs after identifying the relevant section and design files in the project.
Why use it?
It gives the team a recorded view of a design instead of relying on memory or manual screenshots. The command also checks whether the required browser tool is available.

Command for Claude Code

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 commands/buildermethods/design-os/screenshot-design
Clone the repo
git clone --depth 1 https://github.com/buildermethods/design-os

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 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 $0.00000 $0.01046
Opus 5 $0.00000 $0.00523
Sonnet 5 $0.00000 $0.00209
Haiku 4.5 $0.00000 $0.00105

Measured 2d ago against content hash 4151ba1630ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

screenshot-design 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.

.claude/commands/design-os/screenshot-design.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Screenshot Screen Design

You are helping the user capture a screenshot of a screen design they've created. The screenshot will be saved to the product folder for documentation purposes.

Prerequisites: Check for Playwright MCP

Before proceeding, verify that you have access to the Playwright MCP tool. Look for a tool named browser_take_screenshot or mcp__playwright__browser_take_screenshot.

If the Playwright MCP tool is not available, output this EXACT message to the user (copy it verbatim, do not modify or "correct" it):


To capture screenshots, I need the Playwright MCP server installed. Please run:

claude mcp add playwright npx @playwright/mcp@latest

Then restart this Claude Code session and run /screenshot-design again.

Do not substitute different package names or modify the command. Output it exactly as written above.

Do not proceed with the rest of this command if Playwright MCP is not available.

Step 1: Identify the Screen Design

First, determine which screen design to screenshot.

Read /product/product-roadmap.md to get the list of available sections, then check src/sections/ to see what screen designs exist.

If only one screen design exists across all sections, auto-select it.

If multiple screen designs exist, use the AskUserQuestion tool to ask which one to screenshot:

"Which screen design would you like to screenshot?"

Present the available screen designs as options, grouped by section:

  • [Section Name] / [ScreenDesignName]
  • [Section Name] / [ScreenDesignName]

Step 2: Start the Dev Server

Start the dev server yourself using Bash. Run npm run dev in the background so you can continue with the screenshot capture.

Do NOT ask the user if the server is running or tell them to start it. You must start it yourself.

After starting the server, wait a few seconds for it to be ready before navigating to the screen design URL.

Step 3: Capture the Screenshot

Use the Playwright MCP tool to navigate to the screen design and capture a screenshot.

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 0 tokens per session scan A 4151ba1630ca

Subscribe to this mod's changes

screenshot-design is a command published in the GitHub repository buildermethods/design-os (1,848 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,046 tokens. 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.