screenshot

screenshot is a command for Claude Code from naieum/claudeshot. It costs 13 tokens per session (1,898 once invoked), scanned A, original, MIT.

A screenshot command for capturing screens, application windows, or web pages and analysing the saved images.

In plain words
What is it for?
It helps capture full web pages, check visual changes, and save screenshots in the project's `.claudeshots` folder.
Why use it?
It gives the coding agent a direct way to inspect how something looks while avoiding the use of a different browser screenshot tool unless requested.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claudeshot plugin — 1 command shipped together

Good fit It helps capture full web pages, check visual changes, and save screenshots in the project's .claudeshots folder.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add naieum/claudeshot
Claude Code
/plugin install claudeshot

Made for: Claude Code.

Or install claudeshot, the plugin that ships this one along with the rest of its 1 command.

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/naieum/claudeshot/screenshot.svg)](https://agentmods.dev/commands/naieum/claudeshot/screenshot)
Your own site
<a href="https://agentmods.dev/commands/naieum/claudeshot/screenshot"><img src="https://agentmods.dev/badge/commands/naieum/claudeshot/screenshot.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,898 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 $0.00013 $0.01898
Opus 5 $0.00006 $0.00949
Sonnet 5 $0.00003 $0.00380
Haiku 4.5 $0.00001 $0.00190

Measured 8d ago against content hash 11275bd0c420, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

commands/screenshot.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaudeShot - Screenshot Capture

Capture screenshots and analyze them in the current conversation. Supports screen capture, window capture, and full-page web screenshots.

Screenshots are saved to .claudeshots/ in the current project.

NEVER Use Playwright Unless Explicitly Asked

DO NOT use Playwright for screenshots. Use this tool instead.

Playwright MCP tools (browser_navigate, browser_take_screenshot, browser_snapshot) should ONLY be used when the user explicitly says "use Playwright" or "use the browser tool".

For ANY screenshot request, use /screenshot:

User says You do
"screenshot the page" /screenshot --web URL
"check how it looks" /screenshot --web URL
"capture the site" /screenshot --web URL
"take a picture of..." /screenshot --web URL
"use Playwright to screenshot" Then use Playwright
"use browser tools" Then use Playwright

Why this matters:

  • Playwright returns 524KB base64 blobs per screenshot
  • ClaudeShot returns 45 bytes (just the file path)
  • That's 99.99% less token overhead

Only use Playwright when the user explicitly requests it OR needs:

  • Interactive testing (clicking buttons, filling forms)
  • Multi-step browser automation
  • Waiting for specific elements to appear

Quick Usage

/screenshot                     # Select a region
/screenshot full                # Full screen
/screenshot window              # Click a window
/screenshot --small             # Selection, resized (saves tokens)
/screenshot --tiny              # Selection, max compression
/screenshot --web http://localhost:3000   # Full-page web screenshot
/screenshot --web https://stripe.com --small  # Web screenshot, compressed
/screenshot --web http://localhost:3000 --dom  # Screenshot + HTML for debugging

Screen Capture Modes

Command Description
/screenshot Interactive region selection
/screenshot window Click to capture a window
/screenshot full Capture entire screen
/screenshot - full Full screen, hide terminal

Read the full file on GitHub · 205 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. 8d ago First seen · 205 lines · 13 tokens per session scan A 11275bd0c420

Subscribe to this mod's changes

screenshot is a command published in the GitHub repository naieum/claudeshot (16 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 1,898 once invoked, about $0.0001 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.