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.
/plugin marketplace add naieum/claudeshot/plugin install claudeshotWrote 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.
[](https://agentmods.dev/commands/naieum/claudeshot/screenshot)<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 8d ago First seen · 205 lines · 13 tokens per session scan A 11275bd0c420
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.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
can-i-use
Check browser support for web platform features against the project's browser targets.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
verify-pr
Verify a PR's frontend changes through browser automation.