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.
npx skills add metalevel-tech/snapix-mcp-server --skill get-screenshot-and-uploadgit clone --depth 1 https://github.com/metalevel-tech/snapix-mcp-serverWrote 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/skills/metalevel-tech/snapix-mcp-server/get-screenshot-and-upload)<a href="https://agentmods.dev/skills/metalevel-tech/snapix-mcp-server/get-screenshot-and-upload"><img src="https://agentmods.dev/badge/skills/metalevel-tech/snapix-mcp-server/get-screenshot-and-upload/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.
<a href="https://agentmods.dev/skills/metalevel-tech/snapix-mcp-server/get-screenshot-and-upload"><img src="https://agentmods.dev/badge/skills/metalevel-tech/snapix-mcp-server/get-screenshot-and-upload.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00090 | $0.02182 |
| Opus 5 | $0.00045 | $0.01091 |
| Sonnet 5 | $0.00018 | $0.00436 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
get-screenshot-and-upload 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 10d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get Screenshot & Upload to Snapix
Captures a live browser screenshot using VS Code's integrated browser tools (primary method) or chrome-devtools-mcp (fallback), temporarily saves the image, uploads it to Snapix via snapix-mcp, then cleans up the local file.
When to Use
- "Take a screenshot of
<url>and upload to Snapix" - "Capture
<url>and store the image in Snapix" - Any screenshot-to-cloud workflow targeting Snapix
Prerequisites
Primary Method (Recommended)
- VS Code with browser tools enabled: Ensure
workbench.browser.enableChatToolssetting istrue - Integrated browser access: The agent must have permission to use browser tools
- Snapix MCP configured and authenticated (
mcp_metalevel_sna_snapix_*tools available)
Fallback Method
- Chrome with remote debugging: Running on
http://127.0.0.1:9222(only needed if integrated browser is unavailable) See chrome-devtools-mcp instructions for setup details.
Procedure
Decision Flow
The skill follows this priority order:
- Integrated Browser (VS Code built-in tools) - Primary method
- Chrome DevTools MCP - Fallback if integrated browser unavailable
- Python CDP Script - Last resort fallback
Step 1 — Check Available Methods & Navigate
Option A: Integrated Browser (Recommended)
Use VS Code's built-in browser tools:
// Open a new browser page
open_browser_page url="<target-url>"
// Wait for page to load
run_in_terminal command="sleep 3" explanation="Wait for page load" goal="Allow page to fully render"
Option B: Chrome DevTools MCP (Fallback)
Use chrome-devtools-mcp if integrated browser is unavailable:
mcp_io_github_chr_new_page url="<target-url>"
Wait a few seconds for the page to load (run_in_terminal: sleep 3).
Step 2 — Dismiss Dialogs (if any)
For Integrated Browser:
Use read_page to check content, then click_element to dismiss dialogs:
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.
- 10d ago First seen · 258 lines · 90 tokens per session scan A ea73a24942ef
get-screenshot-and-upload is a skill published in the GitHub repository metalevel-tech/snapix-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 2,182 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
node-crawler
Node.js web crawler for production-grade, large-scale tasks — NOT for simple one-off requests. Use only when: bulk scraping, batch downloading, multi-page crawling, long-running spiders, or complex multi-step workflows that need connection pooling, rate limiting, proxy rotation, automatic retries, and Cheerio parsing.…
playwright-test
Write a playwright test, make sure it runs, and is not flaky.
meme-sticker
Turn one uploaded image into a complete 12-piece chat sticker pack by generating two 3x2 sticker sheets, extracting transparent PNGs, normalizing their canvases, and packaging the result as a ZIP. Use this skill whenever a user provides a photo and asks for chat stickers, reaction stickers, meme stickers, custom…
studiomcphub-studio
Image to Retail in 90 seconds. 10-stage creative pipeline: background removal, palette extraction, resize, 6-product mockups, CMYK conversion, print-ready PDF, SVG vectorization, invisible watermarking, AI metadata enrichment, ESRGAN upscaling. Local DAM organizes all outputs. HTML preview gallery.
gem-pw
Browser-automated Gemini Gem CLI (CDP-first) — chat, CRUD, image gen, deep research, --collab surgical-diff review. No API key.