Urlbox CLI: screenshots from your terminal — or your agent

The Urlbox CLI lets you call the Urlbox screenshot API straight from your terminal. And even better: you can hand it to an AI agent and have it taking screenshots in under a minute.

>

That's the pitch. The rest of this post backs it up — stopwatch included.

None of this is newly possible — you could always do it through the Urlbox API. But now you can simply tell an agent: "Use the Urlbox CLI to screenshot these URLs..." and it can install it, understand it, and take your first screenshot in just under a minute.

Here's the plain version, a screenshot straight from your shell:

urlbox screenshot https://stripe.com --full-page --output stripe.png

(That --full-page flag captures the whole scrolling page, not just the viewport.)

Or you may want a PDF or even a video?

urlbox pdf   https://stripe.com/pricing --output pricing.pdf
urlbox video https://theverge.com       --output verge.mp4

That's the terminal version. Now the agent version.

Urlbox is now agent-accessible

Three pieces, working together:

• The API — the rendering engine, same as always.
• The CLI — puts it in your terminal.
• The agent skill — one command teaches your agent how to use it.

The upshot is simple: anything you can do with the Urlbox API, you can now get an agent to do in plain English.

The experiment we ran

We walked the exact cold path an agent takes — install, discover, render — and put a stopwatch on every step. Cold machine to a saved screenshot: about a minute. Here's where the time goes:

• Install from npm: ~30 seconds.
• The tool explains itself: urlbox commands returns every command and flag as structured JSON. An agent reads that and knows the tool — no docs needed.
• A validated render before any key exists: urlbox screenshot https://stripe.com --full-page --dry-run comes back "payload validated, no API call made." The correct command, confirmed, with no credentials.
• Then it hits exactly one wall — code: auth, "no API secret configured", with a link straight to where you get one.
• Add the key (~30 seconds to grab it), and the first screenshot lands in under 6 seconds.

Nearly all of that minute is npm installing and you fetching your key. It works well, and the render itself is just seconds. The one thing the agent can't do for you is paste in your own credential — and that's deliberate: you decide when your credentials get written to disk, not the agent.

How we built it for agents

We took our cue from 37signals, who recently made Basecamp agent-accessible by pairing their API with a CLI and a set of agent skills. We applied the same idea to screenshots, with one goal throughout: make the tool as machine-friendly as possible.

If you're building something an agent should be able to pick up cold, a few decisions made the biggest difference:

• Make every command self-describing. urlbox commands and --help emit structured JSON, so an agent can read the tool instead of guessing at it.
• Give it a dry run. --dry-run validates a request without spending anything, so an agent can confirm it built the right call before committing to it.
• Ship it as an agent skill. One command — urlbox skill install --target claude-code — drops a skill file the agent auto-discovers, so it knows the tool from the first prompt (Cursor, Codex and opencode too).
• Don't hide the rest of the API. The CLI passes any option straight through, so anything you can render through Urlbox, an agent can render for you.

That's why "take every URL in this CSV and screenshot it into a folder" becomes a sentence, not a script. If you have a terminal, you can save screenshots. That's it.

Frequently asked questions

What is the Urlbox CLI?

The Urlbox CLI is a command-line tool that calls the Urlbox screenshot API from your terminal. You can capture screenshots, PDFs, and videos of any URL with a single command, and it ships with an agent skill so AI coding agents can drive it directly.

How do I take a screenshot from the command line?

Install the CLI with npm install -g @urlbox/cli, run urlbox auth to add your API key, then run urlbox screenshot https://example.com --output shot.png. Once your key is set, the first screenshot lands in under 6 seconds.

How fast can an AI agent start using the Urlbox CLI?

In our timed cold-start test, going from never having seen the tool to a saved PNG took about a minute — roughly 30 seconds to install from npm, 30 to fetch an API key, and a few seconds for the render itself.

Can the Urlbox CLI capture PDFs and videos too?

Yes. Use urlbox pdf <url> --output file.pdf for PDFs and urlbox video <url> --output file.mp4 for videos. The CLI passes any Urlbox API option straight through, so anything the API can render, the CLI can too.

Which AI agents does the Urlbox CLI work with?

Any agent that can run a terminal command can use it — it's just a CLI. To make it plug-and-play, we ship ready-made agent skills for Claude Code, Cursor, Codex, and opencode: run urlbox skill install --target <your-agent> and it knows the tool from the first prompt. Other agents can still drive it straight from urlbox --help.

The full CLI guide

The complete CLI guide is in our docs: Urlbox CLI guide — install, auth, every format, batching from a CSV, async + webhooks, and agent setup. If there's anything you think we missed, let us know!

Try it — from your terminal or your agent

This tool is still in its early days, and we'd love for you to share any issues you run into with us. You'll need an Urlbox account to render — start a 7-day trial — then install from npm or GitHub:

npm install -g @urlbox/cli
urlbox auth
urlbox screenshot https://urlbox.com --output hello.png

Or just ask "Use the Urlbox CLI to screenshot this URL" and let your agent take it from there.