Docs

Agent skill

One install teaches Claude Code, Codex, Cursor and the rest when to use Page Scanner and how, and what to say to them.

The MCP server gives an agent nine tools. The skill tells it when to reach for them and how: check the connection first and set Page Scanner up when nothing is connected, capture the tab you are looking at rather than reopen a page you are logged into, which options print well, what truncated means, what Chrome's debugger bar is, and to check what it quotes from a page against the capture before it answers. It is a SKILL.md in the Agent Skills format, so the same file works in every agent that reads the standard, and it lives in a public repository, sbd530/page-scanner-skills.

Install it

Claude Code: the plugin

The plugin carries the skill and registers the MCP server, so these two lines are the whole setup on the agent's side and replace the claude mcp add line on the install page:

claude plugin marketplace add sbd530/page-scanner-skillsclaude plugin install page-scanner@page-scanner-skills

Any agent: the skill on its own

npx skills add sbd530/page-scanner-skills

That installs it for the agents it finds in the current project: Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and the rest; -g installs it for your user instead. An agent that speaks MCP still needs the server registered, one line per client on the install page. An agent with only a shell needs nothing more: the skill falls back to the page-scanner command, run through npx. npx skills update picks up a newer skill later.

Either way, then connect Chrome, once per profile. The extension ships with local agents off. The skill runs install for you, and then asks you to press Connect in the extension's settings and allow Chrome's prompt, since only you can do that; there is no token to paste.

What to say to the agent

Plain requests work. The skill maps them onto the tools:

You sayThe agent does
"Save this tab as a PDF on my Desktop"list_tabs, then scan_page with that tabId and the folder
"Capture https://example.com/report so it prints on A4"scan_page with the url, captureWidth: "a4", pageSize: "a4"
"I need a full-page screenshot of the pricing page, PNG"format: "png"
"Grab the dark version of the docs page"colorScheme: "dark"
"Capture it and open it so I can crop it"openEditor: true; an agent cannot crop, the editor can
"Which of my open tabs are on the wiki?"list_tabs, no capture

Name a tab when the page's state matters: what you have scrolled, filtered or logged into is only in the tab you are looking at. Give a URL when it does not; the agent opens it in a background tab of your Chrome, captures it, and closes it again.

The agent reports the path it wrote, and two things about the file: selectableText, which is the only basis for saying the PDF's text is real, and truncated, which is set when the page was longer than the height ceiling, 60,000 pixels unless the extension's settings raise it, and the file is missing the rest. A skill that follows the file will say so rather than hand you an incomplete document as a whole one.

A site's design system, written down

The plugin, and npx skills add, carry a second skill, design-md. Ask the agent to write down a site's design system, or to document your own, and it has Page Scanner measure the site (design extract, through the MCP server's extract_design or the command), then writes a DESIGN.md from the measurements: colors, type, spacing and radii, the components with their variants and states, and do's and don'ts drawn from the contrast check and the consistency audit. Every value comes from the measured files. The names it gives to values the site did not name are listed as its own, and the site's logo, fonts, images and text are never copied.

Research with a copy of every source

A third skill, research, is for notes you want to go back to. Ask the agent to research a question from pages, collect sources or write notes with quotes, and it:

  • captures each page into a sources/ folder as a PDF with its Markdown beside it, from your tab when the page is behind a login;
  • cites each one from what the page declares about itself (citation data), and says "no date given" rather than guess one;
  • quotes only words that are in the capture, and keeps its own summary apart in a notes.md that says it was written by an agent;
  • runs check_quotes on every quote before it hands the notes over, and fixes or drops any the capture does not have.

Page Scanner runs no model for it: the reading and the writing are your agent's, and the capture and the check are Page Scanner's.

What the agent runs on its own

Nothing you have to hand it. With the MCP server it calls install, list_browsers, list_tabs, scan_page, diff_captures and extract_design, documented here. With a shell only, it runs the command line:

npx @page-scanner/cli browsers --jsonnpx @page-scanner/cli tabs --jsonnpx @page-scanner/cli scan --tab <id> --out ~/Desktop/ --jsonnpx @page-scanner/cli scan --url https://example.com/doc --page-width a4 --out ./doc.pdf --json

--json puts one document on stdout for success and failure alike, which is what an agent wants to read; the commands page has the whole surface and the exit codes.

Two things the skill tells the agent not to do: rotate the pairing token on its own, because that disconnects every browser you paired, and call the pair tool when you have not asked it to, because the token would land in the transcript.

Where it lives

sbd530/page-scanner-skills holds the skill, its argument reference and the Claude Code marketplace file, under Apache-2.0. It is published from the product repository, so a change to the tools and a change to the skill ship together; issues are welcome on either.

On this page