Skip to content
Agentmart
Submit a tool

browse

Web browsing and page extraction.

Skill by Scino

IndexedMIT★ 18
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/scino-browse

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Web browsing and page extraction. Attaches to Chrome over CDP when it is running, otherwise one-shot headless Chrome. Use for /browse, "open URL", public competitor pages, interactive search UIs, or a session where you are already logged in.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/browse

What's inside

Skill name
browse
Description
Web browsing and page extraction. Attaches to Chrome over CDP when it is running, otherwise one-shot headless Chrome. Use for /browse, "open URL", public competitor pages, interactive search UIs, or a session where you are already logged in.
License
MIT
Instructions
87 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • run.mjs

SKILL.md (first lines)

# Browse

Drive a real browser. Prefer this over naive Playwright scripts. Extracted text is sanitized before it hits the model.

## How to invoke

From any harness:

```bash
npx @scino/fstack browse <command>
```

From this skill folder (works when the skill is a junction into the fstack package):

```bash
node run.mjs <command>
```

From a clone:

```bash
node bin/fstack.js browse <command>
```

## Commands

```bash
fstack browse goto https://example.com
fstack browse text
fstack browse text https://example.com
fstack browse screenshot
fstack browse screenshot https://example.com out.png
fstack browse eval "document.title"
fstack browse eval https://example.com "document.title"
fstack browse check-cdp
fstack browse sanitize ./raw.txt
```

`goto` / `text` / `screenshot` / `eval` without a URL need Chrome CDP (your session). With a URL they can run headless in one shot.

`text` waits for visible body text, then fails if the body is still empty. That is usually a search shell, a challenge page, or JS that never painted. Do not retry the same URL. Search or click, then `text` again.

## Strategy 1: One-shot headless

Public pages where the URL already has the content. Pass the URL on the command.

```bash
fstack browse text https://example.com
```

Uses installed Chrome when possible. Text is injection-sanitized.

## Strategy 2: Real Chrome (interaction and login-walled sites)

Use CDP when you need to type, click, or wait on a page, or when headless is blocked.

Empty extract is not a login problem by itself. Many public UIs start as a search shell. Attach CDP, complete the query or click in that window (or `goto` a URL that already encodes the query), wait until results exist, then `fstack browse text` with no URL.

Login-walled sites (LinkedIn, X, and similar) still need you to log in by hand in that Chrome. Only use sessions you own.

Start Chrome once:

**Windows** (throwaway profile; does not fight an already-open Chrome):

```powershell
& "C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="$env:TEMP\chrome-fstack-cdp"
```

To reuse your real cookies, quit Chrome first, then point `--user-data-dir` at `$env:LOCALAPPDATA\Google\Chrome\User Data`.

**macOS:**

```bash
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
```

Confirm with `fstack browse check-cdp`.

## Strategy 3: Harness native browser

If the host agent already has a working browser tool (Cursor, Antigravity), use it for ordinary pages. Use this skill when you need CDP attach, sanitization, or a harness that has no browser.

## Needs

`playwright-core` (ships with `@scino/fstack`). Headless one-shot wants Chrome installed, or `npx playwright install chromium`.

From Scino/fstack, MIT.

More from Scino/fstack

Signals

Stars
18
Forks
0
Open issues
1
Last commit (this folder)
Sep 19, 2026 (1 month ago)
Last release
Sep 26, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Scino

Cite this page

browse skill. Agent Mart. https://agentmart.dev/skills/scino-browse (last updated 2026-10-24)