Safe Browser
Skill Verified ActiveBuild local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.
To enable users to build and demonstrate browser agents that operate within strict domain boundaries, ensuring safety and control during web browsing and scraping tasks.
Features
- Builds local constrained-browser agents
- Enforces domain allowlist with CDP Fetch interception
- Provides a `safe_browser` tool with restricted capabilities
- Includes example for Hacker News scraping with security checks
- Generates audit logs and artifacts for verification
Use Cases
- Browsing or scraping while staying on approved domains
- Demonstrating prompt-injection or link-following containment
- Building scrapers or browser workflows with domain policy
- Generating a Claude Agent SDK example for browser tasks
Non-Goals
- Providing a general-purpose browser automation tool
- Allowing agents raw browser, shell, or CDP access
- Supporting off-domain navigation or arbitrary web requests
Workflow
- Copy the local template and set up the environment.
- Run the provided Node.js script (`hn-scraper-demo.mjs`).
- Observe the agent interacting with the `safe_browser` tool.
- Verify browser navigation stays within the allowlist.
- Review generated artifacts (audit log, screenshots) for proof of concept.
Prerequisites
- Node.js installed
- Chromium browser installed (or will be installed via Playwright)
Installation
First, add the marketplace
/plugin marketplace add browserbase/skills/plugin install skills@browserbaseQuality Score
VerifiedTrust Signals
Similar Extensions
Use My Browser
100Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.
Skillify
97Codify the most recent successful /scrape flow into a permanent browser-skill on disk. Future /scrape calls with the same intent run the codified script in ~200ms instead of re-driving the page. Walks back through the conversation, synthesizes script.ts + script.test.ts + fixture, runs the test in a temp dir, and asks before committing. Use when asked to "skillify", "codify", "save this scrape", or "make this permanent". (gstack)
Project Session Manager
100Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
Public Google Drive
100Create public Google Docs or Google Sheet files without requiring OAuth. Use this skill to create and edit Google Docs and Sheets, no Google sign-in required. Documents are viewable at shareable links. Registration is automatic on first use.
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
X Twitter Scraper
100Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.