safe-browser
safe-browser is an agent skill published by browserbase, listed under building agents. It lives in the browserbase/skills repository, which has 3,742 GitHub stars; we last read it on 2026-09-16.
safe-browser builds local constrained-browser agents that enforce a domain allowlist with Fetch interception and allow a runtime Claude Agent SDK agent to complete browsing tasks. It requires a domain allowlist and connects to the Chrome DevTools Protocol (CDP).
Install
skills is a generic installer for any repository of Claude agent skills -- it reads browserbase/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add browserbase/skills
Maintenance
Build 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.
safe-browser compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| safe-browser (this page) | browserbase | Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist wi… | 3,742 | 2026-09-29 |
| add-webmcp(same repository) | browserbase | Analyze an existing web application, identify safe user-visible capabilities across routes, forms, server act… | 3,742 | 2026-09-29 |
| browser-use-to-stagehand(same repository) | browserbase | Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase. Use when… | 3,742 | 2026-09-29 |
| claude-handoff | mattpocock | Hand the current conversation off to a fresh background agent that picks up the work immediately. | 303,549 | 2026-10-22 |
| context-engineering | addyosmani | Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when swit… | 110,611 | 2026-10-13 |
| using-agent-skills | addyosmani | Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or wo… | 110,611 | 2026-10-13 |
| agent-platform-inference | Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemin… | 21,580 | 2026-10-25 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about safe-browser
- What does safe-browser do?
- safe-browser builds local constrained-browser agents that enforce a domain allowlist with Fetch interception and allow a runtime Claude Agent SDK agent to complete browsing tasks. It requires a domain allowlist and connects to the Chrome DevTools Protocol (CDP).
- How do I install safe-browser?
- Run npx skills add browserbase/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes safe-browser?
- browserbase.
- Is safe-browser maintained, and what licence does it use?
- Its repository has 3,742 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-09-29. We did not find a declared licence, so check the repository before you rely on it.
More agent skills for building agents
- python-sdkby 101-skills
- widgets-uiby 101-skills
- context-engineeringby addyosmani
- using-agent-skillsby addyosmani
- anti-detect-browserby antibrow
- browser-mcp-agentby antibrow