safe-browser agent skill by browserbase
Builds constrained-browser agents whose safe_browser tool enforces a domain allowlist, so an agent can browse without raw browser, shell, or CDP access.
At a glance
| Publisher | Browserbase Official |
|---|---|
| Repository | browserbase/skills (18 listed skills) |
| Category | AI Agents and LLM Engineering |
| License | MIT |
| Last commit | September 1, 2026 (repository) |
| SKILL.md | 87 lines, 478 words |
| Bundled files | 5 files, including assets or templates |
| Quality score | 75/100 · C Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the listing badge and raise the score |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: 1 script file (1 JavaScript). Your agent may run them, so read them first.
- Commands in SKILL.md: its code blocks run
npxandnpm install, which fetch or run software from outside the skill folder. - Environment variables its scripts read:
ANTHROPIC_API_KEY. Check SKILL.md for which ones it needs. - Network: its scripts use an HTTP client or a cloud SDK, and name
news.ycombinator.com. - Tool permissions requested:
Bash, Read, Write, Edit(theallowed-toolsfield of SKILL.md). - License: MIT, an open-source or open-content license.
Install safe-browser
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/browserbase/skills/tree/main/skills/safe-browsertmp="$(mktemp -d)"
git clone --depth 1 https://github.com/browserbase/skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/safe-browser .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo browserbase/skills \
--path skills/safe-browserbrowserbase/skills is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes it
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.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Compatibility, from SKILL.md
| Compatibility | Requires Node.js 18+, npm, and a local Chromium (`npx playwright install chromium`). The generated Claude Agent SDK runtime app needs ANTHROPIC_API_KEY. |
|---|
Sections in SKILL.md
- When to Use
- Default Approach
- Runtime Shape
- Tool Design Rules
- Verification Requirements
- Notes
Files in the skill folder
LICENSE.txtSKILL.mdtemplates/claude-agent-sdk/hn-scraper-demo.mjstemplates/claude-agent-sdk/package-lock.jsontemplates/claude-agent-sdk/package.json
Suede Skill Check: 75/100 · C
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: 6811ca311633. Report version f873515d1a21. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
- Instruction depth: 4 of 7 points. 7 for a SKILL.md body of 500–3,000 words; 4 for 250–4,500; 1 for 100 or more.
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
safe-browser passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 5 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 4 of 7 |
| Reference files | 0 of 3 |
| Bundled scripts | 0 of 2 |
| Recent maintenance | 6 of 9 |
| Curated-list citations | 0 of 7 |
| Tool permissions declared | 2 of 2 |
| Compatibility declared | 2 of 2 |
Show the listing and raise the score
safe-browser is listed with 75/100 · C. This badge links to its Suede listing. Skills scoring 80–99 add a numeric and a letter quality shield; the largest open points for safe-browser are boundary clause (4), example request (3) and instruction depth (3). Send your repository and the points you want to raise, then request a fresh review after updating the skill.
[](https://skills.suedeai.ai/directory/browserbase/skills/safe-browser/)<a href="https://skills.suedeai.ai/directory/browserbase/skills/safe-browser/"><img src="https://skills.suedeai.ai/directory/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Where this skill is cited
browserbase/skills is listed from its publisher's official collection or a listing request.