Browser Search
Stealth browser fetch and multi-engine search for AI web research
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · b3ab500
Task: extract title and text from the JS-rendered page quotes.toscrape.com/js — baseline with bare curl against the cloak-fetch.mjs bundle. Baseline was useless: after tag removal, 0 quotes (content was client-side rendered); the skill launched stealth-Chromium and returned title 'Quotes to Scrape', 1499 characters, and all 10 quotes in 6.6 s. Security claims were verified live, not by text: SSRF-block worked on 169.254.169.254 ('Blocked IP') and localhost ('Blocked hostname'), path-traversal guard repelled --script /etc/passwd, and bundled tests gave 28/28 and 12/12 passed. Main caveat: 2 out of 3 tools (SearXNG and Camofox) required Docker, which was not in the environment — I DID NOT measure them; the flagship 'multi-engine search' remained unchecked, and its own check.sh honestly showed this. Another inaccuracy: SKILL.md promised 'all commands/scripts are read-only, safe in Plan mode', but the very first run of cloak-fetch downloaded 140 MB of Chromium to ~/.cloakbrowser. Docker + two containers — real manual work, hence setup.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What Browser Search does
Three-tier web research stack: SearXNG for multi-engine search, Camofox for JS-heavy pages, and CloakBrowser for sites behind Cloudflare or DataDome. Triggers on web research, scraping, and pages that plain fetching cannot render.
How to install Browser Search
git clone https://github.com/Johell1NS/browser-search.git
mkdir -p ~/.claude/skills
cd browser-search && rm -rf .git && cp -r . ~/.claude/skills/browser-search
cd ~/.claude/skills/browser-search && npm install
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Browser Search
-
/browser-searchStealth browser fetch and multi-engine search for AI web research
It also activates on plain-language prompts like these:
-
This page needs JavaScript to render, can you fetch the actual content -
Search across multiple engines for me and pull the real page text back -
This site is behind Cloudflare, I still need the rendered page content
Frequently asked questions
- Is the Browser Search skill free?
- Yes. The skill itself is free from Johell1NS/browser-search. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Browser Search work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Task: extract title and text from the JS-rendered page quotes.toscrape.com/js — baseline with bare curl against the cloak-fetch.mjs bundle. Baseline was useless: after tag removal, 0 quotes (content was client-side rendered); the skill launched stealth-Chromium and returned title 'Quotes to Scrape', 1499 characters, and all 10 quotes in 6.6 s. Security claims were verified live, not by text: SSRF-block worked on 169.254.169.254 ('Blocked IP') and localhost ('Blocked hostname'), path-traversal guard repelled --script /etc/passwd, and bundled tests gave 28/28 and 12/12 passed. Main caveat: 2 out of 3 tools (SearXNG and Camofox) required Docker, which was not in the environment — I DID NOT measure them; the flagship 'multi-engine search' remained unchecked, and its own check.sh honestly showed this. Another inaccuracy: SKILL.md promised 'all commands/scripts are read-only, safe in Plan mode', but the very first run of cloak-fetch downloaded 140 MB of Chromium to ~/.cloakbrowser. Docker + two containers — real manual work, hence setup.
- What is the Browser Search SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install Browser Search?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Browser Search with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.