agentleFS
Sign inStart free
IvanSkainetIvanSkainet/arena-agent/skills/browseract/SKILL.md

browseract

Skill8 starsChanged 3 months agoMITView on GitHub

Wrapper around the [browser-act][upstream] CLI for stealth-aware browser automation. Works on Windows, macOS, and Linux. [upstream]: https://www.browseract.com/ BrowserAct is not bundled with Arena. Install it via [uv][uv] — a single command that works identically on every OS: [uv]: https://docs.astral.sh/uv/getting-started/installation/ Then verify: You should see the CLI version and handshake: ok. The Python wrapper (run.py) works on every platform; the historical run.sh remains for callers that expect a bash entrypoint on *nix. Run via python skills/browseract/run.py <sub> (or the bash wrapper…

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run via python skills/browseract/run.py <sub> (or the bash wrapper on *nix / from agentctl bact <sub>):

    line 38
  2. Distinctive:

    Default = fully local. Bundled Camoufox / stealth Chromium, no upload of cookies or page content.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

browseract

Wrapper around the browser-act CLI for stealth-aware browser automation. Works on Windows, macOS, and Linux.

Install (one-time)

BrowserAct is not bundled with Arena. Install it via uv — a single command that works identically on every OS:

uv tool install browser-act-cli --python 3.12

Then verify:

python skills/browseract/run.py doctor

You should see the CLI version and handshake: ok.

Update

uv tool upgrade browser-act-cli

Subcommands

The Python wrapper (run.py) works on every platform; the historical run.sh remains for callers that expect a bash entrypoint on *nix.

Run via python skills/browseract/run.py <sub> (or the bash wrapper on *nix / from agentctl bact <sub>):

  • doctor — check install + handshake
  • extract <url> — stealth-extract URL as markdown (saved under $ARENA_AGENT_HOME/reports/bact-extract-*.md)
  • shot <url> — stealth screenshot (PNG saved under $ARENA_AGENT_HOME/reports/bact-shot-*.png)
  • open <url> — start/use session, navigate
  • state — show current page state
  • click <index> — click element by index
  • type <text> — type into focused element
  • input <index> <text> — click then type
  • eval <js> — execute JS, return result
  • close — close current session
  • auth {set <KEY> | clear | status} — manage browser-act API key
  • browsers — list configured browsers
  • raw <args...> — pass-through to browser-act

When to use vs existing browser-* commands

  • agentctl http <url> — raw curl, no JS, cheapest.
  • agentctl readability <url> — headless Chromium + Readability.
  • agentctl bact extract <url> — stealth Chromium + anti-bot + markdown.

Boundaries

  • Default = fully local. Bundled Camoufox / stealth Chromium, no upload of cookies or page content.
  • Cloud features (residential IPs, hosted CAPTCHA) require an explicit browser-act auth set <key>. Not enabled by default.
  • Reports saved to $ARENA_AGENT_HOME/reports/bact-* (default ~/arena-bridge/reports/).

Bridge integration

The Bridge exposes browseract status via arena/admin/browseract.py. Query it with:

GET /v1/capabilities   → browser section includes browseract_installed / version / update_hint

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free