Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add IvanSkainet/arena-agent --skill browseractgit clone --depth 1 https://github.com/IvanSkainet/arena-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ivanskainet/arena-agent/browseract)<a href="https://agentmods.dev/skills/ivanskainet/arena-agent/browseract"><img src="https://agentmods.dev/badge/skills/ivanskainet/arena-agent/browseract/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ivanskainet/arena-agent/browseract"><img src="https://agentmods.dev/badge/skills/ivanskainet/arena-agent/browseract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00651 |
| Opus 5.5 | $0.00000 | $0.00260 |
| Sonnet 5.5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
browseract scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `agentctl http <url>` — raw curl, no JS, cheapest. How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browseract
Wrapper around the browser-act CLI for stealth-aware browser
automation. Works on Windows, macOS, and Linux.
Install (one-time)
BrowserAct is not bundled with Arena. Install it via uv — a single command that works identically on every OS:
uv tool install browser-act-cli --python 3.12
Then verify:
python skills/browseract/run.py doctor
You should see the CLI version and handshake: ok.
Update
uv tool upgrade browser-act-cli
Subcommands
The Python wrapper (run.py) works on every platform; the historical
run.sh remains for callers that expect a bash entrypoint on *nix.
Run via python skills/browseract/run.py <sub> (or the bash wrapper on
*nix / from agentctl bact <sub>):
doctor— check install + handshakeextract <url>— stealth-extract URL as markdown (saved under$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, navigatestate— show current page stateclick <index>— click element by indextype <text>— type into focused elementinput <index> <text>— click then typeeval <js>— execute JS, return resultclose— close current sessionauth {set <KEY> | clear | status}— manage browser-act API keybrowsers— list configured browsersraw <args...>— pass-through tobrowser-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/).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 82 lines · 0 tokens per session scan A c462258beb12
browseract is a skill published in the GitHub repository IvanSkainet/arena-agent (9 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 651 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
yutori-computer-use
Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop, or to work across app windows in the background while they keep working.
vibesurfer
Agent-native headless browser. 26 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines verified per-commit by a real-browser integration suite. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state…
browser-use
Drives web pages with the browseruse tool through one checked pipeline - pick the right web tool, open the page in the chat's own tab, write down how the result will be checked, find elements by ref, act in small steps, read the page back, fix what differs, report only what the page shows. Explains which browser a…
yutori-browse
Automate browser tasks like form filling, data extraction, or multi-step web workflows. Use when the user needs to interact with websites that require clicking, typing, or navigation.
eric-task-master
Run durable local Chrome automation with the installed Task Master CLI. Use when an Agent needs to create and execute a one-off browser task, follow its progress, or manage its Chrome Profile.