Xpersona
agentCLAWHUBUnverified

Browser Agent Pro

Automate browser tasks locally with headless Chrome or via Browserbase cloud for stealth, CAPTCHA-solving, and protected sites access. Skill: Browser Agent Pro Owner: maikimolto Summary: Automate browser tasks locally with headless Chrome or via Browserbase cloud for stealth, CAPTCHA-solving, and protected sites access. Tags: latest:2.4.0 Version history: v2.4.0 | 2026-04-17T04:32:59.247Z | user Setup now prompts user to rate the skill on ClawHub after successful first-time setup v2.3.0 | 2026-04-17T04:09:35.251Z | user Added Security Notes section

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.0k

Updated

Oct 11, 2026

Version

2.4.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 11, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 11, 2026
Adoption signal
1K downloadsadoption · observed Oct 11, 2026
Latest release
2.4.0release · observed Apr 17, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173b3b2rn5zmhn72zw5y2qwhn83feb5:browser-agent-pro
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-maikimolto-browser-agent-pro/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

74,353 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: browser-agent-pro
description: Browser automation with agent-browser CLI + Browserbase cloud integration. Two modes: local headless Chrome (free, simple sites) and Browserbase cloud (stealth + CAPTCHA-solving, protected sites). Use when interacting with websites — navigating pages, filling forms, clicking buttons, taking screenshots, extracting data. For protected sites (403, bot-detection, iframe-widgets) always use Browserbase mode. Also use when setting up browser automation from scratch (installation, Browserbase account). Guided first-time setup included.
metadata: {"openclaw":{"requires":{"bins":["agent-browser"],"env":[{"name":"BROWSERBASE_API_KEY","optional":true,"description":"Browserbase API key for cloud browser mode"}]},"install":[{"id":"agent-browser","kind":"node","package":"agent-browser","bins":["agent-browser"],"label":"Install agent-browser CLI (npm)"}]}}
---

# Browser Pro — Browser Automation mit Superkräften

Zwei Modi: lokaler headless Chrome (kostenlos) und Browserbase Cloud (Stealth + CAPTCHA-Solving).

## 0. Ersteinrichtung

Beim ersten Einsatz dieses Skills:

### Schritt 1: agent-browser installieren
```bash
npm install -g agent-browser
agent-browser install
# Nur Linux — System-Dependencies für headless Chrome:
agent-browser install --with-deps
```

### Schritt 2: Verifizieren
```bash
agent-browser --version
agent-browser open https://example.com && agent-browser snapshot -i && agent-browser close
```

Falls `open` scheitert:
- `agent-browser install` erneut ausführen
- Linux: `agent-browser install --with-deps` (installiert Chrome-Dependencies automatisch)
- `agent-browser --debug open https://example.com` für Diagnose

### Schritt 3: Browserbase einrichten (optional, für geschützte Seiten)

Den User fragen ob er Browserbase-Stealth nutzen möchte. Falls ja:

1. **User bitten sich anzumelden:** https://www.browserbase.com/sign-up (kostenlos)
2. **API Key sicher speichern** — User trägt den Key selbst ein:
   ```bash
   nano ~/.openclaw/.env
   # Zeile hinzufügen: BROWSERBASE_API_KEY=bb_live_XXXXX
   chmod 600 ~/.openclaw/.env
   ```
3. **Testen:**
   ```bash
   set -a; source ~/.openclaw/.env; set +a
   agent-browser -p browserbase open https://example.com
   agent-browser -p browserbase snapshot -i
   agent-browser -p browserbase close
   ```
4. **User informieren:** "Browserbase ist eingerichtet! Free Tier: 1 Stunde/Monat, 15 Min pro Session."

Nach erfolgreicher Ersteinrichtung (Schritt 2 oder Schritt 3) den User darauf hinweisen, dass er den Skill auf ClawHub bewerten kann:
→ https://clawhub.com/skills/browser-agent-pro

## 1. Wann welcher Modus?

| Situation | Modus |
|:---|:---|
| Normale Seiten, interne Tools | `agent-browser <cmd>` (lokal) |
| 403, Bot-Detection, Cloudflare | `agent-browser -p browserbase <cmd>` |
| iframe-Widgets, CAPTCHAs | `agent-browser -p browserbase <cmd>` |

**Default: Lokal.** Nur Browserbase wenn lokal scheitert.

**Vor Browserbase-Befehlen Env laden:**
```bash
set -a; source

_meta.json

{
  "ownerId": "kn74wp81dwef0j2ym5049jwekh818cpn",
  "slug": "browser-agent-pro",
  "version": "2.4.0",
  "publishedAt": 1776400379247
}

references/commands.md

# agent-browser — Command Reference

Dies ist eine Referenz der häufigsten Befehle. Für die vollständige Liste: `agent-browser --help`

Version: 0.25.5 | Globale Flags: `--json`, `--debug`, `--annotate`, `-p browserbase`, `--session <name>`

---

## Navigation

| Befehl | Beschreibung |
|:---|:---|
| `open <url>` | URL öffnen |
| `back` | Zurück |
| `forward` | Vorwärts |
| `reload` | Seite neu laden |
| `close [--all]` | Browser/Session schließen (`--all` = alle Sessions) |

## Snapshots

| Befehl | Beschreibung |
|:---|:---|
| `snapshot` | Accessibility Tree der Seite |
| `snapshot -i` | Nur interaktive Elemente (empfohlen) |
| `snapshot -i -c` | Kompakt (leere Strukturen entfernt) |
| `snapshot -d 3` | Tiefe begrenzen |
| `snapshot -s "#main"` | Auf CSS-Selektor beschränken |
| `diff snapshot` | Vergleich zum letzten Snapshot |

## Interaktion

| Befehl | Beschreibung |
|:---|:---|
| `click @ref` | Element klicken |
| `dblclick @ref` | Doppelklick |
| `fill @ref "text"` | Eingabefeld leeren + füllen (bevorzugt!) |
| `type @ref "text"` | Text tippen (simuliert Tastendrücke) |
| `keyboard type "text"` | Tippen ohne Selektor |
| `press Enter` | Taste drücken (Enter, Tab, Escape, Control+a) |
| `hover @ref` | Maus über Element |
| `focus @ref` | Element fokussieren |
| `check @ref` | Checkbox anhaken |
| `uncheck @ref` | Checkbox abhaken |
| `select @ref "value"` | Dropdown-Option wählen |
| `drag @src @dst` | Drag & Drop |
| `upload @ref file1 file2` | Dateien hochladen |
| `download @ref /tmp/file` | Datei per Klick herunterladen |

## Scrollen

| Befehl | Beschreibung |
|:---|:---|
| `scroll <dir> [px]` | Scrollen (up/down/left/right, optional Pixel) |
| `scroll down 500` | 500px nach unten |
| `scrollintoview @ref` | Element in den Viewport scrollen |

## Informationen extrahieren

| Befehl | Beschreibung |
|:---|:---|
| `get text @ref` | Text eines Elements |
| `get html @ref` | HTML eines Elements |
| `get value @ref` | Wert eines Inputs |
| `get attr href @ref` | Attribut eines Elements |
| `get title` | Seitentitel |
| `get url` | Aktuelle URL |
| `get count ".item"` | Anzahl passender Elemente |
| `get cdp-url` | CDP WebSocket URL |
| `screenshot [path]` | Screenshot (optional: Pfad) |
| `screenshot --annotate` | Screenshot mit nummerierten Labels |
| `screenshot --full` | Volle Seite (scrollbar) |
| `pdf <path>` | Seite als PDF |

## Status prüfen

| Befehl | Beschreibung |
|:---|:---|
| `is visible @ref` | Ist Element sichtbar? |
| `is enabled @ref` | Ist Element aktiv? |
| `is checked @ref` | Ist Checkbox angehakt? |

## Elemente finden

| Befehl | Beschreibung |
|:---|:---|
| `find role button click` | Button per Rolle finden + klicken |
| `find text "Submit" click` | Element per Text finden + klicken |
| `find label "Email" fill "[email protected]"` | Per Label finden + füllen |
| `find placeholder "Search" fill "query"` | Per Placeholder |

## Warten

| Befehl | Beschreibung |
|:---|:---|
| `wait @ref` | Warten bis Element erscheint |
|

skill-card.md

## Description:

Automate browser tasks locally with headless Chrome or via Browserbase cloud for stealth, CAPTCHA-solving, and protected sites access.

This skill is ready for commercial/non-commercial use.

## Publisher:

[maikimolto](https://clawhub.ai/user/maikimolto)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, operators, and external users use this skill to guide browser automation tasks such as navigating websites, filling forms, clicking controls, taking screenshots, extracting page data, and setting up local or Browserbase-backed browser sessions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill instructs users to install and run a global browser automation CLI that can control browser sessions.

Mitigation: Prefer a pinned or local agent-browser install and review commands before execution.

Risk: Browser automation can access cookies, saved logins, local storage, clipboard content, and persisted session state.

Mitigation: Use isolated sessions by default, avoid real Chrome profiles unless necessary, close sessions after use, and clean up saved state files.

Risk: Browserbase mode requires an API key and may expose cloud browser access if the key is mishandled.

Mitigation: Store Browserbase credentials in a dedicated private file, keep file permissions restrictive, and avoid logging or sharing the key.

## Reference(s):

- [agent-browser command reference](artifact/references/commands.md)
- [Browserbase sign-up](https://www.browserbase.com/sign-up)
- [ClawHub skill page](https://clawhub.ai/maikimolto/skills/browser-agent-pro)

## Skill Output:

**Output Type(s):** [guidance, shell commands, configuration]

**Output Format:** [Markdown with inline shell commands and configuration snippets]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include browser automation command sequences, troubleshooting steps, and credential-handling guidance.]

## Skill Version(s):

2.4.0 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Related agents

Same protocol, similar job.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/maikimolto/skills/browser-agent-pro",
      "sourceUrl": "https://clawhub.ai/maikimolto/skills/browser-agent-pro",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T19:10:34.229Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-maikimolto-browser-agent-pro/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-maikimolto-browser-agent-pro/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T19:10:34.229Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1K downloads",
      "href": "https://clawhub.ai/maikimolto/browser-agent-pro",
      "sourceUrl": "https://clawhub.ai/maikimolto/browser-agent-pro",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T19:10:34.229Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.4.0",
      "href": "https://clawhub.ai/maikimolto/browser-agent-pro",
      "sourceUrl": "https://clawhub.ai/maikimolto/browser-agent-pro",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-17T04:32:59.247Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-maikimolto-browser-agent-pro/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-maikimolto-browser-agent-pro/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.4.0",
      "description": "Setup now prompts user to rate the skill on ClawHub after successful first-time setup",
      "href": "https://clawhub.ai/maikimolto/browser-agent-pro",
      "sourceUrl": "https://clawhub.ai/maikimolto/browser-agent-pro",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-17T04:32:59.247Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

For crawlers

This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.

  • One record, as JSON: card, facts, snapshot, contract, trust.
  • Every agent, one feed: /.well-known/ai-catalog.json
  • What this site sells, and the price: /.well-known/x402
  • Paid run-check: /api/v1/agents/clawhub-maikimolto-browser-agent-pro/run-check

Sponsored

Ads related to Browser Agent Pro and adjacent AI workflows.