Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/browser-useWrote 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/pramoddutta/qaskills/browser-use)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/browser-use"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/browser-use/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/pramoddutta/qaskills/browser-use"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/browser-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 709 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Data Exfiltration · line 640 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 421 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00038 | $0.04868 |
| Opus 5.5 | $0.00015 | $0.01947 |
| Sonnet 5.5 | $0.00008 | $0.00974 |
| Haiku 4.5 | $0.00004 | $0.00487 |
Grade B, and why
Browser-Use Automation scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST https://alerts.example.com/notify -d "$STATUS" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://alerts.example.com/notify -d "$STATUS" How it starts
The opening of the file, as written. The whole thing — 772 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser-Use Automation Skill
You are an expert in browser automation using browser-use, a powerful CLI tool designed for persistent, multi-session browser automation. When the user asks you to automate complex browser workflows, manage sessions, or perform long-running automation tasks, follow these detailed instructions.
Core Principles
- Persistent sessions -- Maintain browser state across multiple automation runs.
- Multi-session support -- Run multiple isolated browser sessions in parallel.
- Flexible browser modes -- Support for Chromium (headless), Real (headed), and Remote browser instances.
- Cookie management -- Export, import, and manage cookies for authentication persistence.
- JavaScript execution -- Execute custom JavaScript in page context for advanced automation.
Installation
# Install via npm
npm install -g browser-use
# Or use with npx
npx browser-use --version
# Install with Python
pip install browser-use
# Verify installation
browser-use --help
Browser Modes
Chromium Mode (Default Headless)
# Launch Chromium in headless mode
browser-use start --mode chromium --headless
# With custom user data directory
browser-use start --mode chromium --user-data-dir ./browser-data
# With custom viewport
browser-use start --mode chromium --viewport 1920x1080
Real Browser Mode (Headed)
# Launch visible Chrome browser
browser-use start --mode real --browser chrome
# Launch Firefox
browser-use start --mode real --browser firefox
# Launch with specific profile
browser-use start --mode real --browser chrome --profile "Profile 1"
Remote Browser Mode
# Connect to remote Chrome DevTools Protocol
browser-use start --mode remote --cdp-url ws://localhost:9222
# Connect to Selenium Grid
browser-use start --mode remote --selenium-url http://localhost:4444/wd/hub
Session Management
Creating and Managing Sessions
# Create named session
browser-use session create --name "user-session-1" --persist
# List all sessions
browser-use session list
# Attach to existing session
browser-use session attach --name "user-session-1"
# Delete session
browser-use session delete --name "user-session-1"
# Export session state
browser-use session export --name "user-session-1" --output ./session-state.json
# Import session state
browser-use session import --input ./session-state.json --name "restored-session"
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 · 772 lines · 38 tokens per session scan B e6bfe12fdc7a
Browser-Use Automation is a skill published in the GitHub repository PramodDutta/qaskills (237 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 4,868 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cursor-browser
Drive Cursor IDE's built-in Browser Tab via cursor-browser-cli. Navigate, ref snapshots, click/type/fill/scroll/select-option by ref, wait-for, lock, screenshot, console/network/inspect. For Grok Build, Claude Code, Codex in Cursor terminal. Triggers: Cursor browser, Browser Tab, /cursor-browser, snapshot, under the…
core
Core chrome-use usage guide. Read this before running any chrome-use commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using chrome-use via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
sessions
Run multiple isolated browser sessions in parallel (each --session = own cookies/tabs/refs), recover a stranded tab by CDP targetId across sessions, --reuse-tab, and reset stuck daemons (daemon status/restart). Use for multi-user flows, parallel scraping, or when a session's tab/handle got stuck.
network
Mock responses, rewrite outgoing requests, block URLs, and record HAR with chrome-use network route (CDP Fetch, no proxy). Use when a task needs to stub an API response, override request headers/body, rewrite a URL to staging, block analytics, or capture/inspect network traffic.