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 PramodDutta/qaskills --skill agent-browsergit clone --depth 1 https://github.com/PramodDutta/qaskillsWrote 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/agent-browser)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/agent-browser"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/agent-browser/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/agent-browser"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 630 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 MCP Rug Pull · line 34 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]
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 | $0.00037 | $0.04818 |
| Opus 5.5 | $0.00015 | $0.01927 |
| Sonnet 5.5 | $0.00007 | $0.00964 |
| Haiku 4.5 | $0.00004 | $0.00482 |
Grade A, and why
Agent Browser Automation 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 683 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser Automation Skill
You are an expert in browser automation using agent-browser, a fast Rust-based CLI tool designed specifically for AI coding agents. When the user asks you to automate browser interactions, perform web scraping, or test web applications, follow these detailed instructions.
Core Principles
- Speed-first architecture -- Rust core provides millisecond-level responsiveness for agent commands.
- Structured output -- All commands return JSON output optimized for AI agent parsing.
- Fallback resilience -- Automatically falls back to Node.js implementation when Rust binary is unavailable.
- Agent-optimized commands -- CLI designed for programmatic control, not human interaction.
- Snapshot-driven debugging -- Every action can capture page snapshots for AI agent analysis.
Installation
# Install globally via npm
npm install -g agent-browser
# Or use npx without installation
npx agent-browser --version
# Verify installation
agent-browser --help
Project Structure for Agent-Driven Testing
tests/
browser-automation/
scenarios/
login-flow.json
checkout-flow.json
search-navigation.json
snapshots/
login-success.png
cart-state.png
scripts/
run-scenario.sh
batch-test.sh
config/
browser-config.json
viewport-sizes.json
Core Commands
Navigation Commands
# Navigate to URL
agent-browser navigate --url "https://example.com"
# Navigate with custom viewport
agent-browser navigate --url "https://example.com" --viewport "1920x1080"
# Navigate with custom user agent
agent-browser navigate --url "https://example.com" \
--user-agent "Mozilla/5.0 (iPhone; CPU iPhone OS 14_0 like Mac OS X)"
# Navigate and wait for network idle
agent-browser navigate --url "https://example.com" --wait-until "networkidle"
Output:
{
"success": true,
"url": "https://example.com",
"title": "Example Domain",
"loadTime": 234,
"timestamp": "2024-02-12T10:30:00Z"
}
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 · 683 lines · 37 tokens per session scan A 91bbeb68dbf4
Agent Browser Automation is a skill published in the GitHub repository PramodDutta/qaskills (237 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 4,818 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
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.