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 Demerzels-lab/elsamultiskillagent --skill browser-auto-downloadgit clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagentWrote 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/demerzels-lab/elsamultiskillagent/browser-auto-download)<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/browser-auto-download"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/browser-auto-download/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/demerzels-lab/elsamultiskillagent/browser-auto-download"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/browser-auto-download.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 | $0.00104 | $0.01811 |
| Opus 5 | $0.00052 | $0.00905 |
| Sonnet 5 | $0.00021 | $0.00362 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
browser-auto-download scanned grade A 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 9d 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.
description: "Browser-automated file download with enhanced features. Auto-detects platform (Windows/macOS/Linux, 64/32-bit, ARM/Intel), handles multi-step navigation (homepage to platform-specific pages), captures auto- Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run([ How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Auto Download v4.1.0 (Enhanced)
Download files from dynamic webpages with intelligent detection and multi-step navigation.
Key Features
- Auto-download capture: Detects downloads triggered automatically on page load
- Multi-step navigation: Finds and navigates to platform-specific pages (PC/Desktop versions)
- Platform auto-detection: Windows x64/ARM64, macOS Intel/Apple Silicon, Linux
- Event listening: Captures all download events without requiring button clicks
- Smart fallback: Tries multiple strategies (auto-download, navigation, clicking)
When to Use
Use this skill for:
- Auto-download sites: Downloads start automatically when page loads
- Multi-step flows: Homepage - click "PC version" - download page
- Dynamic content: Download links generated via JavaScript
- Interactive downloads: Requires clicking buttons or navigating UI
NOT for: Direct file URLs (use curl/wget instead)
Quick Start
Option 1: Automatic (Recommended)
python skills/browser-auto-download/scripts/auto_download.py \
--url "https://example.com/download"
The script will:
- Check for auto-downloads on page load
- Look for platform-specific page links (PC/Desktop version)
- Navigate if needed
- Try clicking download buttons as fallback
Option 2: Built-in Shortcuts
# WeChat DevTools
python skills/browser-auto-download/scripts/auto_download.py --wechat
# Meitu Xiuxiu
python skills/browser-auto-download/scripts/auto_download.py --meitu
Option 3: Python Module
from skills.browser-auto-download.scripts.auto_download import auto_download
result = auto_download(
url="https://example.com/download",
auto_select=True, # Platform detection
auto_navigate=True # Multi-step navigation
)
if result:
print(f"Downloaded: {result['path']}")
How It Works
Three-Stage Strategy
Stage 1: Auto-Download Detection
Page loads - Check for downloads - Success?
Yes: No:
Save file Go to Stage 2
What ships with it
8 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.
- 9d ago First seen · 277 lines · 104 tokens per session scan A ec952a2a60fd
browser-auto-download is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 1,811 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.