Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add SuperTapir/web-twin-plugin/plugin install web-twinWrote 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/supertapir/web-twin-plugin/web-twin)<a href="https://agentmods.dev/skills/supertapir/web-twin-plugin/web-twin"><img src="https://agentmods.dev/badge/skills/supertapir/web-twin-plugin/web-twin.svg" alt="Measured on agentmods" 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 | $0.00149 | $0.01205 |
| Opus 5 | $0.00075 | $0.00602 |
| Sonnet 5 | $0.00030 | $0.00241 |
| Haiku 4.5 | $0.00015 | $0.00120 |
Grade A, and why
web-twin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebTwin - Website Extraction & Cloning
Based on WebTwin by Sirio Berati, MIT license.
How to Use (Follow This Order)
Step 1: Ensure dependencies are installed
Run this FIRST, every time. Do NOT skip.
pip install requests beautifulsoup4 urllib3 2>/dev/null
Selenium is optional (for JS-rendered pages). Check with:
python3 -c "import selenium; print('ok')" 2>/dev/null && echo "Selenium available" || echo "Selenium not available, will use HTTP fallback"
Step 2: Run extraction
Write a single Python script. The reference/ directory inside this skill is a ready-to-use package.
import sys
sys.path.insert(0, "${CLAUDE_PLUGIN_ROOT}/skills/web-twin")
from reference import extract_website, is_selenium_available
url = "TARGET_URL_HERE"
output_dir = "/tmp/webtwin-output"
result = extract_website(
url,
output_path=output_dir,
use_selenium=is_selenium_available(), # auto-detect
)
print(f"Title: {result.metadata.title}")
print(f"CSS: {len(result.assets.css)}, JS: {len(result.assets.js)}, Images: {len(result.assets.img)}")
print(f"Components: {list(k for k, v in result.components.to_dict().items() if v)}")
print(f"Saved to: {result.output_path}")
That's it. The module handles Selenium fallback, anti-detection, and asset downloading automatically.
Step 3: Present results
Summarize: title, resource counts, detected components, output path.
API Reference
extract_website(url, *, use_selenium=True, download_assets=True, output_path=None, timeout=30) -> ExtractResult
| Parameter | Type | Default | Description |
|---|---|---|---|
url |
str |
required | Target URL (auto-adds https://) |
use_selenium |
bool |
True |
Headless Chrome for JS rendering |
download_assets |
bool |
True |
Download assets to disk |
output_path |
str | Path | None |
None |
Output dir (default: /tmp/webtwin/) |
timeout |
int |
30 |
Request timeout in seconds |
What ships with it
10 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.
- reference/__init__.py 1.0 KB runs code
- reference/cli.py 2.3 KB runs code
- reference/downloader.py 8.5 KB runs code
- reference/extractor.py 16 KB runs code
- reference/logger.py 945 B runs code
- reference/models.py 3.1 KB runs code
- reference/parser.py 17 KB runs code
- reference/renderer.py 11 KB runs code
- reference/requirements.txt 142 B
- reference/utils.py 4.0 KB runs code
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.
- 8d ago First seen · 126 lines · 149 tokens per session scan A b0fc3d667ea9
web-twin is a skill published in the GitHub repository SuperTapir/web-twin-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 149 tokens to every session and 1,205 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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.
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…
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.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…