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.
git clone --depth 1 https://github.com/jongko54/webEmbeddingWrote 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/plugins/jongko54/webembedding/source-first-clone)<a href="https://agentmods.dev/plugins/jongko54/webembedding/source-first-clone"><img src="https://agentmods.dev/badge/plugins/jongko54/webembedding/source-first-clone/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/plugins/jongko54/webembedding/source-first-clone"><img src="https://agentmods.dev/badge/plugins/jongko54/webembedding/source-first-clone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
source-first-clone 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 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.
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.
What it actually says
{
"name": "source-first-clone",
"version": "0.3.9",
"description": "Source-first URL clone, capture, bounded rebuild, and fidelity verification workflow.",
"author": {
"name": "Jongho"
},
"homepage": "https://webembedding-mcp.vercel.app/",
"repository": "https://github.com/jongko54/webEmbedding",
"license": "MIT",
"keywords": [
"source-first",
"website-cloning",
"mcp",
"playwright",
"fidelity"
],
"skills": "./skills/",
"mcpServers": {
"source-first-clone": {
"command": "python3",
"args": [
"${CLAUDE_PLUGIN_ROOT}/mcp/server.py"
],
"cwd": "${CLAUDE_PLUGIN_ROOT}",
"autoStart": false
}
}
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 74 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 30 lines scan A 6f69b3854804
source-first-clone is a plugin published in the GitHub repository jongko54/webEmbedding (5 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
webcmd
Self-learning browser infrastructure for AI agents: live browser control plus local sitemap memory that makes repeat runs faster and cheaper.
unbrowse
Websites as APIs for Claude Code: the hosted Unbrowse MCP (discover, run, scrape, cloud browser, saved logins) plus its skill. Replaces WebFetch, WebSearch and browser MCPs with Unbrowse.
unbrowse
Websites as APIs: read pages, run site tasks via learned APIs, and a cloud browser with saved logins.
cli-anything-web
CLI-Anything for the Web: Generate agent-native CLIs for closed-source web apps via network traffic analysis.
playwright-bot-bypass
Bypass bot detection using rebrowser-playwright (Node.js) or undetected-chromedriver (Python). Passes bot.sannysoft.com fingerprint checks and automates Google without triggering CAPTCHA. Authorized-use only — respect each site's ToS.
paranoid-qa-ru
A Russian-language quality-assurance add-on for testing web applications with Playwright, a browser automation tool, and reviewing those tests.