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/a8cteam51/claude-code-pluginsWrote 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/a8cteam51/claude-code-plugins/site-launch-comparison)<a href="https://agentmods.dev/plugins/a8cteam51/claude-code-plugins/site-launch-comparison"><img src="https://agentmods.dev/badge/plugins/a8cteam51/claude-code-plugins/site-launch-comparison/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/a8cteam51/claude-code-plugins/site-launch-comparison"><img src="https://agentmods.dev/badge/plugins/a8cteam51/claude-code-plugins/site-launch-comparison.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
site-launch-comparison 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": "site-launch-comparison",
"version": "1.0.0",
"description": "Capture full-page before/after screenshots of two versions of a website and build a self-contained side-by-side HTML comparison report. Built for re-themes, redesigns and replatforms, and for routine staging-vs-production design QA. Handles bot-check interstitials, cookie banners, lazy-loaded images, and agent shell time limits.",
"author": {
"name": "Automattic Special Projects"
},
"repository": "https://github.com/a8cteam51/claude-code-plugins",
"license": "MIT",
"keywords": [
"before-after",
"design-qa",
"migration",
"playwright",
"redesign",
"relaunch",
"screenshots",
"site-launch",
"staging",
"visual-regression",
"wordpress"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 134 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 · 24 lines scan A 0bbecfb6e73d
site-launch-comparison is a plugin published in the GitHub repository a8cteam51/claude-code-plugins (5 stars, last pushed 2d 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 2026-09-16.
Other plugins, from other repositories
pencil-replicator
A browser-to-design capture tool that recreates the web page currently shown in Chrome as a Pencil (.pen) file. It uses separate agents to analyze, build, and check the result.
ux-review
Experiential UX review that drives the RUNNING app as a real user — not a code read. Reading source is a code review and structurally cannot find experience defects (a mode that doesn't do what its label claims, an overlay anchored to the wrong thing, a feature that silently breaks in one state, a table-stakes…
annotate
Point-and-comment on your live local web app in a Playwright browser; comments flow back to Claude Code to fix. Inspect-element hover with a computed-style card, comment-pin markers, crosshair cursor, Shift-to-click-through, and a UI that auto-themes to your app. Requires a Playwright MCP server (bundled by default).
UI Annotator
MCP server that annotates any web page with hover labels for AI assistants.
annotate
Draw on a live frontend in the Playwright browser and feed the annotated screenshot straight back into the Claude Code session. Fully local, no cloud, no extension.
itkdev-browser-feedback
Browser-based visual feedback and annotation MCP server for Claude Code.