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.
/plugin marketplace add sivang/sivan-claude-pluginsnpx agentmods add plugins/sivang/sivan-claude-plugins/site-auditgit clone --depth 1 https://github.com/sivang/sivan-claude-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/sivang/sivan-claude-plugins/site-audit)<a href="https://agentmods.dev/plugins/sivang/sivan-claude-plugins/site-audit"><img src="https://agentmods.dev/badge/plugins/sivang/sivan-claude-plugins/site-audit.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
site-audit 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 3d 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-audit",
"version": "1.0.0",
"description": "Crawl a website and produce a comprehensive quality audit covering broken links, spelling errors, console errors, and visual issues",
"author": {
"name": "Sivan Grünberg",
"email": "[email protected]",
"url": "https://vitakka.co"
}
}
What it installs
The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 70 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.
- 3d ago First seen · 11 lines scan A a2e81de13029
site-audit is a plugin published in the GitHub repository sivang/sivan-claude-plugins (1 stars, last pushed 7mo 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
odin
ODIN - advanced code agent with diagram-first engineering and atomic commit workflows for surgical precision in software development.
genesis
Three modes for Claude Code projects: create a new one from an empty folder (research and design before stack, then build and test it), transition an existing repository to a stated standard, and check the user-level /.claude layer that loads in every session. English-first, with secret denials and human gates on anyt.
backlog
Project backlog manager — records deferred tasks into docs/backlogs/ only when the user asks, when Claude gets consent to defer an unrelated bug or out-of-scope side task, or in a background session needing the user's decision. Never captures silently. Commands to list and manage. Files-based, in-repo, no execution…
brevity
Claude Code says less, and says it straight. Short replies, no jargon, no preamble. Applies ASD-STE100 Simplified Technical English to long replies.
agent-critter marketplace
Agent Critter — Claude Code 桌面宠物插件，兼容 Petdex 2700+ 精灵.
rodrigopg marketplace
Personal Claude Code plugins by Rodrigo Gonçalves.