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/skarn-security/agent-guardWrote 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/skarn-security/agent-guard/claude)<a href="https://agentmods.dev/plugins/skarn-security/agent-guard/claude"><img src="https://agentmods.dev/badge/plugins/skarn-security/agent-guard/claude/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/skarn-security/agent-guard/claude"><img src="https://agentmods.dev/badge/plugins/skarn-security/agent-guard/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
skarn-guard 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 12d 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": "skarn-guard",
"version": "0.33.0",
"description": "Real-time guard on five Claude Code pre-execution hook events (tool calls, permission decisions, submitted and expanded prompts, and subagent creation) plus a response-end advisory that flags an action leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and vet configs, redacted). Ships in audit mode, which reports the verdict and never changes what the agent does; blocking needs enforce mode, which registering alone does not unlock. Backed by the Skarn detection engine. It also declares one local MCP server, named skarn, with four tools (scan_sessions, vet_configs, list_sessions, session_stats): every tool is read-only, none of them writes or changes a file, none of them makes a network call, and every matched value comes back masked.",
"author": {
"name": "Skarn",
"url": "https://getskarn.com"
},
"homepage": "https://getskarn.com",
"repository": "https://github.com/skarn-security/agent-guard",
"license": "MIT",
"keywords": [
"security",
"secrets",
"guard",
"skills",
"audit"
]
}
What it installs
The manifest is a name and a version. 6 hooks, 1 MCP server travel with it, and installing the plugin installs all of 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.
- 12d ago Changed 116acde76049
- 22d ago Changed b5dd9675a81e
- 1mo ago Changed 2c55adec9161
- 1mo ago Changed f7e7fcc93de0
- 1mo ago Changed 31c8960cbcb5
- 1mo ago Changed 519c02519748
- 1mo ago First seen · 20 lines scan A 6ccf2c94dc05
skarn-guard is a plugin published in the GitHub repository skarn-security/agent-guard (36 stars, last pushed 12d 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 2026-08-30.
Other plugins, from other repositories
shopify-plugin
Shopify developer tools for Claude Code — search Shopify docs, generate and validate GraphQL, Liquid, and UI extension code. Skill scripts send usage telemetry (queries, code, model/client identifiers) to shopify.dev by default; set OPTOUTINSTRUMENTATION=true, or create an empty file at /.config/shopify-ai-toolkit/o.
shopify-plugin
shopify-plugin. Agent plugins/extensions for CLIs and IDEs.
looker
Connect to Looker and interact with your data using LookML.
cloud-sql-postgresql
Create, connect, and interact with a Cloud SQL for PostgreSQL database and data.
gerrit
An MCP server for interacting with the Gerrit code review system.
axiom
Use Axiom in your coding agent to search logs, query metrics, and follow traces. Dig into production errors and slow requests, build dashboards, and set up alerts. Includes the Axiom MCP connection and skills for incident response, monitoring, and translating Splunk queries.