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 hashgraph-online/hol-guard-pluginnpx agentmods add plugins/hashgraph-online/hol-guard-plugin/wshobson-agentsgit clone --depth 1 https://github.com/hashgraph-online/hol-guard-pluginWrote 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/hashgraph-online/hol-guard-plugin/wshobson-agents)<a href="https://agentmods.dev/plugins/hashgraph-online/hol-guard-plugin/wshobson-agents"><img src="https://agentmods.dev/badge/plugins/hashgraph-online/hol-guard-plugin/wshobson-agents.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
wshobson-agents 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": "hol-guard",
"version": "0.1.0",
"description": "Local pre-execution security controls and pre-install scanning for AI agent tools, packages, skills, plugins, and MCP servers.",
"author": {
"name": "Hashgraph Online",
"url": "https://github.com/hashgraph-online"
},
"homepage": "https://github.com/hashgraph-online/hol-guard",
"repository": "https://github.com/hashgraph-online/hol-guard-plugin",
"license": "Apache-2.0",
"keywords": [
"hol-guard",
"ai-security",
"agent-security",
"plugin-security",
"mcp-security",
"supply-chain-security"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 38 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 · 21 lines scan A a4a6ea10ac5f
wshobson-agents is a plugin published in the GitHub repository hashgraph-online/hol-guard-plugin (4 stars, last pushed 7d ago), licensed Apache-2.0. 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.
skarn-guard
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.
skarn-recall
Skill: reconstruct what you worked on from your AI coding sessions (recent, stats, redacted export). Reads session content, so it ships separately from skarn-guard. Backed by the Skarn session engine.
healthclaw-guardrails
FHIR AI agent guardrails with 14 MCP tools. PHI redaction on every read, step-up authorization for writes, immutable audit trails, tenant isolation, Curatr data quality evaluation and correction, Fasten Connect EHR ingestion, and HealthEx portable health record export. FHIR R4 US Core v9 (stable) + FHIR R6 ballot3…
logic-lens
Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, semantic errors, and runtime failures that linters miss.
fortify
OpenText Fortify AppSec skills. Use for SAST/DAST/SCA scanning, vulnerability triage, audit workflows, CI/CD pipeline integration, and FCLI commands. Supports Fortify on Demand (FoD) and Software Security Center (SSC).