wshobson-agents

wshobson-agents is a plugin for Claude Code from hashgraph-online/hol-guard-plugin. Its manifest loads nothing; the 1 skill it bundles cost 38 tokens per session together, scanned A, original, Apache-2.0.

A plugin that adds local security checks before AI-agent tools are run or installed. It scans tools, packages, skills, plugins, and MCP servers for risks; MCP servers are connections that let an assistant use external tools.

In plain words
What is it for?
Use it for pre-install scanning and pre-execution controls around AI-agent tools and their software supply chain.
Why use it?
It helps inspect agent add-ons and dependencies before they are allowed into the execution environment.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add hashgraph-online/hol-guard-plugin
agentmods
npx agentmods add plugins/hashgraph-online/hol-guard-plugin/wshobson-agents
Clone the repo
git clone --depth 1 https://github.com/hashgraph-online/hol-guard-plugin

Made for: Claude Code.

Wrote 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.

agentmods badge for wshobson-agents

README.md
[![agentmods](https://agentmods.dev/badge/plugins/hashgraph-online/hol-guard-plugin/wshobson-agents.svg)](https://agentmods.dev/plugins/hashgraph-online/hol-guard-plugin/wshobson-agents)
Your own site
<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>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 38 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

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.

distributions/wshobson-agents/.claude-plugin/plugin.json · 21 lines

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"
  ]
}
Contents

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.

Changes

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.

  1. 3d ago First seen · 21 lines scan A a4a6ea10ac5f

Subscribe to this mod's changes

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.

Related

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/Shopify-AI-Toolkit · not measured

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-security/agent-guard · not measured

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.

skarn-security/agent-guard · not measured

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…

aks129/HealthClawGuardrails · not measured

logic-lens

Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, semantic errors, and runtime failures that linters miss.

hyhmrright/logic-lens · not measured

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).

fortify/skills · not measured