hol-guard

hol-guard is a skill for Claude Code from hashgraph-online/hol-guard-plugin. It costs 22 tokens per session (590 once invoked), scanned A, original, Apache-2.0.

A setup and status-check tool for HOL Guard, a separate local security package that protects OpenClaw, an AI agent platform. It uses the hol-guard command-line program as the authority for its settings and evidence.

In plain words
What is it for?
Use it when you explicitly need to install, initialize, repair, or check HOL Guard for OpenClaw.
Why use it?
It helps you install, start, repair, or verify the protection without assuming that installing this add-on has activated it.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: built for openclaw.

Part of the hol-guard plugin — 1 skill, 2 commands, 1 MCP server, 1 plugin shipped together

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.

agentmods
npx agentmods add skills/hashgraph-online/hol-guard-plugin/hol-guard
Any agent
npx skills add hashgraph-online/hol-guard-plugin --skill hol-guard
Clone the repo
git clone --depth 1 https://github.com/hashgraph-online/hol-guard-plugin

Made for: Claude Code.

Or install hol-guard, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 MCP server, 1 plugin.

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 hol-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashgraph-online/hol-guard-plugin/hol-guard.svg)](https://agentmods.dev/skills/hashgraph-online/hol-guard-plugin/hol-guard)
Your own site
<a href="https://agentmods.dev/skills/hashgraph-online/hol-guard-plugin/hol-guard"><img src="https://agentmods.dev/badge/skills/hashgraph-online/hol-guard-plugin/hol-guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00590
Opus 5 $0.00011 $0.00295
Sonnet 5 $0.00004 $0.00118
Haiku 4.5 $0.00002 $0.00059

Measured 6d ago against content hash 3a758e121092, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hol-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 6d 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/clawhub/hol-guard/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HOL Guard for OpenClaw

Use this skill only when the user explicitly asks to install, enable, initialize, repair, or check HOL Guard.

HOL Guard is a separate open-source local runtime package. This ClawHub skill is a discovery and setup surface. The hol-guard CLI remains the security authority and owns OpenClaw integration, policy, approvals, and evidence.

Canonical source: https://github.com/hashgraph-online/hol-guard

Check current state

Start with read-only checks:

command -v hol-guard

If Guard is installed, run:

hol-guard --version
hol-guard status

Report only what the CLI proves. Installing this skill alone does not mean runtime protection is active.

If the user asked only to check Guard, stop after hol-guard status. Do not install or initialize Guard.

Install or initialize

Continue with setup only when the user explicitly asked to install, enable, initialize, or repair Guard.

If hol-guard is missing, explain that the next command changes the user's Python/pipx environment and obtain explicit approval before running it:

pipx install hol-guard

If pipx is unavailable, stop and tell the user that the documented HOL Guard install path requires pipx. Do not silently switch package managers and do not execute a remote bootstrap script as a fallback.

After Guard is available, initialize protection interactively:

hol-guard init

Do not add unattended flags unless the user explicitly requests unattended setup. hol-guard init owns the real OpenClaw integration and avoids maintaining a second enforcement implementation in this skill.

Verify the resulting state:

hol-guard status

If protection is degraded, report the failed layer and let the Guard CLI or core documentation drive repair. Do not manually rewrite OpenClaw configuration from this skill unless the core HOL Guard documentation explicitly requires it.

Local-first boundary

Guard Cloud is optional. Do not require sign-in, credentials, or cloud connectivity for local OpenClaw protection. Offer cloud connection only if the user asks for synchronized history, shared policy, fleet visibility, or team approvals.

Read the full file on GitHub · 76 lines

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. 6d ago First seen · 76 lines · 22 tokens per session scan A 3a758e121092

Subscribe to this mod's changes

hol-guard is a skill published in the GitHub repository hashgraph-online/hol-guard-plugin (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 590 once invoked, about $0.0001 per session on Opus 5. 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens