A setup procedure for installing and initializing HOL Guard, a local runtime protection tool for Claude Code. It checks whether the tool exists, installs it only with approval, initializes it, and verifies its status.

Use it to check for HOL Guard, install it through pipx after approval, run its interactive initialization, and confirm that protection is active.

It provides a controlled setup path for adding local protection without silently installing software or replacing the tool's own initialization process.

setup — Skill by hashgraph-online

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/setup

Any agent

npx skills add hashgraph-online/hol-guard --skill setup

Clone the repo

git clone --depth 1 https://github.com/hashgraph-online/hol-guard

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 372 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00033	$0.00372
Opus 5	$0.00016	$0.00186
Sonnet 5	$0.00007	$0.00074
Haiku 4.5	$0.00003	$0.00037

Measured 3d ago against content hash 94f644ee1bc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

If `pipx` is unavailable, stop and show the user the install requirement. Do not curl or execute an unreviewed bootstrap script as a fallback.

integrations/claude-code-plugin/skills/setup/SKILL.md · 46 lines

What it actually says

Set up HOL Guard for Claude Code

HOL Guard is a separate open-source local runtime package. This plugin is the Claude Code discovery and setup companion; the actual security boundary is installed and maintained by the hol-guard CLI.

Follow this sequence exactly:

Check whether HOL Guard is already available without changing the machine:
```
command -v hol-guard && hol-guard --version
```
If hol-guard is missing, explain that installation changes the user's Python/pipx environment and ask for explicit approval before installing it. Do not silently substitute another package manager.
After approval, install from PyPI with the documented command:
```
pipx install hol-guard
```
If pipx is unavailable, stop and show the user the install requirement. Do not curl or execute an unreviewed bootstrap script as a fallback.
Initialize Guard interactively:
```
hol-guard init
```
Do not add --yes unless the user explicitly requests unattended setup. hol-guard init owns Claude Code hook installation and avoids maintaining a second security implementation in this plugin.
Verify the resulting local protection:
```
hol-guard status
```
Tell the user what Guard reports as active or degraded. Do not claim protection from plugin installation alone.

HOL Guard works locally without Guard Cloud. Cloud connection is optional and should only be offered when the user asks for synchronized history, team policy, fleet visibility, or shared approvals.

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.

3d ago First seen · 46 lines · 33 tokens per session scan A 94f644ee1bc3

Subscribe to this mod's changes

setup is a skill published in the GitHub repository hashgraph-online/hol-guard (504 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 372 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Security agent-security ai-agent-security ai-agents codex mcp

setup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

What it actually says

Set up HOL Guard for Claude Code

What this file has done since we first saw it

Other skills, from other repositories

reviewable-demo

valid-complex

safe-greeting

broad-allowed-tools

example-skill

19-public-pattern-plugin-hooks