A command that enables HOL Guard, a local security boundary for a coding-agent workspace. It checks whether the protection tool is available, detects supported agents, installs protection for selected agents, and verifies the result.

Use it to protect supported local coding agents such as Claude Code, Codex, Copilot, Cursor, Gemini, or OpenCode.

It helps prevent an agent from proceeding when the local security enforcement tool denies or cannot verify an action. It also avoids exposing environment-file secrets during setup checks.

protect — Command 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 commands/hashgraph-online/hol-guard-plugin/protect

Clone the repo

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

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 335 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.

Model	Per session	Once invoked
Fable 5	$0.00008	$0.00335
Opus 5	$0.00004	$0.00168
Sonnet 5	$0.00002	$0.00067
Haiku 4.5	$0.00001	$0.00034

Measured 3d ago against content hash 454a5ea80886, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

protect 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.

commands/protect.md · 59 lines

What it actually says

Protect this workspace with HOL Guard

Use HOL Guard as the local security boundary for the active coding-agent workspace.

Safety rules

Do not read .env files or print secrets while checking the workspace.
Do not install packages or modify agent configuration unless the user asked to enable protection.
Fail closed if HOL Guard reports a denial, review requirement, malformed response, or unavailable enforcement hook.

Steps

Check whether HOL Guard is already available:
```
hol-guard status
```
If hol-guard is unavailable, explain that the local prerequisite is:
```
pipx install hol-guard
```
Do not install it automatically without user intent.
Detect supported local agent surfaces:
```
hol-guard detect --json
```

For each agent the user wants protected, use HOL Guard's existing installer. Examples:

hol-guard install claude-code
hol-guard install codex
hol-guard install copilot
hol-guard install cursor
hol-guard install dsh
hol-guard install gemini
hol-guard install openclaw
hol-guard install opencode
hol-guard install antigravity

Verify the resulting local protection:

hol-guard status
hol-guard detect --json

Report which requested agent surfaces are protected and surface any review or failure state instead of silently continuing.

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 · 59 lines · 8 tokens per session scan A 454a5ea80886

Subscribe to this mod's changes

protect is a command published in the GitHub repository hashgraph-online/hol-guard-plugin (4 stars, last pushed 7d ago), licensed Apache-2.0. It adds 8 tokens to every session and 335 once invoked, about $0.0000 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.

Security gemini-cli-extension

protect

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Protect this workspace with HOL Guard

Safety rules

Steps

What this file has done since we first saw it

Other commands, from other repositories

bug-check

status

import-history

nowledge-save-handoff

data-quality-check

model-route