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.
npx skills add hashgraph-online/hol-guard --skill setupgit clone --depth 1 https://github.com/hashgraph-online/hol-guardWrote 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/skills/hashgraph-online/hol-guard/setup)<a href="https://agentmods.dev/skills/hashgraph-online/hol-guard/setup"><img src="https://agentmods.dev/badge/skills/hashgraph-online/hol-guard/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hashgraph-online/hol-guard/setup"><img src="https://agentmods.dev/badge/skills/hashgraph-online/hol-guard/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00033 | $0.00372 |
| Opus 5.5 | $0.00013 | $0.00149 |
| Sonnet 5.5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
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 1mo 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. 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-guardis 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-guardIf
pipxis 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 initDo not add
--yesunless the user explicitly requests unattended setup.hol-guard initowns 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.
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.
- 1mo ago First seen · 46 lines · 33 tokens per session scan A 94f644ee1bc3
setup is a skill published in the GitHub repository hashgraph-online/hol-guard (956 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 372 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
crossval-harness
Orchestrate a static + dynamic, exploit-validated red-team of an AI agent — read the source to find candidate vulnerable paths, then run the dynamic skills to confirm or refute each one empirically. The arbiter of truth is whether the exploit works, not a model vote. Authorized testing of agents you own or are…
redteam-an-agent
The end-to-end methodology for red-teaming a specific AI agent — adaptively, exploit-validated, and honestly. Read THIS target's own code, stand up a disposable harness, and prove or refute each weakness through a real attacker-reachable entry point. This is the orchestration + discipline that makes a finding…
audit-agent-code
Security-audit an AI agent's OWN framework code for classic appsec vulnerabilities the LLM can't defend — path traversal, command injection, SSRF, fail-open security controls, missing/late auth, unsafe deserialization — especially at the untrusted-input boundaries (channels, file/media handlers, config & skill…
rt6-memory-poisoning
Red-team an AI agent's persistent memory for cross-session prompt injection ("memory poisoning") — does untrusted content the agent processes get written into long-term memory and re-fire in future sessions with no attacker present? Authorized testing of agents you own or are permitted to test.
rt9-multi-agent
Red-team a multi-agent system — can one agent (or content it relays) inject instructions into another, escalate privilege by hopping between agents, or turn an orchestrator/sub-agent handoff into a trust-laundering path? Authorized testing of systems you own or are permitted to test.
rt1-prompt-injection
Red-team an AI agent for prompt injection — does content the agent is asked to process (email, page, ticket, tool result) override its actual task? Authorized testing of agents you own or are permitted to test.