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 agentmods add agents/hashgraph-online/hol-guard/reviewergit 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/agents/hashgraph-online/hol-guard/reviewer)<a href="https://agentmods.dev/agents/hashgraph-online/hol-guard/reviewer"><img src="https://agentmods.dev/badge/agents/hashgraph-online/hol-guard/reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00007 | $0.00021 |
| Opus 5 | $0.00003 | $0.00010 |
| Sonnet 5 | $0.00001 | $0.00004 |
| Haiku 4.5 | $0.00001 | $0.00002 |
Grade A, and why
reviewer 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 5d 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.
What it actually says
Review the evidence returned by the demo server.
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.
- 5d ago First seen · 7 lines · 7 tokens per session scan A c0a6a6455603
reviewer is an agent published in the GitHub repository hashgraph-online/hol-guard (551 stars, last pushed today), licensed Apache-2.0. It adds 7 tokens to every session and 21 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.
Other agents, from other repositories
release-agent
Use .claude/commands/release.md to prepare the release checklist.
agent-red-teamer
Use this to security-test an AI AGENT (not ordinary app code) — prompt injection, memory poisoning, tool/action abuse, sandbox escape, channel injection, supply chain, exfiltration. It runs TrustShell's static-triage → dynamic-confirm loop and reports only exploit-validated findings. Authorized, disposable-environment…
release-manager
Use this agent when you need to prepare, validate, and publish a production release for a software project. This agent is designed for release engineering tasks including: preparing a new version release (e.g., 'Cut release v0.2.0 or v0.2.0-rc.1'), validating release readiness across all dimensions (code, packages…
integration-ux-critic
Invoke ONLY when explicitly asked for an outside-in usability and adoption assessment of Caracal from a real external engineer's perspective. This agent evaluates: Console UX, SDK ergonomics, CLI experience, documentation clarity, deployment workflows, provider/gateway setup, policy model, app/resource modeling…
inbox-searcher
Email inbox search specialist, takes in appropriate context for the email and a goal of what to search for. Return the answer to the question.
openhands
OpenHands is an open-source AI-driven development platform. ToolShield injects safety guidelines as a microagent that is always loaded into the agent's system prompt.