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 commands/hashgraph-online/hol-guard-plugin/scangit clone --depth 1 https://github.com/hashgraph-online/hol-guard-pluginWhat 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 | $0.00303 |
| Opus 5 | $0.00004 | $0.00151 |
| Sonnet 5 | $0.00002 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
scan 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 2d 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
Scan an agent extension before trust
Treat $ARGUMENTS as the path to the plugin, skill, MCP server, or agent-tooling source that should be inspected.
Safety rules
- Never run the target repository's install, build, lifecycle, or setup scripts just to inspect it.
- Never read
.envfiles or reveal secrets. - Keep the initial pass read-only.
- If no target path was provided, ask for one instead of guessing.
- Do not assume the
hol-guardruntime package provides the separateplugin-scannerCLI.
Steps
-
Check whether the scanner is available:
command -v plugin-scannerIf it is missing, explain that the scanner is published as the separate open-source
plugin-scannerdistribution. Install it only after explicit user approval:pipx install plugin-scanner -
Run the fast local scanner pass:
plugin-scanner lint "$ARGUMENTS" -
When a stronger verification pass is appropriate, run:
plugin-scanner verify "$ARGUMENTS" -
Summarize findings by severity and identify the exact file or surface responsible for each material finding.
-
Do not install or enable the scanned artifact unless the user explicitly asks to proceed after reviewing the findings.
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.
- 2d ago First seen · 46 lines · 8 tokens per session scan A 56d5f1e7a373
scan is a command published in the GitHub repository hashgraph-online/hol-guard-plugin (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 8 tokens to every session and 303 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 commands, from other repositories
logic-health
Sweep a whole codebase or directory for logic correctness — use before a release or to identify risk hotspots.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
status
Check Nowledge Mem connection and server status.
nowledge-save-handoff
Save a resumable handoff summary for the current Droid session.
cleanup
Run a systematic cleanup on the provided code to resolve smells, simplify complexity, and enforce best practices.
semantic-change-check
Audit changes to dbt Semantic Layer definitions for breaking changes and aggregation risks.