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/potatoqualitee/kbupdate/labtestgit clone --depth 1 https://github.com/potatoqualitee/kbupdateWhat 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 | $0.00010 | $0.00229 |
| Opus 5 | $0.00005 | $0.00114 |
| Sonnet 5 | $0.00002 | $0.00046 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
labtest 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 yesterday.
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
Read AGENTS.md and use build/Invoke-KbUpdateHyperVLab.ps1.
Interpret $ARGUMENTS as follows:
probe: run./build/Invoke-KbUpdateHyperVLab.ps1 -ProbeOnlyand summarize availability.quick: run./build/Invoke-KbUpdateHyperVLab.ps1 -UsePublicLabCredentialfor catalog, WinRM, and installed-software inventory coverage.scan, an empty argument, or any unrecognized argument: run./build/Invoke-KbUpdateHyperVLab.ps1 -UsePublicLabCredential -ScanNeededUpdatesfor the complete read-only suite.
Do not print the credential in the response. Do not stop, restart, checkpoint, revert, rebuild, or remove a VM merely to run tests. Do not install or remove an update unless the user separately authorizes one exact guest and KB. Report passed, failed, and skipped counts plus any guest filtered out during authentication.
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.
- yesterday First seen · 15 lines · 10 tokens per session scan A 715cc0b26f9c
labtest is a command published in the GitHub repository potatoqualitee/kbupdate (390 stars, last pushed 21d ago), licensed MIT. It adds 10 tokens to every session and 229 once invoked, about $0.0001 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 2026-09-01.
Other commands, from other repositories
agt-check
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
kb-archive
Archive, detach, purge, or rename KB objects while keeping registry, index, and links consistent.
kb-init
Initialize or rebuild a vault-first, project-scoped Obsidian KB under Research/{project-slug}/ for the current repository.
kb-sync
Run deterministic KB maintenance to refresh scaffold integrity, registry, index, daily note, and runtime binding summary.
agt-status
Show the active AGT governance status for this Claude Code session.
kb-index
Refresh the auto index block inside 02-Index.md without overwriting curated content.