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/z29k/notabene/reviewgit clone --depth 1 https://github.com/z29k/notabeneWrote 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/commands/z29k/notabene/review)<a href="https://agentmods.dev/commands/z29k/notabene/review"><img src="https://agentmods.dev/badge/commands/z29k/notabene/review.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 | $0.00014 | $0.00146 |
| Opus 5 | $0.00007 | $0.00073 |
| Sonnet 5 | $0.00003 | $0.00029 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
review 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 4d 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
Use the notabene skill to process the open review comments in this repo: read the
.notabene/ store, apply each comment's feedback to the docs faithfully, mark them
resolved (or addressed in approve mode), append the journal, then verify — renderer
build, notabene lint, notabene comments verify (store ↔ journal coherence), and the
project's verify[] checks. Ignore comments on hold. Report as a table and never commit
without an explicit request.
$ARGUMENTS
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.
- 4d ago First seen · 14 lines · 14 tokens per session scan A 5a98570824b4
review is a command published in the GitHub repository z29k/notabene (4 stars, last pushed 22d ago), licensed MIT. It adds 14 tokens to every session and 146 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 2026-08-31.
Other commands, from other repositories
wp-init
Set up a WordPress port. Detects the source builder and the target stack, then writes .wp-to-code/config.json.
wp-diff
Compare a ported page against the mirrored original, section by section, on height and position.
wp-measure
Dump the layout tree, section list, content or interactive inventory for a page to a file.
wp-mirror
Download the original site to a local directory that can be served flat, and find each page's section root.
wp-theme
Extract design tokens from the original's computed styles and write them into the target's token file.
wp-audit
Static check for the porting failures that stay silent, including undefined tokens and interpolated class names.