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.
git 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/setup)<a href="https://agentmods.dev/commands/z29k/notabene/setup"><img src="https://agentmods.dev/badge/commands/z29k/notabene/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/commands/z29k/notabene/setup"><img src="https://agentmods.dev/badge/commands/z29k/notabene/setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.00226 |
| Opus 5.5 | $0.00007 | $0.00090 |
| Sonnet 5.5 | $0.00004 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
setup 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 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.
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-setup skill to install/configure (or reconfigure) notabene for this
repo and start the review server. It runs doctor first, routes on the current state
(fresh install / reconfigure / repair), writes or edits notabene.config.mjs (confirmed),
creates the .notabene/ store, and launches the server in the background.
Arguments: $ARGUMENTS
Treat any of these as a non-interactive (express) signal — skip confirmations,
defaults-first, don't ask questions unless a doc folder genuinely can't be determined:
--yes is present, explicit roots / --format are given, or the phrasing is terse.
Safety rails hold even in express mode: never expose the LAN (--host), commit, or delete
anything without an explicit request.
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 · 19 lines · 18 tokens per session scan A 1c65723437ea
setup is a command published in the GitHub repository z29k/notabene (5 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 226 once invoked, about $0.0001 per session on Opus 5.5. 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
genshijin-review
A compact Japanese-language code-review command that reports one finding per line with a severity label and suggested fix.
fix-pr-comments
Systematically resolve Pull Request review comments using gh CLI to fetch comments and apply requested changes.
cg-review
Review code against its call graph — reconstruct the implemented Design Graph and diff it.
review-pack
Inspect Soliton's risk-adaptive context pack for a PR or local diff (Step 1 + Step 2 + Step 2.5 + Step 2.75; no agent dispatch).
review
Command "review" from KhaiTrang1995/claude-code-structure, covering /project:review – code review command, usage, description, output format and shell step.
odoo-review
Review a GitHub PR against Odoo PSDU conventions — business need, file-by-file, then full-logic; before/after fixes; terminal-only, read-only.