notabene-setup

notabene-setup is a skill for Claude Code from z29k/notabene. It costs 253 tokens per session (3,943 once invoked), scanned C, original, MIT.

A setup assistant for Notabene, a tool that lets teams review and comment on documentation through a local review server. It installs or reconfigures the tool and starts the server without requiring manual build commands or a specific programming language.

In plain words
What is it for?
Use it to install Notabene, change its configuration, launch the documentation review server, and hand the project over for processing review comments.
Why use it?
It removes the setup work needed before a documentation review can begin, while keeping the tool's configuration and review data in the project.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code; mentions AGENTS.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the notabene plugin — 3 skills, 5 commands shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add z29k/notabene
Claude Code
/plugin install notabene

Made for: Claude Code.

Or install notabene, the plugin that ships this one along with the rest of its 3 skills, 5 commands.

Wrote 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.

agentmods badge for notabene-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/z29k/notabene/notabene-setup.svg)](https://agentmods.dev/skills/z29k/notabene/notabene-setup)
Your own site
<a href="https://agentmods.dev/skills/z29k/notabene/notabene-setup"><img src="https://agentmods.dev/badge/skills/z29k/notabene/notabene-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 253 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,943 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00253 $0.03943
Opus 5 $0.00127 $0.01972
Sonnet 5 $0.00051 $0.00789
Haiku 4.5 $0.00025 $0.00394

Measured 6d ago against content hash 9a70d07a7d01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

notabene-setup scanned grade C with 1 finding 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Never `rm -rf` the store** or regenerate a config from the template over an existing
packages/claude-plugin/skills/notabene-setup/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

notabene setup (install · reconfigure · run)

Get a user from nothing (or from a config they want changed) to an open review server, with zero npm/build commands typed by hand, on any repo. The renderer is fetched and run through npx — nothing is installed into the user's repo; only data lives there (notabene.config.mjs + the .notabene/ store + their docs).

Everything routes on doctor (read-only state) — you encode no defaults yourself. This skill only sets things up; processing comments is the notabene skill (hand off at the end).

The forwarder — how you call the tool

Never call npx notabene (unscoped — that package does not exist on npm) and never hardcode a version. Always go through the plugin forwarder, which pins the right renderer:

node "${CLAUDE_PLUGIN_ROOT}/bin/nb.mjs" <subcommand> --root <repo-root> [flags…]

<repo-root> = the current project directory (the repo whose docs you're reviewing). Use its absolute path. nb.mjs forwards to npx -y --prefer-offline @z29k/notabene@<pinned>.

Golden rules (no exceptions)

  • Never commit / push / rewrite history without an explicit request. Tell the user to commit the config + .notabene/ store; don't do it for them. (Offering git init on a non-repo is fine — that's not a commit.)
  • Never expose the LAN (host: true / --host) unless the user explicitly asks. It's loopback-only by default; keep it that way.
  • Never rm -rf the store or regenerate a config from the template over an existing one — those hold the user's real comments and settings.
  • Confirm every config write/edit by showing the diff first — in express mode, still print the config you wrote (show, don't ask); never write invisibly.
  • Re-entrant & read-only-first: doctor writes nothing, init is idempotent. Safe to re-run at any point.

Step 0 — Preflight (always)

Run once and read the JSON:

node "${CLAUDE_PLUGIN_ROOT}/bin/nb.mjs" doctor --root <repo-root> --json

Read the full file on GitHub · 237 lines

Changes

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.

  1. 6d ago First seen · 237 lines · 253 tokens per session scan C 9a70d07a7d01

Subscribe to this mod's changes

notabene-setup is a skill published in the GitHub repository z29k/notabene (4 stars, last pushed 24d ago), licensed MIT. It adds 253 tokens to every session and 3,943 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

meta-tags-optimizer

Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…

nowork-studio/notfair-plugin · 91 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

sxo

Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…

nowork-studio/notfair-plugin · 235 tokens

elixir-idioms

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

oliver-kriska/claude-elixir-phoenix · 44 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

security

Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.

oliver-kriska/claude-elixir-phoenix · 47 tokens