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 instructions/z29k/notabene/claude-mdgit 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/instructions/z29k/notabene/claude-md)<a href="https://agentmods.dev/instructions/z29k/notabene/claude-md"><img src="https://agentmods.dev/badge/instructions/z29k/notabene/claude-md.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 5.1 | $0.10797 | $0.10797 |
| Opus 5 | $0.05398 | $0.05398 |
| Sonnet 5 | $0.02159 | $0.02159 |
| Haiku 4.5 | $0.01080 | $0.01080 |
Grade A, and why
notabene CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
notabene renders a repo's Markdown/MDX as a navigable site with Google-Docs-style commenting, and ships a human↔agent review protocol that turns those comments into edits. The viewer is the support; the protocol (the review skill) is the product.
Two installable pieces, one npm workspace:
packages/renderer— the@z29k/notabenenpm package: a generic Astro renderer- the
notabeneCLI (init/dev/build/preview/pdf/lint, plusdoctor/status/stop/migrate/comments/journal). Published to npm.
- the
packages/claude-plugin— the Claude Code plugin (3 skills + a forwarder). The canonical protocol lives indocs/(it is documentation, not a hidden artifact); the plugin skills and the npm-shipped copy are generated from it — see Architecture: the protocol is generated below.
Dogfood: this repo is also its own consumer — docs/ holds the user documentation
(two spaces, guide + reference), wired by the root notabene.config.mjs (store at
docs/.notabene, review: "approve"). .github/workflows/docs.yml publishes it to
GitHub Pages (z29k.github.io/notabene) on push to main via build --public. Review it
locally with node packages/renderer/bin/notabene.mjs dev --root .. The three READMEs
are short landings; the docs site is the single source of user-facing detail — update
docs/, not the READMEs, when documenting features.
Commands
Everything runs against a consumer repo (see run-from-package model below), so the CLI is never invoked bare in this repo. Develop and validate against a scratch consumer:
npm install # installs the renderer's deps (workspace root)
# Quality gates (run in packages/renderer — these are what CI enforces):
cd packages/renderer
npm test # Vitest — pure-logic unit tests (test/*.test.ts)
npm run lint # Biome — lint + format check on bin/src/test (JS/TS; .astro/.css excluded)
npm run format # Biome — apply formatting
NOTABENE_ROOT=/tmp/nb-scratch NOTABENE_CONFIG=/tmp/nb-scratch/notabene.config.mjs \
npm run check # astro check — type-checks .astro + .ts (needs a consumer via env)
# Point the CLI at a throwaway consumer repo (run-from-package):
mkdir -p /tmp/nb-scratch/docs && printf '# Hi\n' > /tmp/nb-scratch/docs/index.md
node bin/notabene.mjs init --root /tmp/nb-scratch # writes notabene.config.mjs + .notabene store
node bin/notabene.mjs dev --root /tmp/nb-scratch # review server → http://localhost:3009
node bin/notabene.mjs build --root /tmp/nb-scratch # verification build — must complete with 0 errors
node bin/notabene.mjs build --root /tmp/nb-scratch --public --site https://example.com \
--out /tmp/nb-public # public read-only static artifact (llms.txt, .md twins)
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.
- 6d ago First seen · 547 lines · 10,797 tokens per session scan A a2ffd005766f
notabene CLAUDE.md is an instructions file published in the GitHub repository z29k/notabene (4 stars, last pushed 24d ago), licensed MIT. It adds 10,797 tokens to every session, about $0.0540 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 instructions, from other repositories
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
curie CLAUDE.md
Claude Code instructions for curie-eng/curie, covering one entry point: curie, release train selection and architecture decision records (adrs).
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
agentic-validation-skills CLAUDE.md
Claude Code instructions for vivekkrishna/agentic-validation-skills, covering agentic test automation guidelines (cige), 1. establish context before testing, 2. anchor every test to intent, 3. define guardrails before executing and 4. treat execution as adaptive guidance.
octowiz CLAUDE.md
Instructions for raelli/octowiz, covering octowiz, releasing & deploying, commands, agent skills and issue tracker.