notebook-standards

notebook-standards is a skill for Claude Code, Codex from stellarshenson/claude-code-plugins. It costs 198 tokens per session (3,090 once invoked), scanned A, original, MIT.

A set of standards for creating and modifying Jupyter notebooks, which combine code, explanations, and results in one document. It defines notebook sections, imports, GPU selection, colors, charts, equations, dataframes, and progress indicators.

In plain words
What is it for?
Use it when writing or changing data-science and machine-learning notebooks that need consistent structure, visual output, hardware setup, and reproducible practices.
Why use it?
It removes guesswork about how notebooks should be organized and presented. It also provides a checklist so changes can be checked against the project's rules.

Skill for Claude CodeCodex

Part of the datascience plugin — 20 skills, 15 commands shipped together

Install

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.

agentmods
npx agentmods add skills/stellarshenson/claude-code-plugins/notebook-standards
Any agent
npx skills add stellarshenson/claude-code-plugins --skill notebook-standards
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins

Made for: Claude Code, Codex.

Or install datascience, the plugin that ships this one along with the rest of its 20 skills, 15 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 notebook-standards

README.md
[![agentmods](https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/notebook-standards.svg)](https://agentmods.dev/skills/stellarshenson/claude-code-plugins/notebook-standards)
Your own site
<a href="https://agentmods.dev/skills/stellarshenson/claude-code-plugins/notebook-standards"><img src="https://agentmods.dev/badge/skills/stellarshenson/claude-code-plugins/notebook-standards.svg" alt="Measured on agentmods" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,090 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00198 $0.03090
Opus 5 $0.00099 $0.01545
Sonnet 5 $0.00040 $0.00618
Haiku 4.5 $0.00020 $0.00309

Measured 4d ago against content hash f190780757e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

notebook-standards 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.

plugins/datascience/skills/notebook-standards/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Notebook Structure Standards

Patterns for Jupyter notebook creation.

Checklist task (MANDATORY when the notebook changes)

Writing or modifying a notebook - TaskCreate one task BEFORE the first cell, carrying the checklist inside it:

  • subject - Verify <notebook path> against post-write checklist
  • description - the Post-write checklist at the end of this file, verbatim, all 17 boxes
  • activeForm - Verifying notebook against standards

Complete it only once every box is ticked or explicitly n/a.

  • Description carries the boxes so this file need not stay in context - a long build fills the window and gets compacted, taking the checklist with it; TaskGet returns the description on demand
  • Register up front, never at the end - the checklist sits at the end of this file, exactly where an agent deep in a build never returns. An open task survives the whole build; a rule below the fold does not
  • Only when the notebook changes - a question about a rule (a colormap, an equation form, a colour name) writes no notebook and creates no task
  • One task, not one per box - the 17 boxes are its definition of done

Mandatory Section Order

  1. Header - mandatory title + author + date + purpose, then an optional problem-specific menu (see below)
  2. GPU Selection - CUDA_VISIBLE_DEVICES before any torch/tf/jax import
  3. Imports - one cell, grouped, inline comments, autoreload
  4. Reproducibility - set_seed(42) for random, numpy, torch
  5. Configuration - hyperparameters in one cell, inline comments, Rich render at the end
  6. Data Loading
  7. Model/Processing
  8. Execution (training, inference)
  9. Save/Export
  10. Evaluation/Summary

Header (first markdown cell)

Orients the reader and doubles as the notebook's own overview, so the Header needs no separate one. Title, author, date and purpose are mandatory; the rest is a menu - pick what fits, drop what does not. Mirrorable template: examples/header-cell.md.

Read the full file on GitHub · 170 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. 4d ago First seen · 170 lines · 198 tokens per session scan A f190780757e0

Subscribe to this mod's changes

notebook-standards is a skill published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 198 tokens to every session and 3,090 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

evaluating-with-leakage-gates

Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…

maziyarpanahi/openmed · 158 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens

tooluniverse-drug-research

Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…

mims-harvard/ToolUniverse · 71 tokens

audit-scientific-figure

Review and score an existing scientific illustration in visible draw.io, Microsoft PowerPoint, or WPS Presentation without hiding defects through flattening. Use for reference-fidelity checks, layout cleanup, connector review, text-fit checks, deep editability and raster-atomicity inspection, local-region gates, or…

icebird1998/scientific-illustrator · 80 tokens