agentmods.dev

notebook.format_interactive_cells

notebook.format_interactive_cells is a skill for Claude Code from gpsaggese/helpers. It costs 12 tokens per session (378 once invoked), scanned A, original, Apache-2.0.

A notebook-formatting task that organizes the Markdown around interactive or visualization cells in a Jupyter notebook.

In plain words
What is it for?
Use it to format visualization cell triplets, explain interactive experiments, and synchronize the notebook with its paired Python file using Jupytext.
Why use it?
It makes each visualization easier to understand by placing its goal, plot and widget descriptions, usage guidance, and implementation in a consistent order.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

not rated 158repo +1 today A scan 12 tokens original Apache-2.0

Good fit Use it to format visualization cell triplets, explain interactive experiments, and synchronize the notebook with its paired Python file using Jupytext.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsaggese/helpers/notebook.format_interactive_cells
View source ↗ gpsaggese/helpers
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.

Any agent
npx skills add gpsaggese/helpers --skill notebook.format_interactive_cells
Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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.format_interactive_cells

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/notebook.format_interactive_cells/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/notebook.format_interactive_cells)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/notebook.format_interactive_cells"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/notebook.format_interactive_cells/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.

agentmods 80×15 button for notebook.format_interactive_cells

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/notebook.format_interactive_cells"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/notebook.format_interactive_cells.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00012 $0.00378
Opus 5.5 $0.00005 $0.00151
Sonnet 5.5 $0.00002 $0.00076
Haiku 4.5 $0.00001 $0.00038

Measured yesterday against content hash c224fbb0a5cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

notebook.format_interactive_cells 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 yesterday.

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.

.claude/skills/notebook.format_interactive_cells/SKILL.md · 42 lines

What it actually says

Goal

  • Given a Jupyter notebook, format the markdown cells that correspond to interactive or visualization cells
  • Each visualization uses a triplet: pre-visualization markdown, the code cell, and post-visualization markdown

Workflow

Update the Cell Triplets

  • Make the markdown cells around each interactive cell follow the triplet structure:
    • Before the visualization: a markdown cell with the goal, then a description cell with the plot descriptions (under each title) and widget descriptions (close to each widget)
    • After the visualization: a guided-usage markdown cell that explains which experiments to run and what was learned, then the implementation cell and the print_obj_info() code cell

Sync with Jupytext

  • At the end, sync the paired .py file with Jupytext, following # Code Architecture and Responsibility -> ## Utilities vs. Notebook Responsibilities in .claude/skills/notebook.rules.md

Conventions

  • Follow the rules in .claude/skills/notebook.rules.md, especially:
    • ## Visualization Cell Triplet Details for the structure of pre- and post-visualization markdown cells
    • # Visualization and Interactivity for the interactive widget patterns
    • ## Cell Triplet Structure for the overall three-cell organization

Constraints

  • Do not change the intent of the notebook

Verification

  • Confirm each interactive cell has both a pre- and post-visualization markdown cell
  • Confirm the .ipynb and paired .py file are in sync via Jupytext
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. yesterday First seen · 42 lines · 12 tokens per session scan A c224fbb0a5cf

Subscribe to this mod's changes

notebook.format_interactive_cells is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 378 once invoked, about $0.0000 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 2026-11-06.

Learning and teachingScientific
Related

notebook.format_interactive_cells compared with skills from other repositories

notebook.format_interactive_cells next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
notebook.format_interactive_cellsgpsaggese/helpersSkill158todayApache-2.0A12Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19kyesterdayMITA81Claude Code
build-interactive-explainersEverMind-AI/RavenSkill6.1kyesterdayApache-2.0A102Claude Code, Codex
tooluniverse-organic-chemistrymims-harvard/ToolUniverseSkill1.8ktodayApache-2.0A86Claude Code
edu-chem-reactionwy51ai/edulabSkill1.8k15d agoApache-2.0A495Claude Code
scaffold-exercisespedrohcgs/claude-code-my-workflowSkill1.7ktodayMITA101Claude Code
present-paperAperivue/medsci-skillsSkill3705d agoMITA59Claude Code