execute-notebook

execute-notebook is a skill for Claude Code from kclemoveki/agentic-skills-eda. It costs 47 tokens per session (1,171 once invoked), scanned A, original, MIT.

A tool that runs a Jupyter notebook from start to finish with a fresh Python session. Jupyter notebooks combine code, results, and notes in one file.

In plain words
What is it for?
Use it to verify an analysis notebook before sharing it or relying on its results, without opening Jupyter manually.
Why use it?
It checks that every cell works in a clean run, saves the results into the notebook, and stops at the first error with its location and details.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to verify an analysis notebook before sharing it or relying on its results, without opening Jupyter manually.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kclemoveki/agentic-skills-eda/execute-notebook
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 kclemoveki/agentic-skills-eda --skill execute-notebook
Clone the repo
git clone --depth 1 https://github.com/kclemoveki/agentic-skills-eda

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 execute-notebook

README.md
[![agentmods](https://agentmods.dev/badge/skills/kclemoveki/agentic-skills-eda/execute-notebook/github.svg)](https://agentmods.dev/skills/kclemoveki/agentic-skills-eda/execute-notebook)
Your own site
<a href="https://agentmods.dev/skills/kclemoveki/agentic-skills-eda/execute-notebook"><img src="https://agentmods.dev/badge/skills/kclemoveki/agentic-skills-eda/execute-notebook/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 execute-notebook

Your own site · 80×15
<a href="https://agentmods.dev/skills/kclemoveki/agentic-skills-eda/execute-notebook"><img src="https://agentmods.dev/badge/skills/kclemoveki/agentic-skills-eda/execute-notebook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 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 $0.00047 $0.01171
Opus 5.5 $0.00019 $0.00468
Sonnet 5.5 $0.00009 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 2mo ago against content hash 9a228b3a4923, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

execute-notebook 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 2mo 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.

skills/execute-notebook/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Execute Notebook

Run the notebook at $ARGUMENTS end-to-end with a fresh kernel and persist its outputs back into the file. This is the "restart and run all" hygiene step recommended by Rule 7 of Ten Simple Rules for Writing and Sharing Computational Analyses in Jupyter Notebooks (Rule et al. 2019), automated.

Step 1 — Pre-flight checks

Before invoking papermill, verify:

  1. Notebook exists: resolve $ARGUMENTS to an absolute path. If the file does not exist, fail with: Notebook not found: <path>.
  2. Papermill installed: run python3 -c "import papermill" via Bash. If it raises ModuleNotFoundError, fail with:
    papermill not installed. Install with one of:
      pip install papermill
      poetry add papermill
    
  3. Dependencies sanity check (warning, not error): if neither requirements.txt nor pyproject.toml exists in the notebook's directory or cwd, print:
    WARNING: no requirements.txt or pyproject.toml found. Consider running /freeze-deps first.
    
    Do not abort on this warning — proceed with execution.
  4. Kernel availability: read the notebook JSON, extract metadata.kernelspec.name. Run jupyter kernelspec list --json via Bash and verify the kernel exists. If not, fail with:
    Kernel '<name>' not available. Available kernels:
    <output of jupyter kernelspec list>
    

Step 2 — Execute the notebook

Invoke papermill from the notebook's directory as cwd (so relative paths like data/foo.csv resolve correctly):

cd <notebook_dir>
python3 -c "
import papermill as pm
import time
start = time.time()
try:
    pm.execute_notebook(
        input_path='<notebook_filename>',
        output_path='<notebook_filename>',  # overwrite
        kernel_name='<kernel_from_metadata>',
        progress_bar=False,
        log_output=False,
        request_save_on_cell_execute=True,  # save partial output on failure
    )
    print(f'OK {time.time() - start:.1f}')
except pm.PapermillExecutionError as exc:
    print(f'FAIL {time.time() - start:.1f} cell={exc.cell_index} ename={exc.ename} evalue={exc.evalue}')
    raise
"

Read the full file on GitHub · 117 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. 2mo ago First seen · 117 lines · 47 tokens per session scan A 9a228b3a4923

Subscribe to this mod's changes

execute-notebook is a skill published in the GitHub repository kclemoveki/agentic-skills-eda (2 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,171 once invoked, about $0.0002 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.

Related

execute-notebook compared with skills from other repositories

execute-notebook next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
execute-notebookkclemoveki/agentic-skills-edaSkill25mo agoMITA47Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k3d agoApache-2.0A123Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA83Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA44Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill33kyesterdayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A205Claude Code