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 skills add jsamuel1/jupyter-editor-mcp --skill notebook-editinggit clone --depth 1 https://github.com/jsamuel1/jupyter-editor-mcpWrote 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/skills/jsamuel1/jupyter-editor-mcp/notebook-editing)<a href="https://agentmods.dev/skills/jsamuel1/jupyter-editor-mcp/notebook-editing"><img src="https://agentmods.dev/badge/skills/jsamuel1/jupyter-editor-mcp/notebook-editing/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.
<a href="https://agentmods.dev/skills/jsamuel1/jupyter-editor-mcp/notebook-editing"><img src="https://agentmods.dev/badge/skills/jsamuel1/jupyter-editor-mcp/notebook-editing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00088 | $0.02954 |
| Opus 5.5 | $0.00035 | $0.01182 |
| Sonnet 5.5 | $0.00018 | $0.00591 |
| Haiku 4.5 | $0.00009 | $0.00295 |
Grade A, and why
notebook-editing 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 2d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jupyter Editor MCP
Overview
The Jupyter Editor MCP server enables AI coding assistants to work directly with Jupyter Notebook files (.ipynb) without requiring a running Jupyter server. This is essential for programmatic notebook manipulation, batch operations, and integrating notebook editing into automated workflows.
When to Use This Skill
Use the Jupyter Editor MCP when you need to:
- Read, analyze, or search notebook content
- Add, modify, or delete cells in notebooks
- Perform batch operations across multiple cells or notebooks
- Manage notebook metadata and kernel specifications
- Merge, split, or reorganize notebooks
- Validate notebook structure and format
Do NOT use this skill for:
- Executing notebook cells (use a Jupyter kernel instead)
- Real-time collaborative editing
- Working with non-.ipynb files
Safety Boundaries
- Use these tools only with local
.ipynbfiles. The server parses and writes notebook JSON at whatever path it is given and does not check the file extension, so never point it at a file that is not a Jupyter notebook; use ordinary file tools for those. - The server never executes code, starts a kernel, or contacts a network service.
- Recommended persistent approvals:
ipynb_read_notebook,ipynb_list_cells,ipynb_get_cell,ipynb_search_cells,ipynb_get_notebook_info. These five only read a notebook. They are a deliberately small allowlist, not a complete list of the tools without side effects. Prefer them first to understand a notebook. - Every other tool stays prompt-gated. A few of them also only read (for example
ipynb_get_metadataandipynb_validate_notebook), but most write, delete, or create notebook files, including batch and multi-notebook tools such asipynb_delete_cells_batch,ipynb_filter_cells, andipynb_apply_to_notebooks. Before calling a tool that changes files, confirm the target file, indices, and intent with the user, and expect the client to ask for approval.
Prerequisites
- Python 3.10+ with
uv/uvxavailable on PATH - An Agent Plugins compatible client (for example Kiro) with this plugin installed
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.
- 2d ago First seen · 316 lines · 88 tokens per session scan A dd49e4afa79e
notebook-editing is a skill published in the GitHub repository jsamuel1/jupyter-editor-mcp (5 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 2,954 once invoked, about $0.0004 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 2026-10-24.
Other skills, from other repositories
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.
nature-experiment-log
A workflow for turning experiment notes, images, audio, or text into structured Markdown laboratory logs with YAML metadata. It can also organize raw attachments and optionally connect the logs to Feishu or Obsidian.
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
structuring-radiology-reports
Converts free-text radiology narratives into structured findings and impression — with measurements, laterality, anatomy, and follow-up recommendations — after OpenMed NER. Use when the user has a CT/MRI/X-ray/ultrasound/mammography report and needs the sections split (technique, comparison, findings, impression)…