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 skills/jupyter-ai-contrib/nb-cli/notebook-clinpx skills add jupyter-ai-contrib/nb-cli --skill notebook-cligit clone --depth 1 https://github.com/jupyter-ai-contrib/nb-cliWrote 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/jupyter-ai-contrib/nb-cli/notebook-cli)<a href="https://agentmods.dev/skills/jupyter-ai-contrib/nb-cli/notebook-cli"><img src="https://agentmods.dev/badge/skills/jupyter-ai-contrib/nb-cli/notebook-cli.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 | $0.00073 | $0.01316 |
| Opus 5 | $0.00036 | $0.00658 |
| Sonnet 5 | $0.00015 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
notebook-cli 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notebook CLI
Use nb for every .ipynb operation. Do not read, write, patch, or edit notebook JSON directly when nb can perform the task.
Core Rules
- Inspect before editing: run
nb read <notebook> --no-outputunless outputs are relevant. - Prefer the default AI-Optimized Markdown output from
nb read; use--jsononly when nbformat JSON is specifically needed. - Prefer cell IDs (
--cell/-c) for durable edits after inspecting a notebook. Use indexes (--cell-index/-i) for quick positional work; negative indexes are supported. - Use
--no-outputwhen summarizing structure or source. Include outputs only when diagnosing results, failures, plots, or displayed values. - Use stdin (
--source -) for multi-line or quoted content to avoid shell escaping mistakes. - If the user specifies
uvor the workspace is clearly auvproject, treatuvas the notebook execution environment for the whole task. Use--uvonnbcommands that support it, such asnb createandnb execute. - When creating a notebook with several sections, add cells in batches of roughly 3–5 cells grouped by logical section using multi-cell sentinels (
@@markdown,@@code). Execute and verify each batch before adding the next. Do not add the entire notebook in one call — it increases latency and makes errors harder to catch. - Every markdown cell must contain a heading and at least one sentence of prose explaining what the following code does or why it matters. A bare heading is not sufficient — see best-practices.md.
- When notebook code depends on third-party packages, add a dependency-install cell at the top of the notebook before imports if package availability is uncertain.
- If a
uvenvironment is present, the dependency cell should use!uv pip install .... - If a
uvenvironment is not present, the dependency cell should use%pip install .... - Run
nb <command> --helpornb cell <subcommand> --helpwhen command syntax is uncertain. - In connected mode, let
nbuse the saved connection fromnb connect. Do not write secret tokens into commands, prompts, logs, or examples; if auto-detection is unavailable, ask the user to establish the connection manually. - Before running non-notebook Python commands that should match the active notebook environment, use
nb status --pythonand run commands through the returned prefix.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 112 lines · 73 tokens per session scan A 201898f05659
notebook-cli is a skill published in the GitHub repository jupyter-ai-contrib/nb-cli (88 stars, last pushed 29d ago), licensed BSD-3-Clause. It adds 73 tokens to every session and 1,316 once invoked, about $0.0004 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 2026-08-30.
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…
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
nature-experiment-log
标准化实验日志记录——直接上传或读取本地图片、语音和文字,产出带 YAML frontmatter 的 Markdown;可选集成飞书 CLI 与 Obsidian。.
parsing-ccda-documents
Parses C-CDA / CCD XML clinical documents to extract human-readable section narrative plus coded entries, keyed by section LOINC codes and templateIds. Use before OpenMed processing when ingesting C-CDA R2.1 documents (CCD, Discharge Summary, H&P, Consultation Note) exported from an EHR and you need the narrative…
paper-spine
Build, rewrite, audit, submit, revise, or transfer scholarly papers end to end, producing verified LaTeX/PDF/Word and target-specific publication packages.