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/minhlucvan/notebookmd/notebookmdnpx skills add minhlucvan/notebookmd --skill notebookmdgit clone --depth 1 https://github.com/minhlucvan/notebookmdWhat 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 | $0.00000 | $0.02704 |
| Opus 5 | $0.00000 | $0.01352 |
| Sonnet 5 | $0.00000 | $0.00541 |
| Haiku 4.5 | $0.00000 | $0.00270 |
Grade A, and why
notebookmd 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
notebookmd — AI Agent Data Analysis Skill
Markup-to-Markdown toolkit for AI agents. Use
notebookmdto produce structured Markdown reports with metrics, charts, tables, and analytics — the same way a human analyst uses Jupyter, Streamlit, or Excel.
Quick Start
from notebookmd import nb
n = nb("dist/report.md", title="My Analysis")
n.section("Key Metrics")
n.metric_row([
{"label": "Revenue", "value": "$4.2M", "delta": "+18%"},
{"label": "Users", "value": "34.5K", "delta": "+2,100"},
{"label": "Churn", "value": "1.8%", "delta": "-0.3%", "delta_color": "inverse"},
])
n.section("Revenue Trend")
n.line_chart(df, x="date", y="revenue", title="Monthly Revenue")
n.section("Details")
n.table(df.head(20), name="Top 20 Records")
n.kv({"LTV": "$14,400", "CAC": "$2,100", "LTV/CAC": "6.9x"}, title="Unit Economics")
n.success("Analysis complete!")
n.save()
Installation
pip install notebookmd # Core (zero dependencies)
pip install "notebookmd[pandas]" # + DataFrames, tables, CSV export
pip install "notebookmd[plotting]" # + matplotlib charts
pip install "notebookmd[all]" # Everything (pandas, matplotlib, plotly, altair, pillow)
When to Use This Skill
Use notebookmd when the task requires:
- Generating a data analysis report from CSV, DataFrame, or API data
- Building a metrics dashboard with KPIs, deltas, and trends
- Creating a structured Markdown document with tables, charts, status indicators
- Producing reproducible analysis artifacts (Markdown file + figures + CSV exports)
- Any task where a human would open Jupyter Notebook, Streamlit, or Excel
Core Concepts
Factory
from notebookmd import nb, NotebookConfig
cfg = NotebookConfig(
max_table_rows=30, # Truncate tables beyond this (default: 30)
float_format="{:.4f}", # Number format for floats (default: "{:.4f}")
)
n = nb("dist/report.md", title="Report Title", cfg=cfg)
out_md— Path to the output.mdfile (directories created automatically)title— Report title rendered as# Titleassets_dir— Directory for figures/CSVs (default:<out_dir>/assets/)cfg— OptionalNotebookConfigfor rendering settings
What ships with it
3 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.
- 2d ago First seen · 325 lines · 0 tokens per session scan A 8c50b0e6c27c
notebookmd is a skill published in the GitHub repository minhlucvan/notebookmd (10 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,704 tokens. 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.
Other skills, from other repositories
genai-sdk
Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
vertex-deploy
Skill "vertex-deploy" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai model garden deploy skill, 1. prerequisites, 2. discovering deployable models, 3. deploying a model and example: deploying gemma 3.
vertex-inference
Skill "vertex-inference" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai genai inference skill, 1. authentication (critical), 2. gemini models, choosing the right sdk and installation.
open-model
Skill "open-model" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai open model tuning, workflow decision tree, phase 0: environment & iam setup {#phase-0}, 0.1 authentication & project context and 0.2 possible locations.
quality-flywheel
Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK. Creates eval datasets (from session traces or synthetic generation), selects and configures metrics (RubricMetric, LLMMetric, CodeExecutionMetric), executes evals via client.evals.evaluate(), and analyzes results to suggest concrete…
gemini
Skill "gemini" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai gemini model tuning, workflow decision tree, phase 0: environment & iam setup {#phase-0}, 0.1 authentication & project context and 0.2 enable apis.