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 mxslr/mlcraft --skill notebook-deliverygit clone --depth 1 https://github.com/mxslr/mlcraftWrote 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/mxslr/mlcraft/notebook-delivery)<a href="https://agentmods.dev/skills/mxslr/mlcraft/notebook-delivery"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/notebook-delivery/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/mxslr/mlcraft/notebook-delivery"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/notebook-delivery.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 | $0.00135 | $0.00692 |
| Opus 5.5 | $0.00054 | $0.00277 |
| Sonnet 5.5 | $0.00027 | $0.00138 |
| Haiku 4.5 | $0.00014 | $0.00069 |
Grade A, and why
notebook-delivery 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 1mo 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notebook and Environment Delivery
Before writing a deliverable, decide WHERE it will run, then adapt to it. If the user has not said, ask which of the three targets they want.
Detect the target environment
| Target | Signal from user | What to adapt |
|---|---|---|
| Kaggle | "kaggle", "commit", "save version", dataset already on Kaggle | Paths under /kaggle/input and /kaggle/working; note the weekly GPU quota and 12h commit limit; use Save and Run All (Commit) for long runs; preprocess once and reuse. |
| Google Colab | "colab", "google colab", Drive | Mount Google Drive; read data and write checkpoints to Drive so a disconnect does not lose progress; note free-tier idle timeouts. |
| Local GPU (VSCode) | "local gpu", "my laptop", "vscode", "run offline" | Require an NVIDIA CUDA GPU; size resolution and batch to the local VRAM (usually far less than 16 GB); read data from a local folder path the user sets. |
Make the notebook portable when possible: auto-detect the environment and set the working directory and data path from it, so the same file runs in more than one place.
Environment-specific cautions to state plainly
- Kaggle: quota is total hours per week and resets weekly. A run must fit the budget; measure seconds per epoch on a quick test first. Do not run long jobs in an interactive session that dies when the tab closes; use a Commit.
- Colab: free GPU disconnects on idle; always checkpoint to Drive and support resume.
- Local: CPU-only cannot train these models in reasonable time. If no CUDA GPU, say so and recommend Kaggle or Colab.
Writing style for generated notebooks (required)
- Keep explanations short and simple. One or two sentences per markdown cell is usually enough.
- Write in a professional research tone, like a methods section: state what and why, not chit-chat.
- Do not use em-dash characters. Use a normal hyphen, a comma, or a new sentence instead.
- Do not use emoji anywhere in the notebook, comments, or markdown.
- Prefer plain, precise wording. Avoid exclamation marks and filler.
- Every claim about a result must come from an actual run, not an assumption.
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.
- 1mo ago First seen · 35 lines · 135 tokens per session scan A eb5484f7a468
notebook-delivery is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 3mo ago), licensed MIT. It adds 135 tokens to every session and 692 once invoked, about $0.0005 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.
Other skills, from other repositories
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
reinforcement-learning
Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…