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/stellarshenson/claude-code-plugins/fix-notebooknpx skills add stellarshenson/claude-code-plugins --skill fix-notebookgit clone --depth 1 https://github.com/stellarshenson/claude-code-pluginsWhat 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 | $0.00022 | $0.00988 |
| Opus 5 | $0.00011 | $0.00494 |
| Sonnet 5 | $0.00004 | $0.00198 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
fix-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 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Notebook
Read a notebook and fix it to comply with ALL standards. Applies changes directly.
Skills to apply
datascience:notebook-standards- section order, GPU selection, imports, config cell; itsreferences/rich-output.md(colour palette, print patterns) andreferences/equations.md(unicode inline + display math)datascience:progressbars- progress bar style and patterns
Read these skills before making changes. They are the source of truth. Do NOT hardcode colors or patterns in this skill - always defer to the skills.
What to fix
Header
- Missing or sparse header -> add/rewrite with flowing prose (purpose, method, rationale)
- Bullet-list-only approach -> numbered phases with "what AND why"
- Missing output description -> add
**Output**: <artifacts>
Structure (per notebook-standards skill)
- GPU after imports -> move before
- Scattered imports -> consolidate into single cell with autoreload
- Missing reproducibility -> add set_seed
- Scattered config -> consolidate with rich summary at end
- No markdown headers before sections -> add them
- Section header without overview text below it -> add a 1-2 sentence overview (or 3-5 bullets when listy) before the first code cell of that section. File-level Header section is the sole exception
- Configuration cell with no Rich render at end -> add the sectioned
rprint(f"""[bold cyan]Configuration[/bold cyan] ...""")block per the canonical template innotebook-standards/SKILL.md - Configuration cell on a GPU notebook without
[bold]Device[/bold]sub-section showingtorch.cuda.get_device_name(0)-> add the Device block pernotebook-standards/references/gpu-setup.mdsection 5 - Markdown cell containing equations as plain text (e.g.
P(A|B) = P(B|A) * P(A) / P(B)) -> rewrite pernotebook-standardsreferences/equations.md: unicode glyphs inline, full/display equations as standalone$$...$$blocks on their own line - Markdown cell with odd number of unescaped
$(heuristic for stray dollar amounts that MathJax will eat) -> surface the cell number and ask the user whether each$is a price (escape as\$) or a math delimiter (leave + verify pairs match)
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 · 74 lines · 22 tokens per session scan A 72c1e627593f
fix-notebook is a skill published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 988 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.