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 gpsaggese/helpers --skill notebook.brainstorm_outlinegit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/notebook.brainstorm_outline)<a href="https://agentmods.dev/skills/gpsaggese/helpers/notebook.brainstorm_outline"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/notebook.brainstorm_outline/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/gpsaggese/helpers/notebook.brainstorm_outline"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/notebook.brainstorm_outline.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 | $0.00014 | $0.00705 |
| Opus 5.5 | $0.00006 | $0.00282 |
| Sonnet 5.5 | $0.00003 | $0.00141 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
notebook.brainstorm_outline 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
-
Given technical material, come up with 5 ideas for interactive Jupyter notebooks that teach its concepts through visualization, interaction, and exploration
-
When possible, use "famous" examples, data, experiments, and problems related to the material
-
Output
notebook_ideas.<TAG>.md, a markdown file that describes the ideas -
State in the output how it was generated, with this line right after the title:
- Generated by `.claude/skills/notebook.brainstorm_outline/SKILL.md`
Template
- For each idea, use a template like
## 1. <Title> ### Goal Students gain intuitive understanding of ... by building and analyzing ... and exploring the relationship between ... ### Learning Objectives - Understand ... - Visualize ... ### Core Concepts - ... ### Key Packages - **package**: ... (Do not cite the standard packages like pandas, scipy, numpy, matplotlib) ### Learning Activities - Build ... - Generate ... - Test ... - Explore ... - Measure ... - Interactive ...
Example
- For a query like "Explain propositional logic":
## 1. Interactive Logic Explorer ### Goal - Students will: - Gain intuitive understanding of propositional logic by building and analyzing logical formulas, truth tables, and inference rules - Explore the relationship between syntax, semantics, and computation. ### Learning Objectives - Construct propositional formulas and evaluate truth values - Enumerate all models and check entailment - Understand SAT solving and computational complexity - Visualize how expressiveness and tractability trade off ### Core Concepts - Propositional logic syntax (operators: not, and, or, implies, iff) - Semantics via truth tables and model interpretation - Inference rules (Modus Ponens, Modus Tollens, Resolution) - Model checking algorithm (sound and complete) - Satisfiability and NP-completeness ### Key Packages - **sympy**: symbolic logic, propositional formula manipulation - **python-sat**: SAT solver backends ### Learning Activities - Build formulas interactively: `(Rain and Cold) or Sunny` - Generate and display truth tables for arbitrary formulas - Test entailment between two formulas: does KB entail alpha? - Explore inference rules (modus ponens, resolution) - Measure SAT solver complexity as # variables increases - Interactive "Wumpus World" knowledge base reasoning
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.
- yesterday First seen · 102 lines · 14 tokens per session scan A e08b45b1e912
notebook.brainstorm_outline is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 705 once invoked, about $0.0001 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 2026-11-06.
notebook.brainstorm_outline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| notebook.brainstorm_outlinegpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 14 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | yesterday | MIT | A | 81 | Claude Code |
| build-interactive-explainersEverMind-AI/Raven | Skill | 6.1k | yesterday | Apache-2.0 | A | 102 | Claude Code, Codex |
| tooluniverse-organic-chemistrymims-harvard/ToolUniverse | Skill | 1.8k | today | Apache-2.0 | A | 86 | Claude Code |
| edu-chem-reactionwy51ai/edulab | Skill | 1.8k | 15d ago | Apache-2.0 | A | 495 | Claude Code |
| scaffold-exercisespedrohcgs/claude-code-my-workflow | Skill | 1.7k | today | MIT | A | 101 | Claude Code |
| present-paperAperivue/medsci-skills | Skill | 370 | 5d ago | MIT | A | 59 | Claude Code |