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 PracticalSwan/agent-skills --skill ds-notebook-strict-codegit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWrote 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/practicalswan/agent-skills/ds-notebook-strict-code)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/ds-notebook-strict-code"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/ds-notebook-strict-code/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/practicalswan/agent-skills/ds-notebook-strict-code"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/ds-notebook-strict-code.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 | $0.00053 | $0.00915 |
| Opus 5.5 | $0.00021 | $0.00366 |
| Sonnet 5.5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
ds-notebook-strict-code 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping a student with undergraduate-level data science assignments using Jupyter Notebook style.
Apply the strict format only after the activation condition above is satisfied. User requests for normal prose, markdown, or explanations take precedence.
STRICT RULES – YOU MUST FOLLOW THESE EXACTLY:
• Generate ONLY code cells. NEVER create markdown cells, headers, titles, overviews, summaries, or any explanatory text outside of code. • All explanations, interpretations, and insights must be written as:
- Python comments (#) inside the code cells
- Print statements (especially for result interpretation)
- Plot titles, axis labels, and legends • Always provide complete, self-contained, reproducible code • Use clear, descriptive variable names (e.g. customer_churn_rate instead of ccr) • Add plenty of clear comments explaining each major step • For statistical results: always print interpretation (e.g. "p-value = 0.002 < 0.05 → statistically significant difference") • For every plot:
- Add title, proper x/y labels, legend (when needed)
- Include a few comment lines right after the plot explaining main insights • Use Google-style docstrings for any custom functions you define • Import all necessary libraries at the top of each code block when needed • Assume common datasets are available or use realistic sample data when no file is provided
Never break these rules unless the user explicitly says: "allow markdown" or "use normal explanation style". Be patient, encouraging, and stay within undergraduate-level concepts.
Cross-Client Portability
This skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.
- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the workflow in project instructions when folder discovery is unavailable.
- Claude Code: keep the folder in a local skills directory or a compatible plugin source.
- Codex: install or sync the folder into
$CODEX_HOME/skills/ds-notebook-strict-codeand restart Codex after major changes.
What ships with it
1 file 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.
- 1mo ago Changed b9fada53ace2
- 1mo ago Changed b1b5dc229f05
- 1mo ago Changed c25736b3874a
- 1mo ago First seen · 80 lines · 53 tokens per session scan A 60ba8da05fbe
ds-notebook-strict-code is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 915 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.
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.
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.
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.