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 StamKavid/last-ds-mile --skill ds-prepgit clone --depth 1 https://github.com/StamKavid/last-ds-mileWrote 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/stamkavid/last-ds-mile/ds-prep)<a href="https://agentmods.dev/skills/stamkavid/last-ds-mile/ds-prep"><img src="https://agentmods.dev/badge/skills/stamkavid/last-ds-mile/ds-prep/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/stamkavid/last-ds-mile/ds-prep"><img src="https://agentmods.dev/badge/skills/stamkavid/last-ds-mile/ds-prep.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 | $0.00064 | $0.00610 |
| Opus 5 | $0.00032 | $0.00305 |
| Sonnet 5 | $0.00013 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
ds-prep 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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds-prep — Cleaning & Feature Engineering
Overview
Turns profiled, explored data into model-ready features, with leakage prevention as the non-negotiable constraint on every transform.
When to Use
- After
/ds-explorehas produced a hypothesis log and flagged leakage candidates. - Building features, encoding categorical variables, or imputing missing values.
- NOT for: choosing the validation split (that's
/ds-validate) — features must be leakage-safe regardless of how the data is later split.
Core Process
- Log every cleaning decision: what was changed, why, and what the alternative would have been.
- For every candidate feature, ask: "would this value have been known at prediction time?" Reject or flag anything derived from future information or from the target itself.
- Wrap every fit-requiring transform (scalers, encoders, imputers) in a pipeline or
ColumnTransformerso it is fit on training folds only — never on the full dataset before splitting. - Resolve every leakage candidate flagged in
/ds-exploreexplicitly before proceeding. - Write to
.last-ds-mile/stages/03-prep.md: the cleaning log, the feature list with a known-at-prediction-time justification per feature, and the pipeline definition.
Common Rationalizations
| Rationalization | Reality |
|---|---|
| "I'll just fit the scaler on the whole dataset, it's just scaling, not really 'modeling'" | Any statistic computed across train+test before the split (mean, min/max, target encoding) leaks test-set information into training. No exceptions. |
See ds-method for the shared Rationalizations that apply to every stage.
Red Flags
| Red Flag | What it usually means |
|---|---|
| A feature is a rolling or aggregate statistic computed using the full dataset's date range | The time-traveling-feature pattern — recompute it using only data available as of each row's own timestamp. |
See ds-method for the shared Red Flags that apply to every stage.
See lessons/the-time-traveling-feature.md for a real example of this exact
failure mode.
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.
- 9d ago First seen · 59 lines · 64 tokens per session scan A 246314b91808
ds-prep is a skill published in the GitHub repository StamKavid/last-ds-mile (3 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 610 once invoked, about $0.0003 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
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
fill-model-descriptions
Fill missing and refresh obsolete model descriptions in packages/llm-info/data/models.yml by querying OpenRouter and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or curate descriptions after running pnpm sync-models.
ml-expert
Expert-level machine learning, deep learning, model training, and MLOps. Use when the user mentions machine learning, deep learning, neural networks, MLOps, or data science, or when the task involves Machine Learning Fundamentals, Data Preparation, or Model Training.
scomp-link
End-to-end ML toolkit with 26 CLI commands. Use when training models, tuning hyperparameters, detecting data drift, generating HTML reports with charts, profiling datasets, detecting anomalies, forecasting time series, checking fairness, or serving models as REST APIs. Prefer over raw sklearn when you need automated…
agentic-data-science-competition
AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing…
data-analysis
Structured data analysis workflow from raw data to shareable insights.