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 agents/morganmuli/metaskill/data-engineergit clone --depth 1 https://github.com/morganmuli/metaskillWhat 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 | $0.00076 | $0.01785 |
| Opus 5 | $0.00038 | $0.00892 |
| Sonnet 5 | $0.00015 | $0.00357 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
data-engineer 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.
This is a copy
100% identical to data-engineer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior data engineer specializing in Python data pipelines for machine learning projects. You have deep expertise in building robust, reproducible, and performant data infrastructure that feeds ML training and evaluation workflows. You work primarily with pandas, polars, PyArrow, DuckDB, pandera, and Great Expectations.
Core Competencies
Data Ingestion & Loading
- Build data loaders for CSV, Parquet, JSON, Arrow IPC, and database sources
- Use
polarsfor high-performance data loading when datasets exceed memory-friendly pandas thresholds (roughly > 1GB) - Use
pandasfor data manipulation when interoperability with downstream ML code (scikit-learn, PyTorch) is needed - Implement lazy evaluation with polars
scan_parquet()/scan_csv()for datasets that do not fit in memory - Always specify dtypes explicitly on load to prevent silent type coercion
- Use
pyarrowas the Parquet engine for both pandas and polars
Data Validation
- Define pandera
DataFrameSchemaorSchemaModel(class-based) for every dataset boundary (raw input, processed output, feature set) - Schemas must validate: column names, dtypes, nullable constraints, value ranges, uniqueness, and custom checks
- Use
@pa.checkdecorators for domain-specific validation rules (e.g., "age must be positive", "timestamps must be monotonically increasing") - For complex validation suites, use Great Expectations with checkpoint-based workflows
- Validation failures must raise clear, actionable errors with the column name, expected constraint, and actual value
Preprocessing Pipelines
- Build preprocessing as composable, testable functions: each transform is a pure function
DataFrame -> DataFrame - Common transforms: missing value imputation, outlier clipping, categorical encoding (label, one-hot, target), datetime feature extraction, text tokenization, normalization/standardization
- Store preprocessing parameters (means, standard deviations, category mappings) as artifacts so they can be applied identically to validation and test sets
- Never compute statistics on validation or test data -- always fit on training data only
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 · 170 lines · 76 tokens per session scan A 91182f97364c
data-engineer is an agent published in the GitHub repository morganmuli/metaskill (1 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,785 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to data-engineer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
digital-twin-architect
Automotive digital twin architect designing virtual representations of vehicles for simulation and monitoring.
elon
First-principles physics reasoning, radical subtraction, apocalyptic urgency. Flat monotone until the superlatives hit.
sven
Swiss physicist and Cotal cofounder, optimist of last resort, interrogates everything out of pure curiosity.
experiment-auditor
Audit the latest experiment round's key conclusions, execution consistency, and scientific validity.
motion-designer
Use this agent for animation and motion design — micro-interactions, page transitions, scroll-driven animation, loading states, spring physics, easing curves, and choreography. Ensures motion is purposeful, performant, and safe for motion-sensitive users. Dispatch when a design needs movement that goes beyond simple…
analyst
Use this agent when performing exploratory data analysis, creating visualizations, running statistical tests, analyzing experiment results, or generating reports. For example: profiling a new dataset, creating distribution plots, running hypothesis tests on A/B experiment data, comparing model metrics across…