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/zpower426/datapowers/data-explorationnpx skills add zpower426/datapowers --skill data-explorationgit clone --depth 1 https://github.com/zpower426/datapowersWrote 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/zpower426/datapowers/data-exploration)<a href="https://agentmods.dev/skills/zpower426/datapowers/data-exploration"><img src="https://agentmods.dev/badge/skills/zpower426/datapowers/data-exploration.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.02277 |
| Opus 5 | $0.00016 | $0.01138 |
| Sonnet 5 | $0.00007 | $0.00455 |
| Haiku 4.5 | $0.00003 | $0.00228 |
Grade A, and why
data-exploration 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 5d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Exploration (EDA)
Systematic, evidence-based exploration of a dataset. Produces a structured understanding of data shape, quality, distributions, and relationships.
Iron Law: NO MODELING WITHOUT EXPLORATORY DATA ANALYSIS FIRST
Checklist
You MUST create a task for each of these items and complete them in order:
- Dataset overview — shape, schema, dtypes, memory usage
- Target variable analysis — distribution, class balance (if classification)
- Missing data audit — count, pattern, mechanism (MCAR/MAR/MNAR)
- Numeric feature analysis — distributions, outliers, skewness
- Categorical feature analysis — cardinality, value distributions, rare categories
- Temporal analysis — if datetime columns exist, check trends and gaps
- Relationship analysis — correlations, mutual information with target
- Leakage candidate screening — flag suspicious features
- Data quality score — per-column quality rating
- EDA summary — key findings, recommended next steps, blockers
Process Flow
digraph eda {
"Dataset overview" [shape=box];
"Has target variable?" [shape=diamond];
"Target variable analysis" [shape=box];
"Missing data audit" [shape=box];
"Numeric analysis" [shape=box];
"Categorical analysis" [shape=box];
"Has datetime columns?" [shape=diamond];
"Temporal analysis" [shape=box];
"Relationship analysis" [shape=box];
"Leakage screening" [shape=box];
"Quality score" [shape=box];
"EDA summary + save report" [shape=doublecircle];
"Dataset overview" -> "Has target variable?";
"Has target variable?" -> "Target variable analysis" [label="yes"];
"Has target variable?" -> "Missing data audit" [label="no"];
"Target variable analysis" -> "Missing data audit";
"Missing data audit" -> "Numeric analysis";
"Numeric analysis" -> "Categorical analysis";
"Categorical analysis" -> "Has datetime columns?";
"Has datetime columns?" -> "Temporal analysis" [label="yes"];
"Has datetime columns?" -> "Relationship analysis" [label="no"];
"Temporal analysis" -> "Relationship analysis";
"Relationship analysis" -> "Leakage screening";
"Leakage screening" -> "Quality score";
"Quality score" -> "EDA summary + save report";
}
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.
- 5d ago First seen · 267 lines · 33 tokens per session scan A e672a4d8195f
data-exploration is a skill published in the GitHub repository zpower426/datapowers (1 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,277 once invoked, about $0.0002 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
fba-simulator
Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
gsmm-validator
Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.
gsmm-builder
Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.
stat-result-validator
Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.