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/duonginspace/claude-code-databricks-ml/explore-datanpx skills add duonginspace/claude-code-databricks-ml --skill explore-datagit clone --depth 1 https://github.com/duonginspace/claude-code-databricks-mlWhat 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 | $0.00068 | $0.00344 |
| Opus 5 | $0.00034 | $0.00172 |
| Sonnet 5 | $0.00014 | $0.00069 |
| Haiku 4.5 | $0.00007 | $0.00034 |
Grade A, and why
explore-data 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 2d 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.
What it actually says
Data exploration task
Dataset or path: $ARGUMENTS
Steps
- Load the data using pandas. Infer the format (csv, parquet, delta) from the path or CLAUDE.md context.
- Run
df.info(),df.describe(),df.isnull().sum()— save output toeda_results/summary.txt. - Identify column types: numeric, categorical, datetime, text.
- For each numeric column: plot distribution histogram and boxplot.
- For categorical columns: show value counts for columns with <50 unique values.
- Compute a correlation matrix for numeric features — save as
eda_results/correlations.csv. - Flag data quality issues: duplicates, high-cardinality categoricals, columns with >20% missing, suspicious outliers (>4σ).
- Save all plots to
eda_results/plots/. - Write a concise narrative to
eda_results/report.md: dataset shape, key distributions, top correlations, and data quality issues to address before modeling.
Output
Return a 3-5 sentence summary of the most important findings and what they imply for feature engineering or modeling.
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.
- 2d ago First seen · 27 lines · 68 tokens per session scan A c827f8558957
explore-data is a skill published in the GitHub repository duonginspace/claude-code-databricks-ml (5 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 344 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.