Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultnpx agentmods add skills/georgekhananaev/claude-skills-vault/data-wranglerWrote 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/georgekhananaev/claude-skills-vault/data-wrangler)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/data-wrangler"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/data-wrangler/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/georgekhananaev/claude-skills-vault/data-wrangler"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/data-wrangler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.02792 |
| Opus 5 | $0.00048 | $0.01396 |
| Sonnet 5 | $0.00019 | $0.00558 |
| Haiku 4.5 | $0.00010 | $0.00279 |
Grade A, and why
data-wrangler 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 12d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Wrangler
Manipulate tabular data (CSV, Excel, JSON, Parquet, TSV) w/ pandas-powered scripts. Two scripts cover all operations: data_wrangler.py for data ops, excel_toolkit.py for Excel-specific features.
When to Use
- User asks to read, edit, filter, sort, or transform CSV/Excel/JSON/Parquet/TSV files
- User asks to merge/join datasets, deduplicate, fill missing values, or validate data
- User asks to create Excel workbooks w/ formatting, dropdowns, freeze panes, or multi-sheet
- User asks to pivot, unpivot, group-by, aggregate, sample, or split datasets
- User asks to add computed columns, rename columns, cast types, or apply formulas
- User asks to convert between data formats (CSV -> Excel, JSON -> Parquet, etc.)
- User asks to inspect/profile data structure, types, nulls, stats
Prerequisites
# Required
pip install pandas openpyxl
# Optional (per feature)
pip install pyarrow # Parquet support
pip install xlrd # Legacy .xls read
pip install pandasql # SQL queries on DataFrames
pip install fastparquet # Alternative Parquet engine
Quick Routing
| Task | Script | Command |
|---|---|---|
| Inspect/profile data | data_wrangler.py |
inspect |
| Filter rows | data_wrangler.py |
filter --where "expr" |
| Sort by columns | data_wrangler.py |
sort --by Col --desc |
| Group & aggregate | data_wrangler.py |
group --by Col --agg "Col:func" |
| Merge/join files | data_wrangler.py |
merge f2 --on Key --how left |
| Pivot / unpivot | data_wrangler.py |
pivot --index/--unpivot |
| Remove duplicates | data_wrangler.py |
dedupe --subset "Col" |
| Fill missing values | data_wrangler.py |
fill --column Col --strategy mean |
| Drop cols/rows | data_wrangler.py |
drop --columns "A,B" |
| Rename columns | data_wrangler.py |
rename --map "old:new" |
| Cast types | data_wrangler.py |
cast --column Col --dtype datetime |
| Computed columns | data_wrangler.py |
derive --formula "New = A + B" |
| Random sample | data_wrangler.py |
sample --n 100 |
| Split by values | data_wrangler.py |
split --by Region |
| Validate rules | data_wrangler.py |
validate --rules rules.json |
| Apply formulas | data_wrangler.py |
formula --expr "C=A+B" |
| Convert formats | data_wrangler.py |
convert -o data.xlsx |
| SQL queries | data_wrangler.py |
query --sql "SELECT..." |
| List Excel sheets | excel_toolkit.py |
sheets |
| Extract sheet | excel_toolkit.py |
extract --sheet Sales -o sales.csv |
| Combine -> xlsx | excel_toolkit.py |
combine *.csv -o combined.xlsx |
| Format headers | excel_toolkit.py |
format --header-style bold,blue --autowidth |
| Freeze panes | excel_toolkit.py |
freeze --at B2 |
| Auto-filter | excel_toolkit.py |
autofilter |
| Dropdown validation | excel_toolkit.py |
validate --column Status --values "Open,Closed" |
| Protect sheet | excel_toolkit.py |
protect --password secret |
| Create workbook | excel_toolkit.py |
create --columns "Name,Age" -o template.xlsx |
What ships with it
3 files 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.
- 12d ago First seen · 260 lines · 95 tokens per session scan A fb5eea504725
data-wrangler is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,792 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
xlsx
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for…
google-sheets
Read and write Google Sheets spreadsheets - get content, update cells, append rows, fetch specific ranges, search for spreadsheets, and view metadata. Use when user asks to: read a spreadsheet, update cells, add data to Google Sheets, find a spreadsheet, check sheet contents, export spreadsheet data, or get cell…
dgn-to-excel
Convert DGN files (v7-v8) to Excel databases. Extract elements, levels, and properties from infrastructure CAD files.
dwg-to-excel
Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.
ifc-to-excel
Convert IFC files (2x3, 4x1, 4x3) to Excel databases using IfcExporter CLI. Extract BIM data, properties, and geometry without proprietary software.
historical-data-manager
Extract, clean, and organize legacy construction data from archives. Migrate historical project data, cost records, and schedules into modern formats.