All plugins

data-wrangler

Deterministic tools for local tabular data — the counting a model should never guess at. table_profile computes an exact profile of a CSV/TSV/JSON/JSONL file (row and column counts, inferred types, null counts and percentages, distinct counts, min/max/mean/median, top text values, duplicate-row and empty-row counts). table_query runs one read-only SQL query over the file in SQLite (table data): writes are refused up front and again by a connection authorizer, results are row-capped with the total matched count always reported, and a 10-second query budget applies. table_clean writes a cleaned copy — snake_case headers, trimmed cells, fully-empty rows dropped, exact duplicates removed (optionally on a subset of columns) — and returns a full change report; the input file is never modified. A bundled data-tables skill teaches the profile → query → clean → verify workflow. Python standard library only (csv/json/sqlite3): no dependencies, no configuration, no credentials. Disclosure — Reads local CSV/TSV/JSON/JSONL files named in a tool call (Hermes' read blocklist applies), and table_clean writes one cleaned copy to a model-chosen path (Hermes' write denylist applies, and approval-gated paths are refused); no network calls, no shell, no state kept.

yogeshchoudhary555Toolsv1.0.0Updated 5 days ago

About

Deterministic tools for local tabular data — the counting a model should never guess at. table_profile computes an exact profile of a CSV/TSV/JSON/JSONL file (row and column counts, inferred types, null counts and percentages, distinct counts, min/max/mean/median, top text values, duplicate-row and empty-row counts). table_query runs one read-only SQL query over the file in SQLite (table data): writes are refused up front and again by a connection authorizer, results are row-capped with the total matched count always reported, and a 10-second query budget applies. table_clean writes a cleaned copy — snake_case headers, trimmed cells, fully-empty rows dropped, exact duplicates removed (optionally on a subset of columns) — and returns a full change report; the input file is never modified. A bundled data-tables skill teaches the profile → query → clean → verify workflow. Python standard library only (csv/json/sqlite3): no dependencies, no configuration, no credentials. Disclosure — Reads local CSV/TSV/JSON/JSONL files named in a tool call (Hermes' read blocklist applies), and table_clean writes one cleaned copy to a model-chosen path (Hermes' write denylist applies, and approval-gated paths are refused); no network calls, no shell, no state kept.

data-wrangler — deterministic data tools for Hermes Agent

Profile it. Query it. Clean it. With exact numbers, not vibes.

An LLM is good at reasoning about data and bad at counting it. Ask a model how many
nulls a column has, what the average order value is, or whether a CSV has duplicate
rows, and it will happily estimate from whatever preview fits in context.

data-wrangler gives Hermes three tools that compute the answer from the whole
file, deterministically, using only the Python standard library:

ToolWhat it does
table_profileExact profile of a CSV/TSV/JSON/JSONL file: row & column counts, inferred column types, null counts/percentages, distinct counts, min/max/mean/median for numeric columns, top values for text columns, duplicate-row and empty-row counts.
table_queryRuns one read-only SQL query (SELECT/WITH) over the file, loaded into SQLite as the table data. Writes are denied twice: up front, and by a SQLite authorizer on the connection. Returns rows + total matched count. 10-second query budget.
table_cleanWrites a cleaned copy (input never modified): headers normalised to snake_case, whitespace trimmed, fully-empty rows dropped, exact duplicates removed (optionally on a column subset) — and returns a full change report: rows in/out, duplicates dropped, cells trimmed, headers renamed.

Plus a bundled skill (data-tables) that teaches the agent the workflow:
profile first → answer with SQL → clean explicitly → verify the result.

Why a plugin, not a prompt

A prompt can tell the model to "be careful with numbers". It cannot make the model
read 50,000 rows, count duplicates exactly, or run a GROUP BY without arithmetic
slips. These tools do the counting in code — the model's job goes back to deciding
what to ask and explaining the answer. Same input → same output, every time.

Install

From the Hermes plugin catalog (once listed):

hermes plugins install data-wrangler

Or from git:

hermes plugins install yogeshchoudhary555/hermes-data-wrangler

Or manually: copy this directory to ~/.hermes/plugins/data-wrangler and enable it.

Requires Hermes >= 0.22. No Python dependencies (standard library only), no API
keys, no configuration.

Usage

Just talk to Hermes about a data file:

"What's actually in ~/Downloads/messy_sales.csv?"

→ table_profile reports 14 rows, one fully-empty row, one exact duplicate,
Price (USD) at type float with a missing value, Region needing a trim.

"Which region brought in the most revenue?"

→ table_query runs
SELECT " Region " , SUM("Price (USD)" * "Units Sold") AS revenue FROM data GROUP BY 1 ORDER BY 2 DESC
and answers from the computed result.

"Clean it up for me."

→ table_clean writes messy_sales.cleaned.csv and reports:
rows 14 → 12, 1 empty row dropped, 1 duplicate dropped, 3 cells trimmed,
headers renamed to order_id, product_name, region, price_usd, units_sold, order_date.

See examples/messy_sales.csv for the demo file used above.

Tool reference

table_profile

  • path (required): CSV, TSV, JSON (array of objects, or an object with a
    rows/data/records/items array), or JSONL file.
  • Null tokens recognised: empty, NA, N/A, null, none, NaN (case-insensitive).
  • Limits: 100 MB file, 1,000,000 rows.

table_query

  • path (required), sql (required, single read-only query over table data),
    limit (optional, default 100, max 1000 returned rows; total_matched always reported).
  • Numeric-looking columns are stored as REAL so aggregates and sorting are numeric;
    everything else is TEXT. Original column names are preserved — quote names with
    spaces: "Price (USD)".

table_clean

  • path (required), out (optional; default <name>.cleaned.csv beside the input;
    .json suffix writes JSON), dedupe (optional, default true),
    dedupe_columns (optional subset, by original or cleaned name).
  • The input file is never modified; out equal to the input is refused.

Disclosure (catalog rule 13)

  • Files: reads only the local data files the user (or agent) names in a tool
    call. Writes exactly one file per table_clean call — the cleaned output the
    user asked for.
  • Network: none. Shell commands: none. Credentials: none.
  • Background processes / telemetry: none.
  • Queries run in an in-memory SQLite database; nothing is persisted anywhere,
    and no plugin state is kept between calls.

Development

Validate exactly the way catalog CI does:

hermes plugins doctor /path/to/data-wrangler --ci
hermes plugins validate /path/to/data-wrangler --install-deps

License

MIT

README from the reviewed commit 7c32cb8; it updates when the author re-pins.

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section