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 skills add richard-gyiko/data-wrangler-plugin --skill data-wranglergit clone --depth 1 https://github.com/richard-gyiko/data-wrangler-pluginWrote 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/richard-gyiko/data-wrangler-plugin/data-wrangler)<a href="https://agentmods.dev/skills/richard-gyiko/data-wrangler-plugin/data-wrangler"><img src="https://agentmods.dev/badge/skills/richard-gyiko/data-wrangler-plugin/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/richard-gyiko/data-wrangler-plugin/data-wrangler"><img src="https://agentmods.dev/badge/skills/richard-gyiko/data-wrangler-plugin/data-wrangler.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00131 | $0.02137 |
| Opus 5 | $0.00066 | $0.01069 |
| Sonnet 5 | $0.00026 | $0.00427 |
| Haiku 4.5 | $0.00013 | $0.00214 |
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 9d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Wrangler
Transform and export data using DuckDB SQL.
Contents
- Usage - Command syntax and Windows escaping
- Explore Mode - Quick data profiling
- Query Mode - Return results to Claude
- Write Mode - Export to files
- Request/Response Format - JSON structure
- Source Types - File, database, and cloud sources
- Transformations - SQL patterns reference
- Secrets - Secure credential handling
Usage
IMPORTANT - Windows Shell Escaping:
- Always
cdto the skill directory first - Use double quotes for echo with escaped inner quotes (
\") - Use forward slashes in file paths
cd "<skill_directory>" && echo "{\"query\": \"SELECT * FROM 'D:/path/to/file.csv'\"}" | uv run scripts/query_duckdb.py
Explore Mode
Get schema, statistics, and sample in one call. Use before writing queries to understand data structure.
{"mode": "explore", "path": "D:/data/sales.csv"}
Response:
{
"file": "D:/data/sales.csv",
"format": "csv",
"row_count": 15234,
"columns": [
{"name": "order_id", "type": "BIGINT", "null_count": 0, "null_percent": 0.0},
{"name": "customer", "type": "VARCHAR", "null_count": 45, "null_percent": 0.3}
],
"sample": "| order_id | customer | ... |\\n|----------|----------|-----|\\n| 1001 | Alice | ... |"
}
Options:
sample_rows: Number of sample rows (default: 10, max: 100)sources: For database tables (same as query mode)
Query Mode
Return results directly to Claude for analysis.
Direct File Queries
{"query": "SELECT * FROM 'data.csv' LIMIT 10"}
Multi-Source Joins
{
"query": "SELECT s.*, p.category FROM sales s JOIN products p ON s.product_id = p.id",
"sources": [
{"type": "file", "alias": "sales", "path": "/data/sales.parquet"},
{"type": "file", "alias": "products", "path": "/data/products.csv"}
]
}
What ships with it
4 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.
- 9d ago First seen · 294 lines · 131 tokens per session scan A 7718c08a3bb4
data-wrangler is a skill published in the GitHub repository richard-gyiko/data-wrangler-plugin (3 stars, last pushed 8mo ago), licensed MIT. It adds 131 tokens to every session and 2,137 once invoked, about $0.0007 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
cloudflare-d1
Cloudflare D1 serverless SQLite on edge. Use for databases, migrations, bindings, or encountering D1ERROR, statement too long, too many requests queued errors.
cloudflare-vectorize
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
cloudflare-kv
Cloudflare Workers KV global key-value storage. Use for namespaces, caching, TTL, or encountering KVERROR, 429 rate limits, consistency issues.
bun-drizzle-integration
Use when integrating Drizzle ORM with Bun's SQLite driver for type-safe schema definitions and migrations.
bun-redis
Use when working with Redis in Bun (ioredis, Upstash), caching, pub/sub, session storage, or key-value operations.
bun-sqlite
Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.