duckdb

duckdb is a skill for Claude Code, Codex from G1Joshi/Agent-Skills. It costs 17 tokens per session (412 once invoked), scanned A, original, MIT.

A small SQL database that runs inside your application instead of as a separate server. It is built for analysing local files such as CSV, JSON, and Parquet, as well as data in object storage.

In plain words
What is it for?
Use it for local data analysis, Python or R data pipelines, and querying files in formats such as Parquet directly from applications or cloud storage.
Why use it?
It lets developers run analytical queries on large datasets without setting up a separate data warehouse or database service.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for local data analysis, Python or R data pipelines, and querying files in formats such as Parquet directly from applications or cloud storage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/g1joshi/agent-skills/duckdb
Install

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.

Any agent
npx skills add G1Joshi/Agent-Skills --skill duckdb
Clone the repo
git clone --depth 1 https://github.com/G1Joshi/Agent-Skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for duckdb

README.md
[![agentmods](https://agentmods.dev/badge/skills/g1joshi/agent-skills/duckdb/github.svg)](https://agentmods.dev/skills/g1joshi/agent-skills/duckdb)
Your own site
<a href="https://agentmods.dev/skills/g1joshi/agent-skills/duckdb"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/duckdb/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.

agentmods 80×15 button for duckdb

Your own site · 80×15
<a href="https://agentmods.dev/skills/g1joshi/agent-skills/duckdb"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/duckdb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00412
Opus 5 $0.00009 $0.00206
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 9d ago against content hash 1cd4e6e41ec9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

duckdb 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.

skills/databases/duckdb/SKILL.md · 58 lines

What it actually says

DuckDB

DuckDB is "SQLite for Analytics". It is an in-process SQL OLAP database. It runs inside your application process and is blazing fast for analytical queries on local files (Parquet, CSV, JSON).

When to Use

  • Local Analytics: Analyze millions of rows on your laptop in seconds.
  • Data Engineering: Process data in Python/R pipelines (replacement for Pandas).
  • Serverless Data Lake: Query S3 parquet files directly via Lambda without a running warehouse.

Quick Start (Python)

import duckdb

# Query local CSV directly
duckdb.sql("SELECT avg(price) FROM 'sales.csv' WHERE region='US'").show()

# Connect to S3
duckdb.sql("INSTALL httpfs; LOAD httpfs;")
duckdb.sql("SELECT count(*) FROM 's3://my-bucket/data.parquet'")

Core Concepts

Vectorized Execution

Standard DBs process row-by-row. DuckDB processes batches of columns (Vectors), utilizing modern CPU SIMD instructions.

Universal Format Reader

Can query CSV, JSON, Parquet, Arrow, SQLite, and Postgres tables as if they were local tables.

Zero Dependencies

Single binary/library.

Best Practices (2025)

Do:

  • Use Parquet: It is the native language of analytics. DuckDB + Parquet is incredible.
  • Replace Pandas: For datasets larger than RAM, DuckDB works (Disk spilling) where Pandas crashes.
  • Use explicitly typed SQL: DuckDB’s SQL dialect is very friendly and standard (Postgres-compatible).

Don't:

  • Don't use for Multi-User OLTP: It handles concurrency poorly (single writer). Use Postgres for that. Use DuckDB for analysis.

References

Changes

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.

  1. 9d ago First seen · 58 lines · 17 tokens per session scan A 1cd4e6e41ec9

Subscribe to this mod's changes

duckdb is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 412 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories