A plug-in that queries and summarises CSV files with SQL without loading the entire file into the coding agent's context. CSV is a plain-text format for rows and columns, while SQL provides commands for filtering and aggregating those rows.

Use it to inspect table data, filter records, calculate summaries, and answer questions about CSV contents.

It makes large CSV files easier to inspect while keeping the agent's working context small. It is suited to read-only analysis rather than editing the source file.

csvql — Plugin for Claude Code by melihbirim

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.

Clone the repo

git clone --depth 1 https://github.com/melihbirim/csvql

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/melihbirim/csvql/plugin/github.svg)](https://agentmods.dev/plugins/melihbirim/csvql/plugin)

Your own site

<a href="https://agentmods.dev/plugins/melihbirim/csvql/plugin"><img src="https://agentmods.dev/badge/plugins/melihbirim/csvql/plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/melihbirim/csvql/plugin"><img src="https://agentmods.dev/badge/plugins/melihbirim/csvql/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill cost 80 tokens a session between them.

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.

Security

Grade A, and why

csvql 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 5d 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.

plugin/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "csvql",
  "displayName": "csvql",
  "version": "1.3.0",
  "description": "Answer questions about CSV files with read-only SQL, without loading the file into context. csvql can't write or reach the network, and --root keeps it inside chosen folders",
  "author": {
    "name": "Melih Birim"
  },
  "homepage": "https://github.com/melihbirim/csvql",
  "repository": "https://github.com/melihbirim/csvql",
  "license": "MIT",
  "privacyPolicyUrl": "https://melihbirim.github.io/csvql/privacy/"
}

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 80 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill csvql A 80 tokens

Files

What ships with it

1 file beside plugin.json 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.

icon.png 65 KB

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.

5d ago Changed 223e2401f70f
7d ago First seen · 14 lines scan A b5bef3afa117

Subscribe to this mod's changes

csvql is a plugin published in the GitHub repository melihbirim/csvql (30 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-31.

Analytics and metrics cli command-line csv csv-parser duckdb sql

csvql next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
csvqlmelihbirim/csvql	Plugin	30	yesterday	MIT	A	—	Claude Code
sqneilotoole/sq	Plugin	2.6k	yesterday	MIT	A	—	Claude Code
confluencepchuri/confluence-cli	Plugin	323	2d ago	MIT	A	—	Claude Code
tokenjamMetabuilder-Labs/tokenjam	Plugin	125	5d ago	MIT	A	—	Claude Code
axiom-cliaxiomhq/cli	Plugin	60	yesterday	MIT	A	—	Claude Code
sidemanticsidequery/sidemantic	Plugin	139	yesterday	AGPL-3.0	A	—	Claude Code
hnheartleo/hn-cli	Plugin	51	2mo ago	MIT	A	—	Claude Code