A database access skill for exploring and querying SQL and NoSQL databases through local desktop applications. SQL includes systems such as PostgreSQL and SQLite; NoSQL includes systems such as MongoDB and DynamoDB.

Use it to discover connections, list tables or collections, run SQL, and query Elasticsearch, MongoDB, DynamoDB, and other supported databases.

It gives coding work a common way to list schemas, inspect data, and run queries across different database systems without handling database credentials directly in the tools.

data-studio — Skill for Claude Code and Codex by geek-fun

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 geek-fun/data-studio-agent --skill data-studio

Clone the repo

git clone --depth 1 https://github.com/geek-fun/data-studio-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/geek-fun/data-studio-agent/data-studio/github.svg)](https://agentmods.dev/skills/geek-fun/data-studio-agent/data-studio)

Your own site

<a href="https://agentmods.dev/skills/geek-fun/data-studio-agent/data-studio"><img src="https://agentmods.dev/badge/skills/geek-fun/data-studio-agent/data-studio/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/skills/geek-fun/data-studio-agent/data-studio"><img src="https://agentmods.dev/badge/skills/geek-fun/data-studio-agent/data-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 868 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.

Model	Per session	Once invoked
Fable 5.1	$0.00147	$0.00868
Opus 5.5	$0.00059	$0.00347
Sonnet 5.5	$0.00029	$0.00174
Haiku 4.5	$0.00015	$0.00087

Measured 8d ago against content hash 423aa6501678, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

data-studio 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 8d 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.

packages/data-studio/skills/data-studio/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Studio

MCP tools prefixed data_studio__* route to the user's local dockit (NoSQL) and sqlkit (SQL) desktop apps over a localhost-only bridge (127.0.0.1). This skill explains how to use them well.

Prerequisites

dockit and/or sqlkit installed and running, with at least one database connection added.
Settings → MCP Bridge → Auto-start enabled in the desktop apps (on by default).

If tools fail to connect, tell the user to launch the desktop apps and check Settings → MCP Bridge. Never ask the user for credentials: real credentials are resolved inside the apps, and tools only ever accept an opaque connection_id.

Workflow

Start with data_studio__list_connections (or data_studio__get_status) to discover running backends and connection IDs. These two tools have no app segment; all others are four-segment names.
Route by app + backend; tool names follow data_studio__{app}__{backend}__{action}:
- SQL databases: data_studio__sqlkit__sqlkit__* (e.g. data_studio__sqlkit__sqlkit__execute_query)
- Elasticsearch/OpenSearch: data_studio__dockit__es__*
- MongoDB: data_studio__dockit__mongo__*
- DynamoDB: data_studio__dockit__dynamo__*
Explore before querying: list_databases → list_tables / cat_indices / list_collections → describe_table / get_mapping → then execute_query / search / find.
Reference connections strictly by a connection_id returned by the listing tools; never fabricate IDs.
Show the user every statement executed, with row/record counts and a short interpretation.

Permission tiers

Tier	Examples	Behavior
Safe (Read Only)	schema reads, `execute_query`, `search`, `find`	run freely under the default Read Only mode
Elevated	`execute_write`, index/mapping/alias changes, `insert_`, `update_`	allowed only when the app is in Data Read-Write mode
Destructive	`execute_delete`, `execute_ddl`, `drop_`, `delete_`, `truncate_*`	require Full Access AND explicit user confirmation in the client

Read the full file on GitHub · 53 lines

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.

8d ago First seen · 53 lines · 147 tokens per session scan A 423aa6501678

Subscribe to this mod's changes

data-studio is a skill published in the GitHub repository geek-fun/data-studio-agent (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 147 tokens to every session and 868 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-31.

Claude Code Databases agentic-ai ai-agent cursor dynamodb

data-studio next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
data-studiogeek-fun/data-studio-agent	Skill	3	3d ago	Apache-2.0	A	147	Claude Code, Codex
postgresql-table-designwshobson/agents	Skill	42k	2d ago	MIT	A	37	Claude Code
sql-optimization-patternswshobson/agents	Skill	42k	2d ago	MIT	A	44	Claude Code
event-store-designwshobson/agents	Skill	42k	2d ago	MIT	A	33	Claude Code
cqrs-implementationwshobson/agents	Skill	42k	2d ago	MIT	A	35	Claude Code
projection-patternswshobson/agents	Skill	42k	2d ago	MIT	A	36	Claude Code
dynamodbericrisco/rsc-harness	Skill	529	3d ago	MIT	A	82	Claude Code, Codex