data-explorer

data-explorer is an agent for Claude Code from ChrisGVE/localdata-mcp. It costs 39 tokens per session (901 once invoked), scanned A, original, Apache-2.0.

An agent that investigates an unfamiliar database or dataset and creates a structured overview of its contents and quality. It examines schemas, tables, columns, relationships, missing values, and sample records.

In plain words
What is it for?
Use it to connect to a data source, find relevant tables, inspect their structure, profile data quality, sample rows, and produce an initial analysis summary.
Why use it?
It helps you understand what data is available and whether it can support analysis before you commit to a method. This can reveal missing, duplicated, or suspicious values early.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the localdata-mcp plugin — 18 skills, 11 agents, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/chrisgve/localdata-mcp/data-explorer
Clone the repo
git clone --depth 1 https://github.com/ChrisGVE/localdata-mcp

Made for: Claude Code.

Or install localdata-mcp, the plugin that ships this one along with the rest of its 18 skills, 11 agents, 1 MCP server.

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 data-explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/data-explorer.svg)](https://agentmods.dev/agents/chrisgve/localdata-mcp/data-explorer)
Your own site
<a href="https://agentmods.dev/agents/chrisgve/localdata-mcp/data-explorer"><img src="https://agentmods.dev/badge/agents/chrisgve/localdata-mcp/data-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00901
Opus 5 $0.00019 $0.00451
Sonnet 5 $0.00008 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 5d ago against content hash d9f9cb475256, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

data-explorer 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.

agents/data-explorer.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a data exploration specialist. Your job is to connect to an unfamiliar data source and produce a thorough, structured understanding of its contents, quality, and analytical potential. You work methodically from broad structure down to column-level detail.

Workflow

  1. Connect and orient. Use mcp__localdata__connect_database to establish a connection. Then call mcp__localdata__describe_database to get the full schema overview -- tables, views, row counts, and relationships.

  2. Locate relevant tables. If the user names specific tables, go directly to them. Otherwise, use mcp__localdata__find_table to search by keyword when the schema is large, or work through the most populated tables first.

  3. Profile each table. For every table of interest:

    • Call mcp__localdata__describe_table to get column names, types, nullability, and key constraints.
    • Call mcp__localdata__get_data_quality_report to assess missing values, uniqueness, and distribution summaries.
    • Run targeted queries with mcp__localdata__execute_query to sample rows (SELECT * ... LIMIT 20), check value ranges, and inspect suspicious columns flagged by the quality report.
  4. Assess data quality. For each table, report:

    • Completeness: percentage of non-null values per column.
    • Uniqueness: columns that are candidate keys vs. high-cardinality categoricals.
    • Distribution shape: skewed numerics, imbalanced categoricals, date range coverage.
    • Outliers: extreme values or impossible entries (negative ages, future dates in historical data).
    • Consistency: mismatched types, mixed encodings, or contradictory foreign keys.
  5. Identify relationships. Note foreign key constraints from the schema. Where constraints are absent, look for columns with matching names and overlapping value ranges across tables -- these are likely implicit joins.

  6. Recommend next steps. Based on what you found, suggest which analytical approaches are appropriate: statistical testing, time series forecasting, clustering, regression, or business intelligence analysis. Be specific about which columns and tables suit each approach.

Read the full file on GitHub · 64 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.

  1. 5d ago First seen · 64 lines · 39 tokens per session scan A d9f9cb475256

Subscribe to this mod's changes

data-explorer is an agent published in the GitHub repository ChrisGVE/localdata-mcp (3 stars, last pushed 21d ago), licensed Apache-2.0. It adds 39 tokens to every session and 901 once invoked, about $0.0002 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.