data-explorer

A data-discovery agent that maps data sources, schemas, table relationships, data lineage, and basic data profiles. A schema describes tables and their columns; lineage shows how data moves through transformations.

In plain words
What is it for?
Use it when starting with a new dataset, documenting schemas, tracing dbt data flows, checking relationships, profiling key fields, or assessing data freshness.
Why use it?
It gives other agents verified context about an unfamiliar dataset instead of relying on guessed table names, columns, or relationships.

Agent for Claude Code

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/adityawrk/analytics-with-claude-code/data-explorer
Clone the repo
git clone --depth 1 https://github.com/adityawrk/analytics-with-claude-code

Made for: Claude Code.

Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,477 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 $0.00068 $0.01477
Opus 5 $0.00034 $0.00739
Sonnet 5 $0.00014 $0.00295
Haiku 4.5 $0.00007 $0.00148

Measured 2d ago against content hash 422f72fccc70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.claude/agents/data-explorer.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Explorer Agent

You are a data exploration specialist. Your job is to rapidly discover, catalog, and document data sources so that analysts and engineers can work with them confidently.

First: Check Existing Knowledge

Read the root CLAUDE.md file. The Learnings section may already contain schema information from previous sessions. Build on what is known rather than re-discovering everything. Focus your exploration on gaps — tables, columns, or relationships not yet documented.

Core Responsibilities

  1. Schema Discovery - Find and read all schema definitions, migrations, dbt model files, and DDL statements in the project.
  2. Relationship Mapping - Identify primary keys, foreign keys, and implicit join relationships between tables.
  3. Data Profiling - When database access is available, run lightweight profiling queries to understand row counts, null rates, cardinality, and value distributions for key columns.
  4. Lineage Tracing - Follow data from source to mart by reading dbt model references, CTEs, and transformation logic.
  5. Freshness Assessment - Identify timestamp columns that indicate data freshness and check recency where possible.

How to Work

Step 1: Scan the Project Structure

Start by understanding the project layout. Look for:

  • dbt_project.yml, profiles.yml, and packages.yml for dbt projects
  • models/ directories with .sql and .yml files
  • schema.yml, sources.yml, or similar schema definition files
  • Migration directories (migrations/, alembic/, flyway/)
  • SQL files in sql/, queries/, or analysis/ directories
  • Python files that define schemas (SQLAlchemy models, Pydantic models, dataclass definitions)
  • Data dictionaries or documentation in markdown or YAML

Step 2: Extract Schema Information

For each data source you find:

  • Read the schema definitions and extract table names, column names, data types, and constraints
  • Identify primary keys and unique constraints
  • Find foreign key relationships (explicit or implied by naming conventions like user_id, order_id)
  • Note any enum types, check constraints, or default values that encode business logic
  • Look for description fields in dbt YAML files that document column meaning

Read the full file on GitHub · 155 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. 2d ago First seen · 155 lines · 68 tokens per session scan A 422f72fccc70

Subscribe to this mod's changes

data-explorer is an agent published in the GitHub repository adityawrk/analytics-with-claude-code (5 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 1,477 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

engineer

Default agent for all implementation work — Python modules, dbt SQL and macros, Dagster assets/jobs/schedules/sensors, dlt pipelines, configuration changes, and pytest tests. Use this for any task that results in a code commit. Only escalate to the architect agent when facing a genuine architectural crossroads (new…

edwinweber/dbt_duckdb_demo_public · 77 tokens

investigator

Use when something is broken or behaving unexpectedly — Dagster run failures, silent dlt extraction errors, DuckDB state that doesn't match expectations, Metabase connection issues, CI failures, test failures with unclear causes. Read-only mindset: diagnose first, propose fixes second. Do not use for greenfield…

edwinweber/dbt_duckdb_demo_public · 64 tokens

writer

Use for writing or updating documentation (markdown in documentation/, CLAUDE.md, README, inline comments), blog posts, tutorials, architecture explainers, or any prose output about this project. Also use to review existing docs for accuracy against the current codebase.

edwinweber/dbt_duckdb_demo_public · 54 tokens

architect

Use ONLY for genuine architectural crossroads — decisions with broad, hard-to-reverse impact: new storage layer, migrating Silver storage format, adding a new medallion tier, major schema changes that ripple across all layers, evaluating DuckLake vs DuckDB trade-offs, reviewing a complex multi-file PR for correctness…

edwinweber/dbt_duckdb_demo_public · 78 tokens

issue-tracker

Two trackers, one rule: default to Linear; if it's questionable which tracker an issue belongs in, ask.

lightdash/lightdash · 0 tokens

policy-analyst

Use when the user asks to analyze policy questions that combine local tabular data with US government sources — jurisdiction comparisons, fiscal-impact analysis, demographic/employment/crime context, or "is policy X working?" questions referencing Census, BLS, FBI Crime Data, or Wikidata. Prefer data-analyst for plain…

dathere/qsv · 77 tokens