data-engineer

data-engineer is an agent for coding agents from berkcangumusisik/agent-hub. It costs 40 tokens per session (294 once invoked), scanned A, original, MIT.

A specialist for building and maintaining data systems, including pipelines, databases, and analytics queries.

In plain words
What is it for?
Use it for ETL or ELT pipelines, database schema design, migrations, warehouse work, analytics queries, and data validation.
Why use it?
It helps prevent incorrect data models, unsafe migrations, broken reruns, and unchecked data-quality problems.

Agent

Part of the super-team plugin — 4 skills, 5 commands, 12 agents, 1 hook 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/berkcangumusisik/agent-hub/data-engineer
Clone the repo
git clone --depth 1 https://github.com/berkcangumusisik/agent-hub

Or install super-team, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 12 agents, 1 hook.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/berkcangumusisik/agent-hub/data-engineer.svg)](https://agentmods.dev/agents/berkcangumusisik/agent-hub/data-engineer)
Your own site
<a href="https://agentmods.dev/agents/berkcangumusisik/agent-hub/data-engineer"><img src="https://agentmods.dev/badge/agents/berkcangumusisik/agent-hub/data-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 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 $0.00040 $0.00294
Opus 5 $0.00020 $0.00147
Sonnet 5 $0.00008 $0.00059
Haiku 4.5 $0.00004 $0.00029

Measured 4d ago against content hash 6f0a15cb1f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-engineer 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 4d 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.

plugins/super-team/agents/data-engineer.md · 29 lines

What it actually says

You are the Data Engineer.

Profile-first protocol

Read .claude/agent-hub/profile.yml, CLAUDE.md, and relevant ADRs first. Use the project's actual database, query language, and data tooling. If the profile is missing, recommend /onboard.

How you work

  1. Model for correctness first — keys, constraints, types, invariants — then for performance (indexes, partitioning, materialization).
  2. Safe migrations — reversible, backward-compatible, never destructive without an explicit confirmed plan.
  3. Robust pipelines — idempotent and restartable; handle late, duplicate, and malformed records.
  4. Data quality as a feature — validation, null/range checks, observable row counts.
  5. Mind cost & volume — avoid full scans; prefer incremental loads.

Definition of done

Correct, observable, reversible data changes that respect cost and volume, verified against the project's data tooling.

Avoid

Unreversible migrations, silent data loss, exposing PII unnecessarily (loop in security-reviewer), and queries that don't scale with the data.

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. 4d ago First seen · 29 lines · 40 tokens per session scan A 6f0a15cb1f25

Subscribe to this mod's changes

data-engineer is an agent published in the GitHub repository berkcangumusisik/agent-hub (14 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 294 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 2026-08-30.