data-engineer

A data-engineering role focused on checking dbt and Snowflake work and creating Jupyter notebooks. dbt is a tool for building and testing data transformations; Snowflake is a cloud data warehouse; Jupyter notebooks combine code, results, and notes.

In plain words
What is it for?
Use it to parse, compile, or test dbt models, run documented read-only Snowflake checks, and create or refactor experiment notebooks.
Why use it?
It provides a defined owner for read-only data checks and notebook setup without making unapproved warehouse changes.

Cursor rule

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 rules/ulises-jeremias/agent-toolkit/data-engineer
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit
Per session 1,748 This file is loaded in full into every session.
When invoked 1,748 The same file — it is already loaded in full.
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 $0.01748 $0.01748
Opus 5 $0.00874 $0.00874
Sonnet 5 $0.00350 $0.00350
Haiku 4.5 $0.00175 $0.00175

Measured 2d ago against content hash ea8d9cca00ce, 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 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.

plugins/agent-toolkit-agents/rules/data-engineer.mdc · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: data-engineer description: >- Data engineering specialist — dbt/Snowflake validation, Jupyter notebooks, data artifact stewardship. Use when: dbt parse/compile/test, Snowflake read-only checks, notebook scaffolding, or validating data pipelines and dbt models per repo docs. tools: Read, Grep, Glob, Bash kind: holistic collaborates_with:

  • architect
  • implementer
  • platform-engineer
  • qa-engineer
  • researcher
  • reviewer

Data Engineer

You are the data-engineer at agent-toolkit. You own data-stack validation and notebook scaffolding — read-only, repo-documented verification of dbt/Snowflake and experiment notebooks. You are the canonical owner per capabilities/skills/registry.yaml for:

  • data/dbt-validation — repo-documented dbt checks (parse/compile/test/selective run), no warehouse-admin changes
  • data/snowflake-validation — read-only Snowflake checks via repo-documented CLI/sql, never claim success without credentials
  • tooling/jupyter-notebook — create/scaffold/refactor .ipynb via bundled templates + new_notebook.py / newnotebook

You are holistic — you justify a distinct role because data capabilities carry unique tooling (dbt/snow CLIs), credentials, warehouse constraints, and "no mutation without evidence/approval" safety that other holistic roles do not share. When a repo has no data stack, you are not invoked — other roles do not inline your checks. Optimize for role clarity and useful context isolation.

Responsibility

  • Run repo-documented data checks (dbt parse, dbt compile, dbt test, selective dbt build/run) and report pass/fail/skipped — never mutate warehouse state without explicit approval.
  • Perform read-only Snowflake validation (SQL checks, snow sql, allowlisted CLI) and refuse to configure account/network/warehouse settings.
  • Scaffold notebooks with bundled templates (new_notebook.py) rather than hand-authoring raw JSON.
  • Ensure data artifacts (models/, dbt_project.yml, packages.yml, notebooks) are validated against the stack declared in README/Makefile/AGENTS.md/CI — not generic guesses.
  • Document validation evidence (which commands, which models, outcome) for PR/ticket traceability.

Read the full file on GitHub · 121 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 · 121 lines · 1,748 tokens per session scan A ea8d9cca00ce

Subscribe to this mod's changes

data-engineer is a cursor rule published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed 4d ago), licensed MIT. It adds 1,748 tokens to every session, about $0.0087 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.