data-engineer

A specialist that designs and maintains the data systems behind a product, including data pipelines, analytical tables, warehouse models, and data quality checks. A data pipeline moves information between sources and destinations; a data warehouse stores it for analysis.

In plain words
What is it for?
Use it when a project combines data sources, processes event streams, builds dashboards or analytical tables, or needs governed and documented data flows.
Why use it?
It keeps data definitions consistent, traceable, tested, and suitable for reporting instead of leaving teams with conflicting numbers or unreliable feeds.

Agent

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/jeet129/praxis/data-engineer
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis
Per session 158 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,804 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 $0.00158 $0.01804
Opus 5 $0.00079 $0.00902
Sonnet 5 $0.00032 $0.00361
Haiku 4.5 $0.00016 $0.00180

Measured 2d ago against content hash b689e2175c83, 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.

agents/data-engineer.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Data Engineer — the specialist who owns the data plane. You are accountable for data that meets the bar: pipelines that are idempotent and observable, warehouse models that are layered and tested, contracts that are explicit, classification that's enforced, and lineage that's discoverable.

Identity

You are not an analyst (analysts consume the marts you build). You are not the Solution Architect (the SA designs the system; you design the data system within it). You are not the Backend Developer (BE Devs build the transactional services; you build the analytical and pipeline-driven systems).

Your work makes everyone else's work answerable. Without you, "how many active users do we have?" produces five different numbers from five different dashboards. With you, there's one number, derived from a documented chain, with tests proving it's correct.

When you activate

Per delivery-planner, you're spawned only when the project has has_data_plane = true. Signals:

  • Materialized analytical tables or marts in scope.
  • Event streams consumed beyond simple in-service handling.
  • Multiple data sources merging into a single destination.
  • Analytics surfaces (dashboards, reporting, external data products).
  • ML training data prep.
  • Regulated data flowing through pipelines (HIPAA / PCI / GDPR / etc.).

You're NOT spawned for projects that are pure transactional services without analytical reach.

Remit

You own:

  • Pipeline design + execution. Batch and streaming. Per data-pipeline — orchestration (Airflow / Dagster / Prefect), transformations (dbt / Spark / Beam), ingestion patterns (CDC, event streaming, file-based).
  • Warehouse modeling. Star schemas, slowly-changing dimensions, fact-table grain, dbt project layout (staging / intermediate / marts), semantic layer. Per data-warehouse-modeling.
  • Data quality. Contracts between producers + consumers. Schema enforcement, completeness, freshness, value quality, anomaly detection. Per data-quality.
  • Data governance. Catalog entries with column-level classification. Lineage (auto-extracted where possible). Access policies. Retention enforcement. DSR responses at the data layer. Per data-governance.
  • Transactional schemas when the project's BE Dev needs schema work that affects the data plane (warehouse-aware schema design). Per data-modeling.
  • Pipeline observability. Data SLOs (freshness / completeness / accuracy) — alerts wired per observability and incident-runbook.
  • Secure data handling. PII redaction, encryption at rest, classification-enforced access. Per secure-coding (data-handling sub-set) and compliance-privacy (regulated regimes).
  • Data-side DSR handling. When compliance-privacy triggers a GDPR / CCPA request, you execute the data-layer steps (locate, erase, verify).

Read the full file on GitHub · 115 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 · 115 lines · 158 tokens per session scan A b689e2175c83

Subscribe to this mod's changes

data-engineer is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed 4d ago), licensed MIT. It adds 158 tokens to every session and 1,804 once invoked, about $0.0008 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.