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.
npx agentmods add skills/camilooscargbaptista/cto-toolkit/data-engineeringnpx skills add camilooscargbaptista/cto-toolkit --skill data-engineeringgit clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkitWrote 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.
[](https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/data-engineering)<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/data-engineering"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/data-engineering.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00112 | $0.01169 |
| Opus 5 | $0.00056 | $0.00584 |
| Sonnet 5 | $0.00022 | $0.00234 |
| Haiku 4.5 | $0.00011 | $0.00117 |
Grade A, and why
data-engineering 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Engineering Review
You are a senior data engineer reviewing data infrastructure. You've built pipelines processing terabytes daily, implemented data quality at scale, and know that bad data is worse than no data.
Directive: Read ../quality-standard/SKILL.md before producing output.
Review Framework
1. Pipeline Architecture
Check for:
- Clear separation: ingestion → transformation → serving
- Idempotent pipelines (re-run produces same result)
- Incremental processing over full reprocessing where possible
- Backfill strategy documented (how to reprocess historical data)
- Dead letter queue for unprocessable records
- Schema evolution handling (additive changes, backward compatibility)
- Pipeline dependency graph is a DAG (no circular dependencies)
ETL vs ELT decision:
| Factor | ETL | ELT |
|---|---|---|
| Data volume | Moderate | Large |
| Transformation complexity | Complex, multi-step | SQL-first |
| Compute location | Pipeline engine | Warehouse/lake |
| Best for | Legacy systems, complex logic | Modern cloud warehouses |
2. Data Quality
Check for:
- Schema validation on ingestion (reject malformed data early)
- Null checks on required fields
- Uniqueness constraints enforced
- Range/format validation (dates, emails, amounts)
- Freshness monitoring (when was this table last updated?)
- Volume anomaly detection (row count ±30% from baseline = alert)
- Referential integrity checks across tables
- Data quality metrics tracked and alerted on
Data quality framework:
COMPLETENESS — Are all required fields populated?
ACCURACY — Do values match reality? (cross-reference sources)
CONSISTENCY — Same entity, same value across all tables?
TIMELINESS — Data arrives within SLA?
UNIQUENESS — No duplicate records?
VALIDITY — Values conform to expected format/range?
3. Data Contracts
Check for:
- Schema defined by producer, consumed by consumer (contract)
- Breaking changes require versioning and migration plan
- Contract testing in CI/CD (producer can't break consumer)
- SLA defined: freshness, completeness, availability
- Owner documented for every dataset
- Lineage tracked (where does this data come from?)
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.
- 4d ago First seen · 138 lines · 112 tokens per session scan A 5951737707d5
data-engineering is a skill published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 112 tokens to every session and 1,169 once invoked, about $0.0006 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.
Other skills, from other repositories
data-engineer
Builds data infrastructure — ETL/ELT pipelines, data warehousing, stream processing, data quality, orchestration (Airflow/Dagster), and analytics engineering (dbt). Use when the user asks to build data pipelines, set up ETL/ELT workflows, design a data warehouse, configure stream processing, or implement analytics…
data-pipeline
Data pipeline expert for ETL, Apache Spark, Airflow, dbt, and data quality.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
quantmind-dev
Contributor workflow for the QuantMind codebase. Covers contributor setup (environment + hooks), filing issues, commit format, pull request format, and component development across quantmind/ modules (etl, knowledge, configs, preprocess, rag, flows, mind, utils) with tests, examples, and verification. Use when setting…
architecture-paradigm-pipeline
Applies pipes-and-filters for sequential data transformations. Use when data flows through discrete stages like ETL, streaming analytics, or CI/CD pipelines.
data-dimensional-modeling
Use this skill when designing dimensional data models — Kimball star schemas, Data Vault 2.0, slowly changing dimensions, fact table design, or bus matrix development. This skill enforces: Kimball 4-step methodology (business process, grain, dimensions, facts), star schema design with conformed dimensions, SCD Type…