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 skills add olehsvyrydov/AI-development-team --skill data-engineergit clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/olehsvyrydov/ai-development-team/data-engineer)<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/data-engineer"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/data-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/data-engineer"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/data-engineer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00129 | $0.00601 |
| Opus 5.5 | $0.00052 | $0.00240 |
| Sonnet 5.5 | $0.00026 | $0.00120 |
| Haiku 4.5 | $0.00013 | $0.00060 |
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 today.
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.
What it actually says
Data Engineer (/data)
Command: /data · Category: Development
Gate Check (workflow)
Consult the workflow-engine skill first.
- Before implementing: the required upstream gates the workflow-engine determines apply must be
passed—ARCH_APPROVEDwhen adding a new pipeline/warehouse/streaming dependency or crossing a data boundary;SECOPS_APPROVEDwhen handling PII or external data sources; andAPPROVAL_GATEon thefulltrack. - On completion: pipelines ship with data-quality tests (freshness, volume, schema, null/uniqueness) and idempotent/backfillable design before
/rev.
When to use (and when not)
- Use for: ETL/ELT, dbt models & tests, warehouse/lakehouse modeling (star/snowflake, SCD), streaming pipelines, orchestration DAGs, CDC, data contracts & quality.
- Hand off instead when: OLTP schema/index/query tuning → /dba; app endpoints/business logic → /be; embeddings/RAG indexing → /ai; cloud infra/IaC for the platform → devops-engineer.
Core expertise
- Transformation: dbt (models, tests, snapshots, exposures), SQL modeling, incremental & SCD patterns.
- Storage: BigQuery, Snowflake, DuckDB, Postgres, object stores; partitioning, clustering, cost control.
- Movement: batch (Airbyte/custom) + streaming (Kafka, Flink, Spark Structured Streaming), CDC, exactly-once concerns.
- Orchestration: Airflow / Dagster / Prefect — idempotent, retriable, backfillable tasks; lineage.
- Quality & contracts: Great Expectations / dbt tests, freshness/volume checks, schema evolution, data contracts.
Standards
- Pipelines are idempotent and backfillable; reruns don't double-count.
- Every dataset has owner + tests + freshness SLA; transformations are version-controlled (dbt).
- Prefer ELT into a warehouse; keep transformations declarative and testable.
- Cost is a first-class concern (partition pruning, incremental builds).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 31 lines · 129 tokens per session scan A 9395ece76f22
data-engineer is a skill published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 601 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-19.
Other skills, from other repositories
bf-clarify
Use when brownfield analysis has open inferences or gaps that need human answers.
bf-rebuild-plan
Use when brownfield analysis is done and the app must become an ordered rebuild backlog.
bf-ui
Use when a rebuild must keep the legacy UI's screens and visual theme.
loop
Use when asked to loop or iterate a change until every gate is green.
bf-blueprint
Use when a rebuild's decisions and backlog exist and the target architecture must be drawn.
debug
Use when a bug, test failure, build failure, or unexpected behaviour is reported or observed, before proposing any fix.