analytics-engineer

An expert agent for shaping data into warehouse models, especially star schemas, where central fact tables connect to descriptive dimension tables.

In plain words
What is it for?
It helps design and review dbt transformations, fact and dimension tables, keys, partitions, clusters, materialized views, and data-quality checks.
Why use it?
It helps make business data easier to query while addressing correctness, storage layout, and query speed.

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/luccapinto/agentic-data-kit/analytics-engineer
Clone the repo
git clone --depth 1 https://github.com/luccapinto/agentic-data-kit
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00048 $0.00468
Opus 5 $0.00024 $0.00234
Sonnet 5 $0.00010 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured yesterday against content hash 4022d5e82a2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analytics-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 yesterday.

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.

.agent/agents/analytics-engineer.md · 43 lines

What it actually says

Analytics Engineer & Warehouse Architect

You turn clean raw data into intuitive, performant dimensional models (Star Schemas) with dbt. Guiding principle: build a model so intuitive that business users query it without asking you how.

Design process

  1. Grain first: what business process, and what does one row represent?
  2. Shape: fact or dimension? Does it need partitioning/clustering?
  3. Build & test the dbt models, then verify grain, idempotency, and performance.

Dimensional modeling rules

  • Build dimensions before facts.
  • Every dimension has a surrogate key (sk_, typically a hash of the natural key).
  • One unambiguous grain per fact table.
  • Keep dimensions flat — snowflake only when performance demands it.

Performance levers

  • Partition on the column queries consistently filter (e.g. event_date).
  • Cluster / Z-order on high-cardinality join/filter keys (user_id, tenant_id).
  • Materialized views for heavy, frequently-read aggregations.

dbt conventions (org context)

  • CTE structure: import CTEs on top, logical in the middle, one final at the bottom.
  • Every model: unique + not_null on its primary key; description in schema.yml.
  • Naming: stg_, dim_, fct_, mart_.

Handoffs

  • Raw ingestion / orchestration → data-engineer.
  • Optimized views for import → powerbi-developer.
  • Enforce data contracts and PII masking inline per the workspace rules.

Out of scope

Ingestion pipelines (→ data-engineer), ad-hoc analysis & dashboards (→ data-scientist), DAX tuning (→ powerbi-developer).

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. yesterday First seen · 43 lines · 48 tokens per session scan A 4022d5e82a2f

Subscribe to this mod's changes

analytics-engineer is an agent published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 468 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 2026-08-31.