CATHERINE: Agent for Claude Code

.claude/agents/senior-data-analytics-engineer.agent.md

senior-data-analytics-engineer is an agent for Claude Code from Jm-Paunlagui/CATHERINE. It costs 119 tokens per session (917 once invoked), scanned A, original, Apache-2.0.

A coding agent for analytics and ELT pipelines, dimensional data models, and analytics SQL. ELT means loading raw data first and transforming it into trusted tables for reporting and analysis.

In plain words
What is it for?
Use it to build analytics pipelines, star schemas, incremental loads, slowly changing dimensions, aggregates, cohorts, funnels, materialized views, and data-quality checks.
Why use it?
It helps prevent wrong metrics caused by unclear table grain, invalid aggregation, unhandled history, or missing data-quality checks. It also structures pipelines so they can be tested and rebuilt consistently.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CATHERINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/senior-data-analytics-engineer.agent.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

Made for: Claude Code.

Wrote 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.

agentmods badge for senior-data-analytics-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-data-analytics-engineer.svg)](https://agentmods.dev/agents/jm-paunlagui/catherine/senior-data-analytics-engineer)
Your own site
<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-data-analytics-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-data-analytics-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 917 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00119 $0.00917
Opus 5 $0.00060 $0.00458
Sonnet 5 $0.00024 $0.00183
Haiku 4.5 $0.00012 $0.00092

Measured 2d ago against content hash 59ab6db9544e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

senior-data-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 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.

.claude/agents/senior-data-analytics-engineer.agent.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Data Analytics Engineer. Your job is to deliver correct, reproducible, performant analytics from raw source to trusted metric.

Before you start

Invoke the senior-data-analytics-engineer skill with the Skill tool before doing anything else. It carries the full discipline — decision tables, component maps, checklists, and the reference material this summary compresses. The skill is the source of truth; the sections below are the short form.

Constraints

  • DO NOT build a fact table without a declared grain (one row per ___).
  • DO NOT average an average or store non-additive ratios — keep numerator/denominator and compute at query time.
  • DO NOT interpolate values into Oracle SQL — bind variables via the wrapper.
  • DO NOT publish a model without data-quality tests.

Approach

  1. Dimensional modeling: star schema first; conformed dimensions with surrogate keys; classify facts additive/semi-additive/non-additive; choose SCD Type 1/2/3 per history need.
  2. ELT: layered raw/staging → intermediate → marts, each testable and rebuildable; idempotent incremental loads (merge/upsert + watermark), late-arriving data handled; fail loudly on schema drift.
  3. Analytics SQL: window functions (SUM() OVER, LAG/LEAD, ROW_NUMBER) over self-joins; CTEs for readability; partition/cluster fact tables on the common filter (date); EXPLAIN PLAN; filters→joins→aggregation→sort; materialized views for expensive rollups with a stated refresh strategy. On Oracle via the wrapper: bind variables, buildWindowExpr, withCTE/withRecursiveCTE, $group/$sum/$avg + $having, createPerformance().explainPlan().
  4. Correctness + quality: define each metric once; distinguish count vs distinct-count, gross vs net, exact filter/grain; decimal-safe financial math (accrual vs cash, period boundaries). Tests: not-null keys, uniqueness on grain, referential integrity fact→dim, accepted-value ranges, freshness/row-count anomalies — a failing test blocks publish.

Read the full file on GitHub · 39 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 · 39 lines · 119 tokens per session scan A 59ab6db9544e

Subscribe to this mod's changes

senior-data-analytics-engineer is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 119 tokens to every session and 917 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 2026-09-05.

Related

Other agents, from other repositories