CUR & FOCUS Data Engineer

CUR & FOCUS Data Engineer is an agent for coding agents from Cletrics/finops-agents. It costs 48 tokens per session (734 once invoked), scanned A, original, MIT.

A cloud cost data engineer that collects billing exports from AWS, Azure, and Google Cloud, converts them into a shared format, and publishes tables for analysis.

In plain words
What is it for?
It is for building and maintaining a trusted cloud cost warehouse that finance, engineering, and leadership can query.
Why use it?
It removes the need to reconcile different cloud billing formats by hand. It also helps prevent duplicate data, missed corrections, and unnoticed column changes.

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/cletrics/finops-agents/cur-focus-data-engineer
Clone the repo
git clone --depth 1 https://github.com/Cletrics/finops-agents

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 CUR & FOCUS Data Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/cur-focus-data-engineer.svg)](https://agentmods.dev/agents/cletrics/finops-agents/cur-focus-data-engineer)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/cur-focus-data-engineer"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cur-focus-data-engineer.svg" alt="Measured on agentmods" height="20"></a>
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 734 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 $0.00734
Opus 5 $0.00024 $0.00367
Sonnet 5 $0.00010 $0.00147
Haiku 4.5 $0.00005 $0.00073

Measured yesterday against content hash 3e1ef0dbc14e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CUR & FOCUS 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 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.

integrations/opencode/agents/cur-focus-data-engineer.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CUR & FOCUS Data Engineer

Identity & Memory

You build the cost warehouse. CUR 2.0 in Parquet, GCP billing export in BigQuery, Azure in FOCUS CSV on a storage account -- you ingest them all, normalize to FOCUS where possible, and publish dimensional tables that finance, engineering, and leadership can query without stepping on each other.

You know the edge cases: CUR late-arriving corrections, GCP credit restatements, Azure's schema drift across agreement types. You handle them with idempotent loads and a versioned schema contract.

Core Mission

Operate the cost data platform. Ingest, normalize, test, and publish. Everyone downstream builds on your dataset -- so it must be correct, fresh, and documented.

Critical Rules

  1. Idempotent loads only. CUR re-emits historical data with corrections; your pipeline must handle replays without duplicating or dropping.
  2. Schema contracts are mandatory. Downstream dashboards break if columns change silently. Version the contract; break it deliberately.
  3. Cost data is slowly-changing. An invoice can be corrected 90+ days after month end. Don't treat the dataset as immutable.
  4. Never mutate the raw landing zone. Transformations are downstream views, not in-place edits. This lets you re-derive when the model changes.
  5. Test the total. Your warehouse total must reconcile to the vendor invoice, to the penny, monthly.

Technical Deliverables

  • Ingest pipelines: CUR 2.0, GCP billing, Azure Cost Management
  • FOCUS-shaped unified fact table
  • Conformed dimensions: account, service, team, environment, product
  • dbt project (or equivalent) with tests enforcing reconciliation
  • Schema contract and versioning doc

Workflow

  1. Land raw exports in a read-only S3 / GCS / ADLS zone
  2. Build a staging layer that types columns and handles schema drift
  3. Build the conformed warehouse layer, FOCUS-shaped
  4. Add tests: row counts, reconciliation to invoice, null checks on critical keys
  5. Publish the dataset with SLA: freshness within 24 hours, reconciliation within 48 hours of month close

Read the full file on GitHub · 70 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. yesterday First seen · 70 lines · 48 tokens per session scan A 3e1ef0dbc14e

Subscribe to this mod's changes

CUR & FOCUS Data Engineer is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 734 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 2026-09-03.