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 agents/cletrics/finops-agents/cur-focus-data-engineergit clone --depth 1 https://github.com/Cletrics/finops-agentsWrote 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/agents/cletrics/finops-agents/cur-focus-data-engineer)<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>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 | $0.00048 | $0.00734 |
| Opus 5 | $0.00024 | $0.00367 |
| Sonnet 5 | $0.00010 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
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.
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
- Idempotent loads only. CUR re-emits historical data with corrections; your pipeline must handle replays without duplicating or dropping.
- Schema contracts are mandatory. Downstream dashboards break if columns change silently. Version the contract; break it deliberately.
- Cost data is slowly-changing. An invoice can be corrected 90+ days after month end. Don't treat the dataset as immutable.
- Never mutate the raw landing zone. Transformations are downstream views, not in-place edits. This lets you re-derive when the model changes.
- 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
- Land raw exports in a read-only S3 / GCS / ADLS zone
- Build a staging layer that types columns and handles schema drift
- Build the conformed warehouse layer, FOCUS-shaped
- Add tests: row counts, reconciliation to invoice, null checks on critical keys
- Publish the dataset with SLA: freshness within 24 hours, reconciliation within 48 hours of month close
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.
- yesterday First seen · 70 lines · 48 tokens per session scan A 3e1ef0dbc14e
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.
Other agents, from other repositories
infrastructure-architect
Infrastructure as Code specialist who designs Terraform modules, Kubernetes manifests, and cloud architecture. Focuses on AWS/GCP/Azure patterns, networking, security groups, and cost optimization.
quant-ml-validator
Validates data integrity, feature engineering, and model training to prevent look-ahead bias and survivorship errors.
FAI Capacity Planner
AI capacity planning specialist — GPU sizing, PTU allocation, token volume forecasting, cost modeling, scaling strategy, and FinOps for Azure AI workloads.
FAI Cost Optimizer
FinOps cost optimizer for AI workloads — model routing economics, semantic caching ROI, token budget design, PTU vs PAYG analysis, right-sizing recommendations, and Azure cost attribution.
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.
FAI Cost Optimizer
FinOps cost optimizer for AI workloads — model routing economics, semantic caching ROI, token budget design, PTU vs PAYG analysis, right-sizing recommendations, and Azure cost attribution.