Topic · 14 entries · updated 2026-10-09

FinOps

What the platform costs and how it is metered. The cost model, unit economics, showback, budgets and alerts, an anomaly case and a FOCUS export.

2 Inside pages, 9 docs pages, 3 tickets

Inside 2

Agent sessions
The Claude Code sessions that build and run this platform, each owning one track of work and pushing through the gate. Spend and tokens are summed from per-request events; a spend alert fires above USD 40 in the trailing hour.
updated 2026-10-09
Local LLM
The self-hosted model server on the home server, metered by a pass-through proxy (the ollama-exporter) for time to first token, decode speed, token counts and resident models. The only service with defined SLOs and burn-rate alerts.
updated 2026-10-09

FinOpsThe cost side of the platform in the FinOps Foundation's terms (phases, principles, personas, domains, FOCUS) and how each applies to a one-person platform built with Claude Code.
Budgets and alertsThe cost controls that exist (the Claude Code spend alert, the AWS monthly budget with its internal dashboard and four alert rules, the eval harness caps), why only the AWS Budgets e-mail reaches a person, and what a budget alert for Claude Code would look like.
Cost modelEvery cost component of the platform with its billing model, its meter and the amount where a source exists; components without a meter say so.
FOCUS exportA FOCUS 1.4-shaped CSV of the platform's metered costs for 2026-10-01 to 2026-10-08, the script that writes it, the column mapping and the declared deviations from the specification.
ShowbackThe list-price value of the platform's usage, as Claude Code and the eval harness price it, set against what is billed, and the reasons the two differ.
The phantom two millionA FinOps anomaly case from 2026-10-09: parallel Claude Code sessions wrote into one counter series, and Prometheus reported USD 1.97M for a week that cost USD 1,003 at list price.
Unit economicsCost per unit of output with real numbers: Claude Code spend per day, per model, per API call, per million tokens and per commit; runner time per deploy; cost per eval run.

Cost per unit of workCost is an operational signal read per unit of output, metered like latency and alerted like errors. Here a FinOps space meters each component, prices spend per call, commit and deploy, and sets alert thresholds from data; only the AWS budget e-mail reaches a person.
Unit Economics of InfrastructureTotal cloud spend is the wrong metric.

Issues on the board, open first, as of the last build.