centrailYancy Collective LLC
Sign inStart free
How it works / How we parse usage

How we parse usage

What the CLI reads from your agent logs — and what it ignores.

Centrail's CLI reads the usage logs your coding agent already writes — today, Claude Code (~/.claude/projects), GitHub Copilot CLI (~/.copilot/session-state), and Codex (~/.codex/sessions).

What a usage event is

Each event is one model request. From it we read:

FieldExample
Modelclaude-opus-4-8
Tokensinput, output, cache read, cache write
Timestampwhen the request happened
Working dirwhich repo it ran in

What we never read

Your source code. Your prompts. Your completions. The parser only extracts the counts and metadata above — never content.

One model, one maker. A model is always counted toward the company that built it — gpt-5.3-codex counts as OpenAI even when you reach it through Copilot. Copilot is multi-provider, so the same connector also brings Claude and Gemini usage, each attributed to its maker. A standalone Gemini connector is coming.