# inference-arbitrage

Audits a Claude Code plugin — its skill/agent definitions and its real usage
transcripts — to find steps that are being done by raw LLM inference but pass
every test of a deterministic script, and files the well-evidenced ones as
issues on the target plugin's own repo. Runs on demand; each run accumulates
into a snapshot history so cost and candidate status can be tracked over time.

The name echoes `builder-arbitrage`: route each unit of work to the cheapest
executor that can do it correctly — here, "script vs. model" instead of
"which build node."

Status: **scaffolding, pre-implementation.** See `design/` for the full
specification:

- [`design/spec.md`](design/spec.md) — why, scope, functional requirements
- [`design/plan.md`](design/plan.md) — architecture and file layout
- [`design/rubric.md`](design/rubric.md) — the script-vs-inference boundary rubric
- [`design/tasks.md`](design/tasks.md) — build order

Tracked as issues on this repo under the `v0.1.0` milestone.