Does routing coding agent subtasks to cheaper models pay off? A benchmark of 63 runs per arm

I wanted a straight answer to one question: if a coding agent hands its cheap subtasks to a smaller model, how much does a session really cost less, and does the result get worse?

Token Beggar is a plugin that adds a routing card to the session. The chat model grades each task into one of 7 classes and delegates bulk work (large reads, repeated edits, test loops) to a worker with its own context, at a cheaper model and lower effort. Design and root-cause work stays with the chat model. The chat model and effort are a ceiling, so nothing is routed above what you chose.

Quality was 0.96 in both arms.

Design, bug root cause and review never go to a worker, yet they came out 1.07x to 1.14x cheaper. That is run to run spread plus, I suspect, a shorter path the card gives the chat model. So I only quote multipliers of 1.15x or more in the plugin's footer. The routes were tuned on the same 21 tasks, so the table describes this setup and is not a forecast for yours.

One debugging task looked like a regression in 5 of 6 runs with the plugin. The diffs were identical to the passing runs. The cause was a stale .pyc: the fix changed == to !=, which keeps the file size, and the bytecode written by the pre-fix test run still passed Python's mtime check. The scorer now clears bytecode before checking, and both arms were rescored. If you score code produced by agents, clear pycache first.

A compaction guard that writes a handoff note before an automatic compaction and defers it up to 3 times when files were edited after the last test run. The weekly model list refresh is a GitHub Action.

Repo, raw runs and the scorer: https://github.com/Arthur031221/Token-Beggar (MIT).