README

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents


  Aaron J. Li1,
  Weijia Xu2,
  Chandan Singh2,
  Zixiao Chen3,
  Jeevana Priya Inala2,
  Charlotte Siska3,
  
  Acar Tamersoy3,
  Bin Yu1,
  Ion Stoica1,
  Michel Galley2,
  Jianfeng Gao2


  1UC Berkeley   2Microsoft Research   3Microsoft Security



  
  
  
  
  



  
  



  Our measurement on SWE-Bench tasks: 18.4–30.9% lower mean cost across five agent–model
  combinations, cheaper in all 30 repository × combination cells, and Pass@1 up in
  4 of 5. Results



  
    
    
  


TokenEconomizer makes coding agents cheaper to run in the repositories you work in often,
without changing the agent itself. It learns from the sessions an agent has already run in a
repository, and uses that experience to cut waste in the sessions that follow. It has three
mechanisms:

- Micro-skills: remember how the repository works. Sessions keep rediscovering the same
  facts: a build step that must run first, the spelling of a command that works here
  (python -m pytest where pytest is missing, npx tsc where tsc is), an environment
  variable a command needs, where generated files live. Micro-skills learns such facts, in any
  language, from two sources: failures that repeat across sessions, and a model that reviews the
  recent sessions every k sessions (k = 3) and proposes facts. A fact is stated at the start
  of each session once three sessions have confirmed it, and dropped when later sessions
  contradict it.
- Tool pruning: stop loading tools that go unused. Every loaded tool's definition is sent with
  every request. A tool that goes unused over p prompts spread across at least m sessions, or
  over s sessions of any length (p = 10, m = 2, s = 5), is left out of the next sessions
  through the agent's own settings. One command brings it back.
- Failure-loop intervention (the loop guard): step in when a turn is stuck. When a turn (the
  agent's work on one prompt) keeps hitting the same failures, a judge model checks whether it is
  stuck. If the judge is at least c sure (c = 0.7), the agent gets a redirect (a short note,
  added to its context, to try another approach), at most r times per turn (r = 1). If the
  turn is still stuck after that, TokenEconomizer tells you how to stop it; it never stops a turn
  itself.

TokenEconomizer is a plugin for Claude Code, Codex, the GitHub Copilot CLI and Pi,
with experimental support for opencode, Cursor Agent, Grok Build, Hermes Agent and
the Antigravity CLI. Each italic
letter above is a setting, shown with its default (Settings), and each mechanism can be turned on or
off. The plugin announces each action in one line, and if any part of it fails, your session
carries on as if it were not installed. Its model calls (the fact proposer, and the judge with the
redirect it writes) run through your own agent, on the same plan or login, and their cost is
included in its reports. What it learns stays on your machine, in ~/.tokene

Top issues

Latest release

First release of TokenEconomizer, the plugin from TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents (arXiv 2610.22732).

It makes Claude Code, Codex, the GitHub Copilot CLI and Pi cheaper to run in the repositories you work in often, without changing the agent. It learns from each finished session in a repository and changes what the next sessions there start with.

In the paper's SWE-Bench runs: 18.4–30.9% lower mean cost across five agent–model combinations, cheaper in all 30 repository × combination cells, and Pass@1 up in 4 of 5.

 Mechanisms

- Micro-skil