AIToday
AI Coding AssistantsMicrosoft ResearchPublished: Nov 17, 2026, 04:00 JST

TokenEconomizer cuts AI coding agent costs 18.4–30.9%

Send on LINE
TokenEconomizer cuts AI coding agent costs 18.4–30.9%

3 Key Points

  1. What happened

    TokenEconomizer, an open-source plugin from UC Berkeley, Microsoft Research and Microsoft Security, lowered average cost per task by 18.4–30.9% across 277 SWE-Bench tasks and five agent–model combinations, saving the most in all 30 repository-combination pairs.

  2. Why it matters

    That range comes with task success rates described as broadly stable, so the savings do not appear to come at the expense of getting the bug fixes done — though the body notes early tasks can cost more while the plugin learns.

WHO IT HITSDevelopers and engineering teams running AI coding agents like Claude Code on recurring repositories stand to cut model-spend per task, with savings compounding as session history accumulates.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The plugin's design is a response to how AI coding agents actually spend tokens: repeatedly rediscovering the same repository facts, loading tool descriptions they never call, and burning turns on the same failure. Profiling Claude Code on 60 SWE-Bench tasks, the researchers found 30% of tool calls repeated an earlier action once a repository had at least five completed tasks, 16 of 23 tool descriptions were never called, and the 17% of tasks that failed accounted for 32% of spending.

Their conclusion was that a fixed cost-saving strategy does not travel well: three popular open-source plugins each lowered costs in some repositories but not others. TokenEconomizer instead adapts per repository, updating its knowledge after every session. Savings grew as experience accumulated, and the approach carried over to sequential web development (16.0–21.2% lower on Web-Bench) and to security auditing, where every task is in a new repository, at 6.4–19.6% lower.

The body also offers a comparison point for how the savings were achieved. Lowering the model's reasoning effort saved similar or larger amounts but led to substantial performance degradation, whereas TokenEconomizer reports no performance loss — which is likely why the team frames it as a way to make agents spend computation more effectively rather than simply spend less.

FAQ
How does TokenEconomizer reduce costs without changing the agent?
It uses only interfaces the agent already provides, via three mechanisms: micro-skills (one-line notes on repository-specific knowledge), tool pruning (removing tools unlikely to be used), and failure-loop intervention (a judge model that nudges a stuck agent).
Does it need access to my code or an API key?
The body says the plugin requires no API key of its own and keeps what it learns on the developer's machine.
How quickly do the savings show up?
Early tasks can cost more while TokenEconomizer learns, but cumulative costs fell below the default in every repository by the sixth task.
Microsoft ResearchRead Original Article
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleStripe completes OpenRouter acquisition to tie AI costs to revenue