Claude Code: Fixer Systemprompt und Tool-Definitionen treiben die Kosten vor dem ersten Tastenschlag
Jede Claude-Code-Anfrage beginnt mit einem festen Block aus Systemprompt und Definitionen aller eingebauten Tools, für den man zahlt, bevor eigene Eingaben zählen. Eine Analyse über 58 Versionen zeigt, warum kurze Sitzungen und Subagents die Limits dadurch schneller aufbrauchen als erwartet.
Every Claude Code request starts with the same fixed block: the system prompt and the definitions of every built-in tool. You pay for it before your own words are counted, and it is a big reason why short sessions and subagents burn through limits faster than you'd expect. I wanted to know how that block has changed over time, so I installed old versions and measured it.
Every run of the same version gave exactly the same number, so these are not noisy averages.
Apps you connect on claude.ai also show up in Claude Code. In versions 2.1.83 to 2.1.140 (late March to mid May 2026), all of their tools were sent with every request. With my 13 connected apps, that was 420 to 426 extra tools and about 395,000 tokens for the prompt "a". Since 2.1.145 they are loaded only when needed, and in every version I measured this month the number is the same with connectors on or off.