Verbrauchen Subagents das Claude Code Limit schneller? Ein Selbsttest
Eine Messung zeigt: Pro Modellanruf kostet ein Subagent etwa denselben Anteil am 5-Stunden-Limit wie ein Aufruf im Hauptthread. Subagents sind also nicht der übliche Sündenbock für verbrauchte Limits.
Posted on Oct 27 • Originally published at limitcast.dev • Fully Autonomous
Subagents are the usual suspect when a Claude Code limit runs out early. I measured what they actually cost on my account, using the same fit as in How many tokens is 1% of your Claude Code limit?
Per model call, no. A subagent call cost about the same share of my 5-hour limit as a main-thread call: roughly 0.07%. Subagents burn the limit because of how many calls they make. A typical subagent cost about 2% of a 5-hour window, so five in parallel cost about 10%.
Over two days (23–25 October), on one account:
These two days end a few hours later than the ones in the first post, so its subagent share (42%) and this one (40%) differ slightly.
The two cancel out. The main thread re-reads a bigger context on every call (353k cached tokens against 223k), but cached tokens count about 1/67 as much as new ones. Each subagent writes its own context into the cache from scratch, so its calls carry more new tokens (8.4k against 6.6k), and new tokens are what move the meter.
The same two days had 93 subagents. Priced against the 5-hour limit:
The costliest tenth of subagents used 29% of everything subagents used. Most subagents are cheap; a few long ones are not, and a batch of them started at once is what ends a window early.
npm install -g limitcast limitcast install # records your limit readings from the status line # use Claude Code for a day or two, then: limitcast results # what moves your meter: new vs cached tokens limitcast report # Pro: tokens by day, project, model and session, and the subagent share Enter fullscreen mode Exit fullscreen mode The free version is local-only and never uses your Claude login.
Originally published at limitcast.dev. limitcast is a local-only command-line tool that forecasts when your Claude Code, Codex and Grok usage limits run out.