95 Prozent des AI-Coding-Kontingents in zwei Tagen: Logs zeigen Ursachen
Ein Entwickler stellte fest, dass sein Claude-Code-Kontingent schon vor Mittwoch auf 95 Prozent verbraucht war, ohne dass besonders viel Code entstanden war. Eine Auswertung der lokal geloggten Requests offenbarte, wo die Masse von 65.000 Anfragen in drei Tagen herkam.
Posted on Oct 15 • Originally published at activi.dev
I use Claude Code every day to build a SaaS product. This week, the usage meter hit 95% before Wednesday. I assumed I had somehow written a mountain of code.
Every request is logged locally, so I added it up. Here's what three days of work looked like (October 12–15):
That means 99.9% of my tokens weren't code. They were the model re-reading what it already knew.
97.6% of all tokens were cache reads. Every turn, the agent resends the entire conversation so far: files read, tool results, earlier decisions.
When the context sits at 200k tokens, a one-line reply still costs 200k tokens of reading.
Two thirds of my volume came from requests with more than 200k tokens of context. Only 2.5% came from requests under 50k.
A long session doesn't cost more because it does more. It costs more because every new turn is more expensive than the last.
My workflow splits work into small tasks. For each task, one subagent implements and two review — one for spec conformance, one for code quality. It produces clean results.
It also produced 78% of my requests and 53% of my tokens.
Each subagent starts with a fresh but still large context, runs many tool calls, and each call re-reads that context. One task becomes dozens of requests.
Out of 46 sessions, five accounted for three quarters of the total volume. These were multi-hour runs where the context kept growing and I never started over. One of them averaged almost 400k tokens of context per request.
These are raw token counts. Cache reads are not billed or limited the same way as fresh tokens, so this explains the volume, not the exact percentage shown on the usage meter. The pattern is what matters.
If your AI coding quota disappears faster than your output suggests, look at your context size and your subagent fan-out before you blame the model.
Tokens aren't spent on the answer. They're spent on remembering the question.
How are you tracking your agent usage? Do you reset sessions deliberately, or only when something breaks?