> I cannot see the agent burning through $50 for one moderately sized TypeScript cleanup in my setup.

Here's my usage, from the ccusage tool (slightly shortened for readability):

  ┌──────────┬───────────────┬────────────┬─────────────┬─────────────┬───────────────┬────────────────┬────────────────┬─────────────┐
  │ Month    │ Agent         │ Models     │       Input │      Output │  Cache Create │     Cache Read │   Total Tokens │  Cost (USD) │
  ├──────────┼───────────────┼────────────┼─────────────┼─────────────┼───────────────┼────────────────┼────────────────┼─────────────┤
  │ 2026-06  │ - Claude      │ - opus-4-8 │  13,635,792 │  32,562,574 │   177,985,265 │  5,265,814,971 │  5,489,998,602 │    $4665.09 │
  └──────────┴───────────────┴────────────┴─────────────┴─────────────┴───────────────┴────────────────┴────────────────┴─────────────┘

Now obviously that is all with the Max 5x subscription, other agents and models excluded.

So per day that'd be around 155 USD (including weekends), which doesn't seem that far off, as long as the example cleanup takes up around 1/3 of one's daily work (or needs a lot of review/test iterations, or needs to review a lot of the existing code etc.).

▲ user43928 10 hours ago | parent [-]

Interestingly it seems 80% of the cost is in the cached tokens.

I do not know whether that is typical, or indicative of conversations with too many turns.

Not that I would worry about this on a subscription plan, but at work where we are billed at API rates, I try to move to new conversations as often as possible.

	▲	KronisLV 9 hours ago \| parent [-]
		For agentic development upwards of 90% is pretty normal! For example, if you make Claude Code explore a codebase, write a plan based on it and your requirements, do a few iterations of further specifying and altering it, and afterwards let it work for let's say 2-4 hours. Sub-agents and dynamic workflows do alter the numbers a bit, but not to a crazy degree in the long run.