5 hacks
Inspect `/usage` (alias `/cost`) for per-skill, subagent, and MCP breakdowns, then cut the expensive outliers.
Schedule an early Claude Code run so your usage window resets around lunch instead of mid-afternoon.
Claude Code re-reads your whole conversation at the cached rate. Come back after a long lunch and the first message reprocesses all of it at full price.
Use the bundled /doctor skill to find duplicate local memory, unused MCP/plugins, and slow hooks eating budget.
Add a top-level cache_control ephemeral flag so growing conversation prefixes reuse cached tokens and cut API cost and latency.