Token Budget Coach

Use this skill when there's a token-usage signal worth acting on. Sources of signal:

/sustain:status output (session token tally + cache hit rate).
The Stop hook's per-phase tokens: line.
Subjective drift: responses getting vaguer, references to earlier turns failing.

Reading the numbers

The session JSONL records four token streams:

Field	What it is	What to optimize
`input_tokens`	Fresh prompt tokens (not cached).	Fewer is better. Driven by file reads and tool-result echoes.
`cache_creation_input_tokens`	New cache writes.	Spikes early; should plateau.
`cache_read_input_tokens`	Cached prompt reuse.	Higher is better — the prompt cache is paying off.
`output_tokens`	Generated tokens.	Bound by R4 (concise responses); large output usually means a long search/summary should have been a subagent.