From codebase-pilot
Checks token counts per file and plans context budget. Shows which files consume the most tokens and how to optimize context window usage.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codebase-pilot:token-budgetThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze token distribution across your codebase and plan context usage.
Analyze token distribution across your codebase and plan context usage.
codebase-pilot tokens
codebase-pilot tokens --agent <name>
codebase-pilot pack --compress --dry-run
codebase-pilot stats
codebase-pilot stats --global
--agent scope — see which agent contexts are leanest--compress — see the potential savingsstats shows daily/weekly/monthlySavings estimate (per session):
Without codebase-pilot: ~98,798 tokens
With pack --compress: ~29,274 tokens
Pilot saves: ~69,524 tokens per session
Your savings (from pack runs):
Today: 3 sessions — ~92,232 tokens saved
This week: 5 sessions — ~147,498 tokens saved
http://localhost:7456 shows live token statshttp://localhost:7456/files shows per-file token breakdownhttp://localhost:7456/prompts shows all session historynpx claudepluginhub kalpeshgamit/codebase-pilot --plugin codebase-pilotTracks tokens, analyzes caching behavior, identifies bottlenecks in tool usage, and estimates costs to optimize Claude Code session performance and efficiency.
Displays token economics dashboard showing savings from search-first (turbo-search) vs blind file reading. Analyzes session activity logs and codebase stats via /token-stats.
Applies token optimization rules to reduce context usage and response length. Always active, it minimizes file reads, avoids preamble, and batches tool calls.