ww-w-ai

Cheaper and faster than /compact. Restores previous session context by reading transcripts directly — no LLM calls, no token cost

Know exactly what you spent. Interactive HTML dashboard with cost breakdown, token usage, and 5-hour window timeline across all sessions

Live token counter in your CLI. Shows real-time input/output/cache token counts in the Claude Code status bar

Max plan hit the wall? 💀 Report your 5h window data — we''re mapping the rate limit formula Anthropic won''t publish

Disable Claude Code built-in git instructions and inject a curated 280-tok minimum via SessionStart hook. Saves ~2,200 tok/session + ~1,700 tok/call.