Smithery is now a part of Arcade.dev! Read more in our announcement here
Show full session token usage, costs, TLDR savings, and hook activity
Show a beautiful dashboard with token usage, actual API costs, TLDR savings, and hook activity.
IMPORTANT: Run the script AND display the output to the user.
python3 $CLAUDE_PROJECT_DIR/.claude/scripts/tldr_stats.py
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā š Session Stats ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
You've spent $96.52 this session
Tokens Used
1.2M sent to Claude
416.3K received back
97.8K from prompt cache (8% reused)
TLDR Savings
You sent: 1.2M
Without TLDR: 2.5M
š° TLDR saved you ~$18.83
(Without TLDR: $115.35 ā With TLDR: $96.52)
File reads: 1.3M ā 20.9K āāāāāāāāāā 98% smaller
TLDR Cache
Re-reading the same file? TLDR remembers it.
āāāāāāāāāāāāāāā 37% cache hits
(35 reused / 60 parsed fresh)
Hooks: 553 calls (ā all ok)
History: āāā āāāā avg 84% compression
Daemon: 24m up ā 3 sessions
| Metric | What it means |
|---|---|
| You've spent | Actual $ spent on Claude API this session |
| You sent / Without TLDR | Actual tokens vs what it would have been |
| TLDR saved you | Money saved by compressing file reads |
| File reads X ā Y | Raw file tokens compressed to TLDR summary |
| Cache hits | How often TLDR reuses parsed file results |
| History sparkline | Compression % over recent sessions (ā = high) |
