tldr-stats

📁 parcadei/continuous-claude-v3 📅 Jan 24, 2026

108

总安装量

周安装量

#4013

全站排名

安装命令

npx skills add https://github.com/parcadei/continuous-claude-v3 --skill tldr-stats

Agent 安装分布

claude-code 16

opencode 13

codex 11

gemini-cli 11

cursor 9

antigravity 8

Skill 文档

TLDR Stats Skill

Show a beautiful dashboard with token usage, actual API costs, TLDR savings, and hook activity.

When to Use

See how much TLDR is saving you in real $ terms
Check total session token usage and costs
Before/after comparisons of TLDR effectiveness
Debug whether TLDR/hooks are being used
See which model is being used

Instructions

IMPORTANT: Run the script AND display the output to the user.

Run the stats script:

python3 $CLAUDE_PROJECT_DIR/.claude/scripts/tldr_stats.py

Copy the full output into your response so the user sees the dashboard directly in the chat. Do not just run the command silently – the user wants to see the stats.

Sample Output

ââââââââââââââââââââââââââââââââââââââââââââââââââââââââââââââââ
â  ð Session Stats                                            â
ââââââââââââââââââââââââââââââââââââââââââââââââââââââââââââââââ

  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

    ð° TLDR saved you ~$18.83
    (Without TLDR: $115.35 â With TLDR: $96.52)

    File reads: 1.3M â 20.9K ââââââââââ 98% smaller

  TLDR Cache
    Re-reading the same file? TLDR remembers it.
    âââââââââââââââ 37% cache hits
    (35 reused / 60 parsed fresh)

  Hooks: 553 calls (â all ok)
  History: âââ ââââ avg 84% compression
  Daemon: 24m up â 3 sessions

Understanding the Numbers

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 â Y	Raw file tokens compressed to TLDR summary
Cache hits	How often TLDR reuses parsed file results
History sparkline	Compression % over recent sessions (â = high)

Visual Elements

Progress bars show savings and cache efficiency at a glance
Sparklines show historical trends (â = high savings, â = low)
Colors indicate status (green = good, yellow = moderate, red = concern)
Emojis distinguish model types (ð Opus, ðµ Sonnet, ð Haiku)

Notes

Token savings vary by file size (big files = more savings)
Cache hit rate starts low, increases as you re-read files
Cost estimates use: Opus $15/1M, Sonnet $3/1M, Haiku $0.25/1M
Stats update in real-time as you work

GitHub 仓库 ↗ ← 返回陌讯 Skills 聚合平台