How do I use TLDR stats?

Run the Python script and paste the full output so the dashboard renders for you and the user.

What metrics are shown?

Token usage (sent/received), actual costs, TLDR savings, file reads, cache hits, history sparkline, and hook activity.

Do costs reflect different models?

Yes. Cost estimates use Opus, Sonnet, and Haiku rates (per 1M tokens) to show real-world spending.

tldr-stats

npx machina-cli add skill parcadei/Continuous-Claude-v3/tldr-stats --openclaw

Files (1)

SKILL.md

2.9 KB

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

╔══════════════════════════════════════════════════════════════╗
║  📊 Session Stats                                            ║
╚══════════════════════════════════════════════════════════════╝

  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

    💰 TLDR saved you ~$18.83
    (Without TLDR: $115.35 → With TLDR: $96.52)

    File reads: 1.3M → 20.9K █████████░ 98% smaller

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

  Hooks: 553 calls (✓ all ok)
  History: █▃▄ ▇▃▇▆ avg 84% compression
  Daemon: 24m up │ 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 → Y	Raw file tokens compressed to TLDR summary
Cache hits	How often TLDR reuses parsed file results
History sparkline	Compression % over recent sessions (█ = high)

Visual Elements

Progress bars show savings and cache efficiency at a glance
Sparklines show historical trends (█ = high savings, ▁ = low)
Colors indicate status (green = good, yellow = moderate, red = concern)
Emojis distinguish model types (🎭 Opus, 🎵 Sonnet, 🍃 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

Source

git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/tldr-stats/SKILL.mdView on GitHub

Overview

TLDR Stats builds a beautiful dashboard showing session token usage, actual API costs, TLDR savings, and hook activity. It helps quantify the impact of TLDR, compare before/after scenarios, and debug whether TLDR and hooks are actively used.

How This Skill Works

A stats script runs to collect token counts, costs by model, cache hits, and hook calls, then renders a dashboard-style output. You run the script and paste the full output so the user can see the live stats directly in chat.

When to Use It

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

Quick Start

Step 1: Run the stats script: python3 $CLAUDE_PROJECT_DIR/.claude/scripts/tldr_stats.py
Step 2: Copy the full output into your response so the dashboard appears in chat
Step 3: Review tokens, costs, TLDR savings, and hook activity at a glance

Best Practices

Always run the stats script and paste the full output so the dashboard renders in chat
Note the model costs (Opus, Sonnet, Haiku) and how they affect totals
Use cache hits and history sparklines to gauge TLDR effectiveness over time
Compare before/after sessions to measure savings and usage changes
Watch for hook activity and ensure TLDR is being invoked when expected

Example Use Cases

A developer evaluates TLDR impact by comparing two sessions with and without TLDR enabled
A product team tracks TLDR savings across a feature kickoff to quantify cost reductions
A maintainer debugs low hook usage by inspecting the TLDR stats dashboard
An engineer confirms which model was used in a given session via the stats view
An ops role monitors real-time token costs to optimize model selections

Frequently Asked Questions

Add this skill to your agents