skills.rest
mifunedev
mifunedevOFFICIAL
Explore all skills by this author →
Website𝕏@mifunedevGitHub

caveman-stats

Estimate token savings by comparing baseline prose to compressed forms.

28|3|Updated Mar 27, 2026
Search Tags:#heuristics#compression#baseline#session#token-count#savings-estimate
One-click install
npx skills add https://github.com/mifunedev/openharness --skill caveman-stats-mifunedev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-stats
Source: https://github.com/mifunedev/openharness/tree/main/.claude/skills/caveman-stats
Command: npx skills add https://github.com/mifunedev/openharness --skill caveman-stats-mifunedev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prose-heavy prompts and responses often consume more tokens than necessary. This skill provides a quick, heuristic estimate of token savings by comparing a normal-prose baseline to its compressed form, helping you optimize prompts and content.

Core Features & Use Cases

  • Inline: given a normal-prose sample, produce its compressed token estimate and report both counts plus the savings.
  • --session: estimate savings across caveman-active responses in the current session and summarize results.
  • Method: uses a simple heuristic where tokens ≈ ceil(chars / 4); clearly indicate when estimates are approximate.

Quick Start

Provide a normal-prose sample to get an estimated token savings report.

Frequently Asked Questions about caveman-stats

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I estimate token savings from compressing prose prompts?▼

To estimate token savings, provide a normal-prose sample and the skill compares baseline character counts to compressed text, reporting token estimates and percentage savings.

Can I calculate token savings across an entire chat session?▼

Yes, use the session mode to estimate savings across caveman-active responses in the current session, summarizing baseline versus compressed token counts for all relevant content.

How does the heuristic token count estimation actually work?▼

The heuristic calculates tokens by dividing character count by four and rounding up, providing an approximate estimate that is clearly flagged when results are not exact counts.

What is the best way to measure baseline versus compressed token usage?▼

The best way to measure baseline versus compressed token usage is to input normal prose and let the heuristic compare original character estimates against compressed output savings.

Are the token savings estimates exact or approximate?▼

The token savings estimates are approximate because they rely on a simple heuristic dividing characters by four, and the output explicitly notes when reported counts are approximate.

Related Skills

Explore More Data & Analytics Skills→
guhans6guhans6

caveman

Transform AI model responses into caveman-style prose with reduced token usage.

Community
Advanced
Manvendra08Manvendra08
1

token-efficiency

Reduce token consumption and context overflow in LLM interactions.

Community
Basic
MayaDispelerMayaDispeler
3

token-optimization

Optimize Claude prompts with token counting, compression, and cost estimation techniques.

Community
Advanced
korchasakorchasa

analyze-context

Estimate token usage and session cost from conversation history and system prompts.

Community
Basic