ctx-stats

Display token consumption and context savings per tool for the current session.

3|1|Updated Aug 10, 2025

Search Tags:#context #monitoring #ai #usage #stats #token

Ready to run

npx skills add https://github.com/hckhanh/pulumi-any-terraform --skill ctx-stats-hckhanh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ctx-stats
Source: https://github.com/hckhanh/pulumi-any-terraform/tree/main/.agents/skills/ctx-stats
Command: npx skills add https://github.com/hckhanh/pulumi-any-terraform --skill ctx-stats-hckhanh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reveals how much of the prompt context you have saved by using context‑mode, showing token consumption, savings ratio, and per‑tool breakdowns so you can monitor and optimize usage.

Core Features & Use Cases

Token Consumption Display: Shows total tokens used in the current session.
Context Savings Ratio: Calculates how much data was kept in the sandbox versus sent to the model.
Per‑Tool Breakdown: Details savings for each tool that contributed to the session.
Read‑Only Insight: Provides statistics only; it does not modify or reset the knowledge base.
Typical Use: Ideal for developers and AI operators who want to audit the efficiency of context‑mode during a session.

Quick Start

Run the /context-mode:ctx-stats command to view the current session’s context savings.

Frequently Asked Questions about ctx-stats

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

FAQPage Schema

How do I view token consumption and context savings for my current AI session?▼

You can view token consumption and context savings by running the `/context-mode:ctx-stats` command during a context-mode session to display total tokens used and the overall savings ratio.

What is context savings ratio and how is it calculated?▼

Context savings ratio calculates how much data was kept in the sandbox versus sent to the model. It reveals the efficiency of your context-mode usage by comparing saved tokens against used tokens.

Can I see a per-tool breakdown of token usage during a session?▼

Yes, per-tool breakdowns detail the token savings for each tool that contributed to the session, allowing developers and AI operators to audit the efficiency of individual context-mode operations.

Does viewing context stats modify or reset the knowledge base?▼

No, viewing context stats is a read-only insight that retrieves statistics without modifying or resetting the knowledge base, ensuring your session data remains intact while monitoring token usage.

When do I need to monitor context savings during a session?▼

You need to monitor context savings when you want to audit the efficiency of context-mode during an active session, optimizing how much prompt data is sent to the model versus kept in the sandbox.