---
id: "action-measure-context"
type: "action-item"
source_timestamps: ["00:17:10", "00:24:06"]
tags: ["analytics", "diagnostics"]
related: ["framework-kiss-commands", "entity-claude-code", "concept-silent-tax"]
speakers: ["Nate B. Jones"]
action: "Instrument and track input/output token usage per session."
outcome: "Provides visibility into inefficiencies and cost drivers."
sources: ["s45-claude-limit-chatgpt-habit"]
sourceVaultSlug: "s45-claude-limit-chatgpt-habit"
originDay: 45
---
# Measure Token Burn Per Session

## Action
Instrument your workflows to track exactly **how many input and output tokens** are being consumed per call. Use tools like [[entity-claude-code-d45]]'s `/context` command to audit what is loaded in the background before hitting send.

## Outcome
- Surfaces invisible costs (the [[concept-silent-tax]])
- Reveals which sessions are sprawling ([[concept-context-sprawl]])
- Enables ROI tracking against [[concept-smart-tokens]] vs. wasteful tokens

## How
- **Chat tier**: use built-in token counters (Claude Code `/context`, OpenAI dashboard usage panes)
- **API tier**: log `usage` fields from every response; compute cost-per-call ratios
- **Agent tier**: instrument every sub-agent invocation independently

## Why
The 5th of [[framework-kiss-commands]] — *Measure Token Burn*. Checkpoint #4 of [[framework-stupid-button-audit]]. You cannot manage what you cannot see.