Measure token usage and savings via ccusage — establish a baseline and compare before/after. Use right after init (to record the baseline) and again after about a week to quantify the input-token reduction against the ≥40% target. Wraps `agent-stack measure`, which reads ccusage's local JSONL — never vendor self-reported numbers.
Scanned 8/30/2026
Install to Claude Code
npx -y skills add drmahdikazempour/agent-stack --skill stack-measure --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Stack Measure?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/drmahdikazempour-stack-measure)More formats (shields.io, HTML) on the badges page.
---
name: stack-measure
description: Measure token usage and savings via ccusage — establish a baseline and compare before/after. Use right after init (to record the baseline) and again after about a week to quantify the input-token reduction against the ≥40% target. Wraps `agent-stack measure`, which reads ccusage's local JSONL — never vendor self-reported numbers.
---
# stack-measure
Quantify token usage with the neutral `ccusage` tool. Savings are always measured, never claimed.
## What to do
- **Baseline:** `npx @drmahdikazempour/agent-stack measure` (init already stored one in `.agent-stack/baseline.json`).
- **Compare:** `npx @drmahdikazempour/agent-stack measure --since 7d` — reports baseline vs recent average input tokens/day and the % reduction, color-coded against the ≥40% target.
## Notes
- If `ccusage` isn't installed, the command falls back to the local `usage.jsonl` our `Stop` hook appends; install `ccusage` (`npm i -g ccusage`) for authoritative numbers.
- Telemetry-free and local-only: it reads ccusage's JSONL on the user's machine.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.