skills.rest
jrc1883
jrc1883COMMUNITY
Explore all skills by this author →
GitHub

pop-routine-measure

Capture and visualize PopKit routine execution metrics with --measure.

Updated Aug 27, 2026
Search Tags:#metrics#dashboard#measurement#token-usage#cost-estimate#popkit
One-click install
npx skills add https://github.com/jrc1883/popkit-ai --skill pop-routine-measure
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pop-routine-measure
Source: https://github.com/jrc1883/popkit-ai/tree/main/packages/popkit-dev/skills/pop-routine-measure
Command: npx skills add https://github.com/jrc1883/popkit-ai --skill pop-routine-measure

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Routine measurement dashboard solves the challenge of seeing how PopKit routines perform in real time by aggregating duration, tool calls, tokens, and cost estimates into an accessible dashboard.

Core Features & Use Cases

  • Auto-measurement: Automatically captures metrics when users run routines with the --measure flag and stores data for historical analysis.
  • Dashboard Visualization: Displays a detailed dashboard of duration, token usage, per-tool breakdown, and cost estimates.
  • Historical Trends: Enables viewing trends across multiple runs and comparing latest results with previous data for optimization.

Quick Start

Activate routine measurement during a run: enable measurement on a /popkit:routine command with --measure to generate and view the dashboard after completion.

Frequently Asked Questions about pop-routine-measure

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

FAQPage Schema
How do I measure routine execution metrics like token usage and duration?▼

You can measure routine execution metrics by enabling the --measure flag on a PopKit routine command, which automatically captures duration, tool calls, tokens, and cost estimates for dashboard visualization and historical analysis.

What is the best way to visualize token usage and cost estimates for routine runs?▼

Visualizing token usage and cost estimates requires the routine measurement dashboard, which aggregates per-tool breakdowns and execution duration into an accessible view after running routines with the --measure flag.

Can I view historical trends and compare previous routine performance data?▼

Yes, you can view historical trends and compare previous routine performance data because the measurement feature persists captured metrics across multiple runs, enabling optimization through historical comparisons.

Does the routine measurement dashboard require any dependencies to display metrics?▼

No, the routine measurement dashboard operates without external dependencies, using a standard internal data model to store fields for duration, tokens, tool_breakdown, and cost_estimate.

When do I need to use the --measure flag for PopKit routines?▼

You need to use the --measure flag for PopKit morning and nightly routines when you want to activate automated measurement, capture execution metrics, and generate the performance dashboard upon completion.

What specific metrics are captured in the routine measurement data model?▼

The routine measurement data model captures specific metrics including execution duration, total token usage, detailed tool_breakdown, and cost_estimate to provide comprehensive performance insights.

Related Skills

Explore More Data & Analytics Skills→
wecode-aiwecode-ai
705

sandbox

Run shell commands and manipulate files inside an isolated E2B sandbox.

Official
Advanced
razorpayrazorpay
31

trino-query-cost-analyzer

Analyze Trino query plans and historical data to predict CPU time, memory usage, and data scanned.

Official
Advanced
psd401psd401
2

meta-health

Aggregate telemetry and workflow data to generate Markdown health dashboards.

Official
Advanced
iagocavalcanteiagocavalcante
15

token-stats

Quantifies token usage and savings from search-first codebase exploration via activity logs.

Community
Intermediate