cost-tracking

Capture AI provider spend and token usage into structured Markdown cost snapshots.

44|6|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/Habitat-Thinking/ai-literacy-superpowers --skill cost-tracking-habitat-thinking
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cost-tracking
Source: https://github.com/Habitat-Thinking/ai-literacy-superpowers/tree/main/ai-literacy-superpowers/skills/cost-tracking
Command: npx skills add https://github.com/Habitat-Thinking/ai-literacy-superpowers --skill cost-tracking-habitat-thinking

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Lack of structured cost data prevents accurate model routing, inhibits break-even analysis for self-hosting, and leaves budget conversations ungrounded in evidence. This Skill standardizes how teams capture and record AI provider spend so routing decisions and health snapshots reflect real world costs.

Core Features & Use Cases

  • Structured Cost Snapshots: Guides creation of observability/costs/YYYY-MM-DD-costs.md files that record provider spend, token volumes, model breakdowns, per-project estimates, observations, and budget status.
  • Dashboard Guidance: Points users to provider billing pages (Anthropic, OpenAI, etc.) and prompts the fields needed when dashboards lack model-level granularity.
  • Trend Comparison & Routing Impact: Compares new snapshots to prior captures to compute spend deltas and token trends, and surfaces recommendations for updating MODEL_ROUTING.md and health snapshots.
  • Use Case: Quarterly finance/engineering reviews where teams need evidence-backed routing adjustments or to evaluate the ROI of cloud vs self-hosting.

Quick Start

Gather billing figures from your provider dashboards and record them into observability/costs/YYYY-MM-DD-costs.md using the Cost Snapshot format, then commit the snapshot and any suggested MODEL_ROUTING.md updates.

Frequently Asked Questions about cost-tracking

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

FAQPage Schema
How do I track AI provider spend and token usage for cost analysis?

To track AI provider spend, manually extract billing figures and token volumes from provider dashboards, then record them into structured Markdown files under observability/costs/ to compute spend deltas and inform routing decisions.

What is the best way to enforce cost budgets for cloud model routing?

Enforcing cost budgets involves capturing provider spend snapshots in Markdown, comparing new captures against prior historical data to compute deltas, and updating MODEL_ROUTING.md to reflect evidence-backed routing adjustments.

How do I record cloud costs when provider dashboards lack model-level granularity?

When provider dashboards lack model-level granularity, record cloud costs by prompting for the specific fields needed and estimating per-project costs within the observability/costs/YYYY-MM-DD-costs.md snapshot format.

Can I use Markdown snapshots for quarterly finance and engineering cost reviews?

Yes, you can use Markdown snapshots for quarterly finance reviews by comparing historical cost captures to evaluate cloud vs self-hosting ROI and make evidence-backed model routing adjustments.

Do I need manual data extraction to update AI billing health snapshots?

Yes, manual data extraction from AI provider billing pages is required to populate the structured cost snapshots that subsequently inform and update health snapshots and routing configurations.

Why does structured cost data matter for break-even analysis on self-hosting?

Structured cost data matters for break-even analysis because standardizing how teams capture AI provider spend ensures routing decisions and health snapshots reflect real world costs, grounding budget conversations in evidence.