receipts

Parse local receipt files to aggregate AI coding run costs and savings.

68|10|Updated Jul 2, 2026

Search Tags:#reporting #receipts #savings #cost-tracking #token-usage #ai-economics

Ready to run

npx skills add https://github.com/tomascupr/sous-chef --skill receipts-tomascupr

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: receipts
Source: https://github.com/tomascupr/sous-chef/tree/main/skills/receipts
Command: npx skills add https://github.com/tomascupr/sous-chef --skill receipts-tomascupr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the lack of visibility into AI-assisted development costs by providing a clear, per-run breakdown of token usage and financial savings compared to standard frontier model pricing.

Core Features & Use Cases

Cost Transparency: Automatically generates and maintains a ledger of run costs based on token usage and model-specific pricing.
Savings Analysis: Calculates and displays the cost difference between the current worker model and a baseline Fable-only implementation.
Use Case: Use this after a series of coding tasks to generate a summary table for your team, demonstrating the economic efficiency of your current agentic workflow.

Quick Start

Ask the assistant to print the last ten run receipts to see your recent worker spend and total savings.

Frequently Asked Questions about receipts

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

FAQPage Schema

How do I track AI coding costs and calculate token usage savings?▼

AI coding costs and token usage savings are tracked by parsing local receipt files and applying model-specific pricing benchmarks. This generates an expenditure report showing the cost difference between your current worker model and a premium model baseline.

What is the best way to monitor token usage spend for agentic development workflows?▼

Monitoring token usage spend for agentic workflows involves aggregating local run receipts into a financial ledger. It calculates per-run token costs and savings against standard frontier model pricing to provide clear cost transparency.

How do I generate a financial report of my AI coding run costs?▼

Generating a financial report of AI coding run costs requires parsing receipt files stored in the local .sous-chef/receipts directory. The Skill applies an internal price reference table to calculate token-based expenditure and savings.

Do I need a specific directory setup to aggregate AI token costs?▼

Yes, you need access to the local .sous-chef/receipts directory to aggregate AI token costs. This directory contains the run receipt files required to calculate accurate expenditure reports and savings analysis.

Can I compare my current AI model costs against a premium model baseline?▼

Yes, you can compare current AI model costs against a premium model baseline. The Skill calculates and displays the financial savings and cost difference between your active worker model and a Fable-only implementation baseline.

Why does my AI cost tracking report show zero savings?▼

AI cost tracking reports show zero savings when receipt files are missing or model-specific pricing benchmarks cannot be applied. Ensure the .sous-chef/receipts directory contains valid run data and the internal price reference table is accessible.