Find which LLM calls a cheaper model could have handled

Built Frugon, a local MIT tool that finds which LLM calls a cheaper model could have handled.

Free tier30 minBeginnerSource linked

Source

jarodrh on Hacker News · 2026-07-07 · Project link

Written in our own words. Credit to the original author. Link checked 2026-10-15.

What they did

Built Frugon, a local MIT tool that finds which LLM calls a cheaper model could have handled.

Result (as claimed)

Local MIT tool on Show HN.

Tools they used

Claude ChatGPT OpenAI Codex

Cost: OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.

Set it up

Gather the documents
Collect statements, bills, invoices or tax documents for the period you want reviewed.
Ask for an audit, not actions
Have Claude list findings, amounts and suggested next steps before it does anything.
Approve each action
Approve cancellations, disputes or payments one at a time. Never give an agent open-ended access to move money.
Track the result
Record what changed and what you saved so you can check it next month. This is not financial advice.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Find which LLM calls a cheaper model could have handled
What the original author did: Built Frugon, a local MIT tool that finds which LLM calls a cheaper model could have handled.
Reported result (as claimed by the author): Local MIT tool on Show HN.
Source: https://news.ycombinator.com/item?id=48816724
Tools they used: Claude, ChatGPT, OpenAI Codex
Category: Money

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

You are helping me set up this AI use case end to end in Codex.

Goal: Find which LLM calls a cheaper model could have handled
What the original author did: Built Frugon, a local MIT tool that finds which LLM calls a cheaper model could have handled.
Reported result (as claimed by the author): Local MIT tool on Show HN.
Source: https://news.ycombinator.com/item?id=48816724
Tools they used: Claude, ChatGPT, OpenAI Codex
Category: Money

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

You are helping me set up this AI use case end to end in Grok Bot.

Goal: Find which LLM calls a cheaper model could have handled
What the original author did: Built Frugon, a local MIT tool that finds which LLM calls a cheaper model could have handled.
Reported result (as claimed by the author): Local MIT tool on Show HN.
Source: https://news.ycombinator.com/item?id=48816724
Tools they used: Claude, ChatGPT, OpenAI Codex
Category: Money

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5