✦ You asked for this

Free pack · $0

Here is the Token Diet. It is free.

Before you pay more, stop burning what you already pay for. These are the four changes I made so my agents waste less on the same plan. Start with the first one today.

Take me to itfree · on this page
No sign-upNo cardWorks in Claude Code and Codex

✦ The four changes

Four changes. Start with the first one today.

Most of us are not short on plan. We are wasting it. These are the four changes that stopped my agents wasting 1.4 billion tokens on the same plan.

Why now

OpenAI just made ChatGPT's top plan $500 a month. From October 30, the $200 plan gets half the usage it had, 10x the Plus plan instead of 20x.

My real numbers: 1.4 billion tokens my agents never had to read.

rtk gain showed that RTK trimmed 70% of the noisy command output before my agents read it. These are test logs, file listings and git logs, not total plan usage.

  • 1.4B: tokens my agents never had to read
  • 70.7%: of noisy command output trimmed

Do this first (2 minutes, no terminal)

In Claude Code, type /model and pick Sonnet as your everyday model. Switch to Opus only when a job actually fails. In ChatGPT, use the regular model for everyday work and save the Pro and thinking models for hard problems.

Words on this page, in plain English

  • Token: the unit AI reads and writes; your plan's limit is counted in tokens.
  • Claude Code: Anthropic's AI assistant that works in your project folder.
  • Terminal: the app on your Mac where you type commands. Open it with Cmd+Space, type Terminal, press Enter.
  • Codex: OpenAI's coding assistant, the ChatGPT version of Claude Code.
  • Hook: a small rule that runs automatically before the AI does something.

Change 1: Filter the noise before AI reads it

Every time your agent runs a command, the whole output goes back into the model. Test runs, git logs, file listings. Most of it is noise: hundreds of passing tests, the same headers over and over, folders nobody asked about. You pay for every line of it, and it crowds out the stuff that matters. RTK sits between your agent and the terminal and trims that output down to what the model actually needs before it reads it. You do not change how you work. It just happens. To be clear, RTK is not my tool. It is free and open source, made by the team at rtk-ai.app. I just use it every day. It trimmed 70% of noisy command output before my agents read it.

Change 1: the commands

Don't have Homebrew? Install it from brew.sh first (one command). Needs Homebrew on a Mac. Other platforms and agents (Cursor, Gemini CLI and more) are covered on the RTK site.

StepWhat it does
brew install rtkInstalls RTK on your Mac.
mkdir -p ~/.claudeMakes sure Claude Code's settings folder exists.
rtk init -g --auto-patchInstalls RTK's hook into Claude Code with no questions asked.
quit and reopen Claude CodeThe hook loads when Claude Code starts. Then work normally for a day or two.
rtk gainRun this later to see your own savings.
Terminal
brew install rtk
mkdir -p ~/.claude
rtk init -g --auto-patch
# quit and reopen Claude Code, then work normally for a day or two
rtk gain

Change 2: The cheapest model that can do each job

Running the top model on everything is like hiring a surgeon to put on a bandage. It works. It is also the fastest way to hit your limit by Wednesday.

The jobUseFor example
Quick lookups, renames, formatting, summariesSmall, fast modelClaude Haiku
Everyday coding and writingMid modelClaude Sonnet
Architecture, hard debugging, high-stakes writingTop modelClaude Opus

Change 2: the tip

Set your default to the mid model. Step up to the top model only when a task fails, then step back down. Most days you will barely touch it, and you will not miss it.

Change 3: Audit your CLAUDE.md against mine

Your CLAUDE.md gets read at the start of every session, so every extra line costs you every time. But short is not the goal, right is. I keep an Ultimate CLAUDE.md that I give away. The prompt in the Use it now box below goes into Claude Code in your project folder. It audits yours against mine and upgrades only what fits your business. Review the changes before saving your updated CLAUDE.md.

  • Before: rules that do not fit your business
  • Before: stale, repeated or overly long instructions
  • Before: useful rules from the Ultimate CLAUDE.md may be missing
  • After: only rules relevant to your business
  • After: short startup instructions with detail files linked
  • After: you review the changes before saving

Change 4: Put a receptionist in front of your AI (advanced, optional)

For developers: how I route every request. If you use Claude Code, you can install it from the GitHub page; if not, skip this one. Most people send every request straight to the most expensive model. That's like having your CEO answer the phone. So I built a receptionist. I call it MyOS Dispatch. Before any AI runs, it looks at the request and sends it to the cheapest place that can handle it.

  1. Simple stuff: checking a file or a status. Handled instantly, no AI at all.
  2. Jobs I've done before: it runs the saved recipe. No AI needed.
  3. Real work: goes to the cheapest model that can do it, with only the files it needs.

Change 4: who makes the calls

To make those calls fast, Dispatch uses Jev, a tiny model from TypeSafe AI (not mine) that only picks from a short list of answers. It costs me about 18 cents a day. The point: use a classifier for choices, and save the big model for real work. Picking a lane is not a job for the smartest model you pay for.

One habit that lasts

Prices will keep moving. Usage limits will keep moving. The habit that holds up either way is the same one: do not pay a model to read things it does not need.

✦ Use it now

Audit your CLAUDE.md in a minute

Tap Copy, open Claude Code in your project folder, paste it and send. It compares your CLAUDE.md to my Ultimate CLAUDE.md and shows you the changes before it saves anything.

Start here · Change 3 in one prompt

Audit and upgrade my CLAUDE.md

It keeps only what fits how you work, and moves long details into separate docs files.

Read my CLAUDE.md (and AGENTS.md if I have one). Then read Joe Che's Ultimate CLAUDE.md at https://workshop.mastermindshq.business/giveaways/claude-md

Audit mine against his:
1. What useful rules or sections am I missing?
2. What in mine is stale, repeated, or too long?
3. What in his does not apply to my business? Skip those.

Then upgrade my CLAUDE.md. Add only what is relevant to how I actually work. Keep it short: move long details into separate docs files and point to them. Show me the changes before you save.

✦ Get unstuck

Stuck? Find your line.

I do not know what the terminal is

It is the app on your Mac where you type commands. Open it with Cmd+Space, type Terminal, press Enter. If you would rather skip it, do the first change instead: in Claude Code, type /model and pick Sonnet. No terminal needed.

It says brew: command not found

The RTK commands need Homebrew on a Mac. Install Homebrew from brew.sh first (one command), then run the commands again.

I am not on a Mac, or I do not use Claude Code

The commands here are for Homebrew on a Mac. Other platforms and agents (Cursor, Gemini CLI and more) are covered on the RTK site, rtk-ai.app.

rtk gain shows nothing

Quit and reopen Claude Code so the hook loads. Then work normally for a day or two before you run rtk gain.

I use ChatGPT, not Claude Code

The model tip works there too: use the regular model for everyday work and save the Pro and thinking models for hard problems. The audit prompt is for Claude Code.

Will this cut my whole plan by 70%?

No. The 70% is for noisy command output only: test logs, file listings and git logs. It is not total plan usage.

None of these fixed it

Email joe@mastermindshq.business. Say which step you were on and paste what you saw.

✦ What next · paid · optional

Want the next step? Get Found on Google and ChatGPT.

$47one payment, no monthly fee
0API keys or paid services
1prompt per step, run by your Claude Code
14day found check: day 1, 7 and 14
Joe Che

You came for one piece of my Claude Code setup. If you have your own website, the next useful job for that setup is getting the site found.

Get your website listed on Google and Bing so people (and ChatGPT) can find you by your name and your service. ChatGPT finds websites mostly through Bing, so we tell Bing about you too. Your own Claude Code does the work on your computer, one prompt at a time.

  • What it does: sets up Google and Bing, your Google Business Profile, posts that answer real customer questions, and a monthly check.
  • What usually happens: your site shows up when people search your name or business name within a few weeks.
  • What it cannot promise: ranking for competitive searches like "best X near me". That takes months of steady posts.
  • You need a website in a folder Claude Code can open, Node.js 20 or newer, and a free Google account. It is not for Squarespace or Wix sites.
$47One payment. No monthly fee. Your own Claude Code runs it, so nobody else needs access to your accounts.
Get the kit$47 · one payment · secure checkout

Not for you? Close this page. Everything above stays free.

Created by Joe Che.

ChatGPT is a trademark of OpenAI. Claude is a trademark of Anthropic. This page is not affiliated with either.