I implemented ICM, but my usage it still high. Why?

I see this question a lot, so I wanted to share my take.

ICM (the stage-by-stage folder setup, where each stage loads only the context it needs) cuts waste. It doesn't cap usage on its own. If your usage is still high, it's usually one of these:

**1. Your context files are too big.**

This is a symptom of ai generated slop without proper human auditing, maintain your files! If each stage loads a 5,000-word reference doc "just in case," you've moved the bloat into a folder. Check what each stage actually reads. Keep stage instructions short and push reference material into files that are only loaded when needed.

**2. Stages aren't isolated.**

ICM only saves tokens if each stage starts clean. If you run everything in one long conversation, the model re-reads the whole history on every turn. Start a fresh session per stage and pass work forward through output files, not chat history.

**3. Too much gets loaded at the start.**

A bloated root `CLAUDE.md`, or a pile of always-on rules, skills and MCP tools, is paid for on every single message. Trim the always-on layer to the essentials. Manage your hooks and permissions properly!

**4. Outputs are being re-read in full.**

If stage 3 reads the entire raw output of stages 1 and 2, you're paying for it again. Have each stage write a short summary or handoff file, and have the next stage read that instead. My /handoff skill is one of my favorite and most used. One of the few things that's persisted in all my "restarts".

**5. Your model choice is off.**

Running the strongest model on every stage burns usage fast. Use a lighter model for mechanical stages (formatting, extraction, file moves) and keep the heavy model for the stages that need judgment. !! I was just burned on this today. I had my fancy new process all shiny and polished. Yesterday I was polishing and left a mark - today, Opus and Fable CRUSHED my account usage before I could notice, and I feel like I'm a careful person.

**6. Loops and retries.**

Auto-retries, "review and revise" cycles and agents re-scanning the codebase can quietly multiply usage. Set a clear stop condition for each stage and make sure you're reviewing at appropriate times.

**Quick audit (10 minutes):**

- List every file each stage loads and its rough size.

- Check how many turns each stage runs.

- Look at what's loaded before you've typed anything.

- Find the one stage that uses the most, and fix that first.

ICM reduces wasted context. It doesn't reduce the work itself. If the task is big, the usage will be too, but it should now be predictable and easy to trim.

Drop your setup below (folder layout, which stage is heaviest, which plan you're on) and I'll help you find where the usage is going. 👇

What are tokens?

SAME!

Please, Imma pro

3 votes

31 comments

I implemented ICM, but my usage it still high. Why?