How to avoid hitting Claude's token limit

(and losing half your work mid-session):

_

1. Convert files before uploading.

A PDF page costs up to 3,000 tokens.

I paste the text into a Google Doc, download as .md. Done. 90% cheaper.

_

2. Plan in Chat. Build in Cowork.

Chat is cheap. Cowork is expensive.

I figure out what I want in Chat first.

Then I paste the plan into Cowork + Opus 4.6.

_

Full guide here: ruben.substack.com/p/ho…

_

3. Type "ask me questions" instead of a long prompt. My prompt is 30 words max:

 I want to [task] to [success criteria]. Read my folder. Ask me questions using AskUserQuestion before you start.

_

4. Edit your message. Never send a follow-up.

Every "No, I meant..." gets stacked on top of the conversation. Claude re-reads all of it. The Edit button replaces the old message. Cleaner and cheaper.

_

5. Match the model to the task.

Quick question → Chat with Haiku.

Writing a report based on files → Cowork with Opus.

Building a chart from data → Code with Sonnet.

_

More guides on claude at how-to-ai.guide

♻️ Restack if you learned something.