Using Claude Code: Session Management & 1M Context
Source
Thariq
Author
Thariq
Date
Key takeaways · AI-distilled
Rewind beats correcting. Typing 'that didn't work, try X' leaves the failed attempt sitting in context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →; double-tapping Esc drops every message after the point you jump to, so you re-prompt from the file reads with what you learned and none of the wreckage.
Before you rewind, ask Claude to 'summarize from here'. You get a handoff note from the attempt that failed — effectively a message to the next iteration of Claude explaining what was already ruled out.
Compact and clear trade the same thing in opposite directions. Compact is lossy but free: Claude decides what mattered, and you can steer it ('/compact focus on the auth refactor, drop the test debugging'). Clear costs you writing the brief, and the survivors are your pick.
The one-session-per-task rule has an exception for genuinely adjacent work. Documenting a feature you just built in a fresh session means Claude re-reads the same files — slower and more expensive than carrying the context over.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
Practical guidance on the new /usage view, session management, and actually living with a 1M-tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → context window. Read it to stop guessing where your context budget goes and to plan long Claude Code sessions.
Key quotes
“Context rot is the observation that model performance degrades as context grows because attention gets spread across more tokens, and older, irrelevant content starts to distract from the current task.”
“If I had to pick one habit that signals good context management, it’s rewind.”
“Our general rule of thumb is when you start a new task, you should also start a new session.”
