Claude Code tips: how to run long sessions without babysitting them

Short Claude Code sessions run themselves. Long ones, the hour-long refactor or the multi-file feature, need a different set of habits, most of which are about setting things up so you can walk away.

Scope the task before you start

A long session with a vague goal wanders. Write the goal, the definition of done and the constraints in the first prompt, and put anything stable about the repo (build commands, conventions, traps) in a CLAUDE.md so it is read every time. The best long sessions are the ones where the agent never has to guess what you meant.

Set permissions deliberately

Decide up front which tools can run without asking: reads and tests, usually. Keep the gate on writes outside the project, installs, network calls and anything destructive. Use Always for the safe repeats so the asks you do get are the ones that matter, and never switch the gate off wholesale for a session you are not watching.

Checkpoint with commits

Ask the agent to commit at natural boundaries with descriptive messages. A long session then becomes a series of small, revertable steps, and reviewing the diff later is a review of commits rather than a wall of changes. If something goes sideways, you reset to the last good one.

Supervise from a distance

The habit that makes long sessions actually long: leave. The session needs you at unpredictable moments for a few seconds each; be reachable for those moments without being tethered. PeakWatch puts the session list on a Galaxy Watch, ranked by which one is waiting, with the tool and arguments in every approval and a countdown that denies if you do not answer. Dictate the next prompt from wherever you are; ask for a summary when you come back.

Review, then trust

Read the diff. Run the tests yourself once. Long sessions earn trust the same way colleagues do, by being right in ways you checked.