Use # to Add Memory Notes Mid-Conversation
Start any message with # to instantly save a note to Claude Code's persistent memory — without breaking your flow to run a separate command.
# always use TypeScript strict mode for this project
That single line gets written to your memory file and applied in every future session for this project. It's a faster alternative to /memory add when you're mid-task and want to capture a decision the moment you make it.
You can drop multiple notes in one message:
# prefer named exports over default exports
# use Zod for all input validation
# never use `any` in TypeScript
Each line stacks alongside your existing memory entries, so your preferences build up naturally as you work. Claude will respect them from the next message onward.
This is especially useful when you've just agreed on an architectural pattern with Claude and want to lock it in before moving on — note it immediately rather than trusting yourself to remember later.
# use the repository pattern for all database access
# controllers should only handle HTTP — no business logic
Capture decisions as you make them — the best time to add a memory note is right when you decide something.
Log in to leave a comment.
When typing feels slow — describing a complex bug, explaining architecture, or thinking through a problem out loud — press Option+V to switch to voice input. Speak naturally and Claude Code transcribes your words into a prompt, so you can describe what you need at the speed of thought.
When Claude is heading down the wrong path — editing the wrong file, writing code you don't want, or giving a long explanation you don't need — press Escape to stop it immediately. You keep everything it did up to that point and can redirect with a new prompt.
Closed a session and realized you weren't done? Pass --continue (or -c) when launching Claude Code to pick up exactly where you left off — same context, same files, same conversation history — without re-explaining what you were working on.