/memoryTells Claude to remember a specific fact for the rest of the conversation.
Category: Power Commands
Before / After
Remember this for later: [fact].
/memory My team uses Postgres 16 with pgvector. Always assume this stack.
What changes in Claude's response
Without /memory, Claude forgets context after ~5 messages — you'll find yourself re-explaining your stack on message 8. With /memory, the fact gets pinned and Claude references it consistently. Use it for stack details, naming conventions, and project constraints you'll keep coming back to.
When NOT to use /memory
Skip /memory for ephemeral details. Claude has limits on how much it can pin — don't waste the budget on stuff you'll only mention once.
Codes that stack with /memory
/memory is one of 120 tested prompt prefixes. The full cheat sheet has before/after examples, warnings, combos, and 10 workflow playbooks.
See the full cheat sheet — from $5More Power Commands codes
/godmodeThe most thorough, longest, most detailed response Claude can give. Use sparingly.
/autopromptYou give Claude a rough idea, it builds the perfect prompt to get the best output.
MEGAPROMPTGenerates a long, detailed prompt for exactly what you want — usually 500+ words.
/chainRuns multiple prompts in sequence, feeding each one's output into the next.
/systemWrites a custom system prompt you can drop into any LLM, not just Claude.
Get new codes + workflows weekly
Join 30+ developers getting tested prompt codes, skill files, and Claude workflows. One email when there’s something worth sharing.