// 12 tips tagged "claude-md"
Writing AGENTS.md as plain text in CLAUDE.md has no effect — use @AGENTS.md to actually load the file into context.
Set CLAUDE_CODE_NEW_INIT in settings.json to make /init interview you for targeted improvements instead of overwriting your existing CLAUDE.md.
CLAUDE.md loads into every message. Move workflow-specific instructions into skills that load on demand to reduce token costs across your session.
Once you've settled an architectural debate with Claude, write the decision into CLAUDE.md — or it will suggest the same alternatives again next session.
Add a "bad patterns" section to CLAUDE.md with concrete examples of code you never want to see -- Claude absorbs your no-go list before writing a single line.
Ask Claude to add a rule to CLAUDE.md whenever you correct it, so the same mistake never happens twice.
A CLAUDE.md in your home directory sets preferences that apply to every project — no more re-explaining your coding style from scratch.
Stack CLAUDE.md files at different directory levels so each part of your monorepo gets the exact context it needs.
Skip the blank page — /init scans your codebase and generates a tailored CLAUDE.md in seconds.
Start any message with # to instantly save a note to Claude Code's persistent memory — without breaking your flow to run a separate command.
A CLAUDE.md file at the root of your project gives Claude Code persistent context about your codebase.
Every time you correct Claude or agree on a preference, capture it in CLAUDE.md — it becomes the persistent memory that carries across every future session.