26 Claude slash commands that save serious time

I’ve been using Claude almost daily for months, and I still catch myself typing out long instructions when a two-character shortcut would do the same job. Then I stumbled on a post from this LinkedIn creator that lined up every slash command Claude supports in one clean reference. I was honestly a little embarrassed at how many I didn’t know existed.

The original poster basically did the work of digging through Claude’s docs so the rest of us don’t have to. Drop any of these at the very start of your prompt and Claude jumps straight into that mode. No fluff, no setup, no extra tokens wasted.

Here’s the full breakdown, organized so you can actually find what you need when you need it.

Session and conversation control

These are the ones you’ll reach for most. Managing context is half the battle when you work with Claude every day, and the author pulled together a clean set of commands for exactly that.

1. /CLEAR wipes conversation history and resets context. Perfect when you switch topics and don’t want old context bleeding into the new task.
2. /COST shows token usage for the current session. Great for keeping an eye on spend without leaving the chat.
3. /COMPACT [instructions] compresses the conversation and lets you specify what to keep. The hidden gem here is the instructions part, you can tell Claude exactly what context matters.
4. /RESUME [session] reopens a previous conversation by ID or name. No more scrolling through history hunting for that one thread.
5. /BRANCH [name] creates a new branch from the current conversation. Use it when you want to explore a tangent without losing your main flow.
6. /REWIND rolls the conversation and code back to an earlier point. A lifesaver when an experiment goes sideways.
7. /RENAME [name] renames the current session. Leave it blank and Claude auto-generates one for you.
8. /EXPORT [filename] saves the conversation as plain text. Handy when you want to share a session or archive a useful exchange.

Model, usage, and plan controls

This section is where the original poster surfaced commands a lot of people miss. Switching models mid-conversation alone is worth knowing.

9. /MODEL [model] switches between Sonnet, Opus, or Haiku without leaving the chat. Use Haiku for quick lookups, Sonnet for most work, Opus for the heavy lifting.
10. /USAGE shows your plan limits and current rate-limit status. Check it before kicking off a big batch of prompts.
11. /EXTRA-USAGE turns on extra usage when you hit standard limits. Crucial during crunch days.

Project setup and memory

If you work in Claude Code or use Claude across projects, this group is where things get really powerful. The expert grouped these in a way that made me realize how much I’d been doing manually.

12. /INIT sets up your project with a CLAUDE.md guide. Foundation step for any serious project work.
13. /MEMORY edits CLAUDE.md memory files and controls auto-memory. This is where you teach Claude about your preferences, tools, and patterns.
14. /ADD-DIR <path> adds a working directory so Claude can access more files during the session.

Code review and security

For anyone shipping code, these three commands take a chunk of busywork off your plate.

15. /DIFF opens a diff viewer for uncommitted changes and per-turn diffs. Way faster than alt-tabbing to your terminal.
16. /SECURITY-REVIEW scans pending changes for security issues. I think this one alone justifies bookmarking the whole list.
17. /PLAN [description] drops Claude into plan mode, optionally starting with a task. Forces a thought-out approach before code gets written.

Permissions, agents, and skills

This is the configuration layer. The creator did a solid job calling these out because most folks don’t realize how much customization is baked into Claude.

18. /PERMISSIONS manages allow, ask, and deny rules for tool access. Set it once and stop getting prompted on every action.
19. /AGENTS manages agent and sub-agent configurations. The doorway to multi-agent workflows.
20. /SKILLS lists every skill available, built-in and custom. Way easier than digging through folders.

Plugins and connections

The integration commands. These keep your environment clean without forcing a full restart.

21. /PLUGIN manages your Claude Code plugins.
22. /RELOAD-PLUGINS refreshes active plugins without restarting the session. Saves real time when you’re iterating on a plugin config.
23. /MCP manages MCP server connections and OAuth authentication. The control room for everything you’ve connected to Claude.

Personalization

Small but lovely touches the post wrapped up with.

24. /CONFIG opens settings for theme, model, output style, and preferences.
25. /THEME changes the color theme, including light, dark, and accessibility-friendly options.
26. /COLOR [color] sets the prompt bar color for the current session. A tiny thing, but useful when you run several sessions side by side.

Why this list actually matters

The point isn’t to memorize all 26. The point is to know that the shortcut exists so you reach for it instead of typing five sentences.

I caught myself using /COMPACT with instructions right after reading the post, and the difference was immediate. Cleaner context, faster responses, less re-explaining.

The original poster bundled this together as a save-for-later cheat sheet, and honestly, that’s exactly how it should be used. Pin it, screenshot it, drop it in your notes app. You’ll thank yourself the next time you’re 40 turns deep into a conversation and need to branch off without losing the thread.

Check out the full LinkedIn post for the original layout and a few extra notes from the author.