Here’s the complete reference sorted by what they actually do:
โ /init
โณ Reads your repo and writes the project brief
โ /plan
โณ Switches to read-only mode and maps every step before touching a file
โ /context
โณ Shows what is eating your tokens
โ /compact
โณ Frees up context mid-session without losing the thread
โ /clear
โณ Full reset between tasks so old context stops poisoning new output
โ /model
โณ Swap Opus, Sonnet, Haiku mid-session
โ /agents
โณ Spin up sub-agents and split big jobs across parallel workers
โ /chrome
โณ Claude controls your browser. Clicks, fills, reads logs.
โ /loop
โณ Run a prompt on a recurring schedule for up to 3 days
โ /rewind
โณ Undo when Claude goes off track
โ /ultraplan
โณ Forces max reasoning depth for one turn
The graphic has all 89 in one place.
Save it. You’ll come back to it.
๐ Join 1,600+ AI content creators in my free community: (Link in bio)
โป๏ธ Repost to help someone in your network use Claude Code properly.
โ Follow Us for more on AI and LinkedIn growth.
