explain-again
by smughead · ★ 0 · updated today
After a longer reply, offers to re-explain it in plain English, as a diagram, a web page or a video, sent now or edited first (after Karpathy's output-format tips).
Install
/plugin marketplace add smughead/explain-again/plugin install explain-again@explain-againThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startturn.startprompt.submitturn.completecommand.runui.render- API calls
$.clock.after$.command.register$.prompt.fill$.prompt.submit$.ui.resolve
Origin
- How it got here
- Found through a post on X by @smughead902, then checked on GitHub: the repo has a plugin manifest and function hooks. Listed .
- Repository
- github.com/smughead/explain-again
- Path in repo
- repository root
- Source commit
87ab6c1the exact code the scan read- Author
- @smughead
- License
- MIT
- First published
- Last pushed
- First listed here
- On X
- Mentioned in 1 post on X
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.
Posts about this repo
I built Explain Again, a Claude Code mod (thank you @karpathy for the idea). Basically just one button prompts that change the LLM output, typically used for longer outputs when you get sick of reading walls of text when you're not retaining anything anyway. http://github.com/smughead/explain-again