Slash Command

/end-thread

From thread

Close the current side thread and resume the main conversation

Invocation

How this command is triggered — by the user, by Claude, or both

Slash command

/thread:end-thread

Model invocable

No pre-commands

Context Preview

The summary Claude sees in its command listing — used to decide when to auto-load this command

The user is closing a SIDE THREAD opened earlier with `/thread:new-thread`. Resume the main conversation.

## Protocol

1. **Detect prior thread state.** Read your recent assistant turns. If no `┌─── SIDE THREAD` opening fence appears (or every opening fence already has a matching `└─── back to main` closing fence), there is no thread to close. Reply briefly:

   *"No side thread is open."*

   Do nothing else.

2. **Otherwise, close the thread.** On a new line, write the closing fence — the first line is still inside the fence (so it has the `│ ` prefix), the second line is the closing fen...

Command Content

26 lines · ~363 tokens

Stats

Stars0

MaintenanceGood

Last CommitMay 28, 2026

Actions

View Source View Plugin View on GitHub View README

Stats

Actions

Protocol

Detect prior thread state. Read your recent assistant turns. If no ┌─── SIDE THREAD opening fence appears (or every opening fence already has a matching └─── back to main closing fence), there is no thread to close. Reply briefly:

"No side thread is open."

Do nothing else.
Otherwise, close the thread. On a new line, write the closing fence — the first line is still inside the fence (so it has the │ prefix), the second line is the closing fence character:
```
│ >>> /thread:end-thread
└─── back to main ───────────────────
```
Resume the main conversation. From the next line on, drop the │ prefix. Give a brief one-line acknowledgement that you're back (e.g. "Back to the main thread."), then continue addressing whatever the user was working on before the thread opened. Your own conversation memory holds that context — pick up the main work naturally.

Why

/thread:end-thread is the explicit signal that the side discussion is done. Without it, replies would stay inside the fence indefinitely; with it, the visual and contextual switch is unambiguous. The closing fence on its own line is the scroll-back marker that says "everything below here is main conversation again."