Next Prompt

Serge BaranovThread Content
Get it for macOS

Predicts the instruction you'll type next after each finished turn and shows it above the composer, one key from your draft. Press Tab or → in the empty composer, or click the line, to put it in your draft; nothing is sent for you. Choose the model with bb's provider and model picker: Claude Code and Codex models run as one CLI call with no tools, and any other provider runs as a hidden worker thread. Only the thread's user and assistant messages are sent, never tool output, and hidden and child threads are skipped. Each suggestion is one request on a provider you already use; the default, Claude Sonnet 5.5, needs the claude CLI signed in on the bb server.

Overview

View source

See the instruction you were about to type before you type it.

What you get

  • One line above the composer after each finished turn: ↳ next: run the tests.
  • Click it, or press Tab or → in the empty composer, to put it in the draft. It is never sent for you.
  • bb next-prompt to show, generate, and debug suggestions.

How it works

When a visible top-level thread goes idle, the plugin sends the first request and the newest user and assistant messages (no tool output) to a model, Sonnet by default. It filters the reply to one short instruction in your voice and keeps it until the thread moves on. Nothing is written to the thread or the agent's context.

Requirements

Pick the model with bb's provider/model picker. Claude Code and Codex models run as a lean CLI call (claude or codex logged in on the bb server) and use your existing subscription; other providers run as a hidden worker thread. An Anthropic- or OpenAI-compatible HTTP API can replace either.

More in Thread Content 45

Change what people see or do inside an open thread.

View all