classify-hint
by corrupt952 · ★ 1 · updated 5 days ago
Classifies the user's prompt with Haiku against a few yes/no questions in one call and attaches a rough, non-binding hint for the main agent
Install
git clone https://github.com/corrupt952/dotfilesclaude --plugin-dir ./dotfiles/modules/claude/mods/plugins/classify-hintThen 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
prompt.submit- API calls
$.clock.sleep$.model.complete$.session.messages- Can see
every prompt- Reach
- level 2 of 3 drives Claudereads the transcript
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/corrupt952/dotfiles
- Path in repo
modules/claude/mods/plugins/classify-hint- Source commit
17d8550the exact code the scan read- Author
- @corrupt952
- License
- MIT
- First published
- Last pushed
- First listed here
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.
More from corrupt952/dotfiles
blocker-ask-hint
corrupt952/dotfiles
When the auto mode classifier blocks a tool call, reminds the agent to ask the user for approval instead of giving up on an action the user asked for
verify-reports
corrupt952/dotfiles
Attaches a verification reminder to every delivery from another agent: a subagent's hand-back, a background task's notification, another session's message