jev-effort

by gebeer · ★ 1 · updated yesterday

Status linePromptvalidates

0

Sets the main conversation's reasoning effort per prompt with TypeSafe's Jev (via OpenRouter), reading recent conversation context. Shadow mode by default: logs what it would do without changing anything.

install jev-effort

Install

git clone https://github.com/gebeer/jev-effort
claude --plugin-dir ./jev-effort

Then run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.

View source on GitHub

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.submitturn.step
API calls
$.clock.now$.clock.sleep$.env.get$.http.fetch$.session.messages$.ui.log$.ui.status
Can see
every prompt
Reach
level 3 of 3 networkreads env varsreads the transcriptdraws

Origin

How it got here
Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
Repository
github.com/gebeer/jev-effort
Path in repo
repository root
Source commit
9c93f2c the exact code the scan read
Author
@gebeer
License
A license file GitHub could not identify — read it in the repository before reusing code.
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.