# Jev Model Routing

Use to pick the cheapest good-enough model or effort for a turn or a delegated task...

- Repository: https://github.com/kerpopule/hermes-jev-skills (1275 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-29
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add kerpopule/hermes-jev-skills --skill jev-model-routing -g -a claude-code -y`
Codex: `npx skills add kerpopule/hermes-jev-skills --skill jev-model-routing -g -a codex -y`
Cursor: `npx skills add kerpopule/hermes-jev-skills --skill jev-model-routing -g -a cursor -y`
Gemini CLI: `npx skills add kerpopule/hermes-jev-skills --skill jev-model-routing -g -a gemini-cli -y`

## Description

Use to pick the cheapest good-enough model or effort for a turn or a delegated task (lanes small to escalate), to decide continue/retry/verify/escalate/complete after each cycle, or to tune routing.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Model routing with Jev

Jev reads a turn and answers three questions in one ~0.4 s request: how hard is it, what kind of work is it, and would a mistake be costly. Code then walks your pool for that tier and specialty and takes the first model that fits (images, context size). You do not pick models by feel; you ask.

## On Hermes it is automatic

With the `hermes-jev` plugin enabled, each fresh user turn is routed once, before the first model call. Tool-loop follow-ups reuse that decision only while provider, endpoint, host model and outgoing request model remain unchanged. A mismatch disables routing for the rest of that turn, including an A → B → A return, without buying another classifier answer. If the first outgoing model disagrees with host metadata, retain the outgoing request and do not classify; equivalent provider prefixes are normalized. The next turn resets the decision. Endpoint bindings stay in memory and are not written to telemetry. Switches, per profile:

```
/jev                    status
/jev routing shadow     decide and log, but do not switch (start here)
/jev routing on         switch models
/jev routing off
/jev notice on          show "[Jev] medium · coding → kimi-k2.7-code · confidence 0.97" on routed replies
```

A plugin can swap the model, not the provider connection. On OpenRouter that still means every vendor (DeepSeek, GLM, Kimi, MiniMax, Grok, Qwen, Gemini, GPT). If you run `/model` yourself, your choice wins and Jev stays out of the way.

The rest: https://github.com/kerpopule/hermes-jev-skills/blob/HEAD/skills/jev-model-routing/SKILL.md