Overview & Result
An installable skill for developers using Claude Code and Codex. Instead of manually specifying flags, Jev inspects the prompt and dispatches to the most cost-effective model tier.
How Jev fits in the loop
- Skill triggers on user prompt entry.
- Jev classifies prompt into trivial, standard, or reasoning categories.
- Skill redirects invocation to target model backend.
How to reproduce
- Inspect the source implementation at https://github.com/heyman333/jev-router.
- Configure local Jev API credentials and register required tool/model bindings.
- Execute test prompts and observe decision latency and routing outputs.
Why this build matters
Simplifies multi-model workflows directly inside developer terminals.
Limitations
- Metrics are author-reported from the initial release unless independently verified.
- Requires access to the respective agent framework or runtime environment.
- Generative model execution remains external to the Jev decision step.