Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-router is a free Claude Code plugin for developers who want to cut Claude costs. It automatically picks Haiku, Sonnet, Opus, or Fable per prompt, step, and subagent, caps reasoning effort, and shows picks in a live status band.
How it uses Jev
Jev decides which Claude model and reasoning effort to use for each prompt, step, and subagent. The plugin sends the prompt, optional recent messages, and subagent task text to the System One API, then uses the returned choice to route the request and enforce an effort cap.
Primitives:choice
Technique worth stealing
Use a System One model to pick the cheapest capable Claude model and cap reasoning effort per prompt, step, and subagent.
Try it
Install via /plugin marketplace add dominicrico/jev-router and /plugin install jev-router@jev-router, then /jev key and /jev status.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectunclear0.59
- Shows a System One patternunclear0.48
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalnot found in the excerpt0.19
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.10 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 23 Oct 2026.