Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code plugin that scores each submitted prompt with TypeSafe Jev and runs the turn on the model and reasoning effort the prompt deserves, rewriting the model request in code rather than parsing prose.
How it uses Jev
On prompt.submit the redacted prompt goes to Jev with a four-level score (trivial, routine, hard, frontier) and a noul asking whether it is a follow-up. The level maps through router.json's ladder to a model and effort; thresholds are applied in code and the request is rewritten.
Primitives:scorenoul
Technique worth stealing
Effort changes are nearly free because the prompt prefix stays cached, while model changes cost a full cache write, so the default ladder changes effort only and cost-gates downgrades.
Try it
Install via /plugin install jev-model-router --marketplace m-esm/jev-model-router, set TYPESAFE_API_KEY, or run ./install.sh for the command-hook fallback.
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 projectFound in material0.92
- Shows a System One patternFound in material0.97
- Describes handling uncertaintynot found in the excerpt0.15
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalunclear0.56
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 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 3 Nov 2026.