Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code Mod that chooses a model and effort tier (micro, low, medium, high) for each main-conversation turn and for routed subagents, using a prompt classifier such as Jev, Clef, OpenAI, or a local Ollama model.
How it uses Jev
Jev is the default classifier. At the start of each logical turn it is asked for the tier and the turn's activity, and again in the background every 4 requests; with subagent routing on it is also asked once per routed subagent. Jev answers with a third choice question in the same request. The router uses the advice to change only the model and effort in Claude Code's turn hook.
Primitives:choice
Technique worth stealing
Classifier advice is applied only to model and effort in the turn hook, with a local policy of vote, context, failure, and cache-cost rules before each change.
Try it
Install via claude plugin marketplace add alexei-l; Jev is the default classifier and needs a Jev API key.
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 projectnot found in the excerpt0.04
- Shows a System One patternunclear0.41
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.16
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.08 / 2
- About JevFound in material0.76
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 4 Nov 2026.