Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Node ≥20 agent skill that sends state plus typed questions to the Jev model (TypeSafe System One) through OpenRouter, returning calibrated probabilities and action bands instead of generated text.
How it uses Jev
Jev answers noul/choice/score questions over a supplied state; results are validated and mapped to auto/hitl/abstain bands. Used for ticket triage, prompt-injection detection and urgency decisions, with eval measuring accuracy and ECE.
Primitives:choicescorenoul
Technique worth stealing
Treat injection detection as a signal that can push answers into hitl/abstain bands, never as execution permission.
Try it
export OPENROUTER_API_KEY=...; node scripts/jev.mjs selftest; node scripts/jev.mjs ask --request-file examples/requests/ticket-triage.json
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.96
- Shows a System One patternFound in material0.90
- Describes handling uncertaintynot found in the excerpt0.30
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.51
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.36 / 2
- About JevFound in material0.97
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 25 Sept 2026.