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
jevlint is a linter for Jev queries. It takes the request body you would send to System One—a state and questions—and reports where the query is written in a way the model is documented to handle badly. For developers writing Jev queries.
How it uses Jev
Model checks put the question under review to Jev as state, and ask one calibrated question per documented failure mode. Each check is phrased so a high probability means the defect is present; the probability is reported with the finding. Static checks run in code and cost nothing.
Primitives:choicescorenoul
Technique worth stealing
Phrase each check so a high probability means the defect is present; self-test catches inverted checks.
Try it
composer install && ./jevlint check examples/broken-triage.json --static-only
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 projectnot found in the excerpt0.35
- Shows a System One patternnot found in the excerpt0.17
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.90
- Top-10 learning shortlist signalunclear0.49
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 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.