Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Sniff Test reads Markdown and plain text and flags prose against house rules, printing file, line, rule and confidence per flag. It targets writers and teams checking drafts for AI-style tells, with a CLI, pre-commit hook, GitHub Action and Claude Code skill.
How it uses Jev
For judgment rules, each paragraph is sent to Jev with the wording of every judgment rule; Jev returns one probability per rule per paragraph. A reading at or above the threshold (0.7 default) becomes a flag; readings between 0.4 and 0.6 count as no judgment.
Primitives:score
Technique worth stealing
Treat the 0.4–0.6 band as no judgment, since the model answers about 0.5 on text it cannot read.
Try it
npm install --global snifftest; snifftest check --dry-run draft.md
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 projectunclear0.49
- Shows a System One patternFound in material0.88
- Describes handling uncertaintyFound in material0.78
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelnot found in the excerpt0.11
- Solves a common problem (0–2)score on a 0–2 scale1.06 / 2
- About JevFound in material0.85
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 22 Oct 2026.