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 DeepSeek Harness plugin that walks a local directory, sends each text file's head to Jev, and returns a relevance-ranked shortlist so an agent reads only a few candidates instead of dozens.
How it uses Jev
For each file, code sends a state built from the query and a head summary, asking Jev a Score question over relevance criteria. The level is taken from argmax(probabilities); the continuous score is returned as expectedIndex for tie-breaking. Results are sorted and truncated to top.
Primitives:score
Technique worth stealing
Use argmax(probabilities) for the level, not round(score); keep score as a continuous tie-breaker.
Try it
Register as a DSH bundle, restart the host, then call jev_screen(root, query, top).
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 material0.81
- Shows a System One patternnot found in the excerpt0.34
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.91
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.46
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.17 / 2
- About JevFound in material0.98
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.