Automated README summary
Automatically summarized from the README on 15 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jgrep is a CLI that finds code by what it does, not what it is called. It splits files or git diff hunks into chunks, asks Jev typed questions, and prints file:line hits above a probability threshold. It is for developers and CI pipelines.
How it uses Jev
jgrep packs several 5–60 line code chunks into one request with a Noul question per chunk. Jev returns calibrated probabilities for each chunk. jgrep prints file:line hits above a threshold and uses grep-style exit codes. It also supports --tests to select affected test files, and --rows for CSV/JSONL scoring with noul, choice, and score questions.
Primitives:noulchoicescore
Technique worth stealing
Packing multiple code chunks and typed questions into one Jev request to get calibrated probabilities for semantic search.
Try it
npm i -g jevgrep && jgrep init && jgrep "catches an error and silently ignores it" src/
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 material0.89
- Shows a System One patternFound in material0.89
- Describes handling uncertaintyFound in material0.70
- Reports measured numbersFound in material0.97
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalunclear0.54
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.96 / 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 15 Oct 2026.