Automated README summary
Automatically summarized from the README on 16 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A playground for deciding which typed classifier technique answers coding-agent questions, proving it live, measuring value, and shipping winners through a model-neutral CLI. For teams building coding-agent fleets.
How it uses Jev
Jev is one technique among several. It answers typed questions (Choice, Score, Noul) over a JSON state, returning calibrated probabilities. The README does not specify which decisions Jev makes in the shipped CLI or how its output is used in code.
Primitives:choicescorenoul
Technique worth stealing
Labels first; constant and cheapest rule set the bar; commit the bar before the first call; calibrate all backends the same way.
Try it
npx --prefix kit --no-install classifier rerank --query "..." --candidates kit/examples/rerank-candidates.json --fake --robot
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 material0.83
- Shows a System One patternFound in material0.76
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.07
- Is a runnable toolFound in material0.62
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.13
- Solves a common problem (0–2)score on a 0–2 scale1.77 / 2
- About JevFound in material0.96
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 16 Oct 2026.