Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-kit installs guards, a warm daemon, file search, a browser agent, review, belay, compaction and monitoring so Claude Code agents can use TypeSafe's Jev as a judge. It targets developers running Claude Code who want typed decisions in the agent loop.
How it uses Jev
Jev judges each PreToolUse tool call: a rules table runs first, then one typed Jev question handles the ambiguous half, and the returned decision becomes a deny or allow. A tier guard checks sub-agent rungs, and the browser agent has Jev choose each click instead of a language model.
Primitives:choicescorenoul
Technique worth stealing
Let a small typed-decision model pick each step so the language model only writes text, collapsing per-run spend.
Try it
git clone the repo, run install/install.sh, add TYPESAFE_API_KEY to ~/.config/jev-kit/env, stay in shadow mode first.
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 patternunclear0.46
- Describes handling uncertaintynot found in the excerpt0.09
- Reports measured numbersFound in material0.96
- Is a runnable toolFound in material0.90
- Top-10 learning shortlist signalunclear0.55
- 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 19 Oct 2026.