CalibratedDecisions.

Repo · Coding & code review

Jev for Claude Code (brookcs3)

Unofficial Claude Code plugin exposing TypeSafe Jev typed judgments (noul/choice/score) plus corpus→eval loops.

Open github.com ↗

From the repository

Jev: TypeSafe's System One model as a Claude Code tool. Evidence-backed calibrated odds, typed judgments at scale (classify, search, rerank, score, guard, cite, route, extract), and a corpus → set → run → eval → train loop around fixed weights. Unofficial.

agent-skillscalibrationclaude-codeclaude-code-pluginclaude-pluginjevllm-evaluationtypesafe

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects