Jev 101
Start Guides
Search
中文 EN
Ops heat 1 · Quiet★ 0heat incomplete (no X)

jevlint

A MIT model-based linter (npm @indxjp/jevlint) that combines AST metrics with hosted TypeSafe Jev (or other decision providers) to rank which files to refactor first, explain findings, and hand prompts to Claude Code/Codex—including PR/commit delta reviews.

Repo: INDXDev/jevlint ↗

What it is

Rank messy files with calibrated scores, not a wall of ESLint noise.

What it does: AST + decision-model scoring, ranked refactor queue, agent fix prompts.

Why it belongs in the showcase: Distinct code-quality use of hosted Jev beyond chat review bots.

Caveats: Provider auth for judgment lanes.

Evidence

Public MIT repo, created 2026-11-04, 0 stars as of 2026-11-05. README/docs document npx --ast-only offline mode, jevlint auth set typesafe, CI badge, multi-language scoring, caching, and Claude Code plugin/hook.

Caveats

  • Decision-model path needs a provider key; --ast-only skips remote judgment
  • Independent project; not affiliated with TypeSafe
  • Requires recent Node (24.22.1+ or listed LTS lines)

Unofficial case page. Stars / list position observed for heat; do not treat heat as a quality SLA. Review the upstream README before you depend on it.