Skip to content

Oxlint Plugin Jev

Experimental oxlint plugin that turns plain-English yes/no questions into lint rules, answered by TypeSafe Jev with a probability you threshold.

Stars
86
Language
TypeScript
License
MIT
Published by
Community
Author
wobsoriano
Last verified
Oct 2026

About this project

Oxlint rules written in plain English, answered by TypeSafe Jev. A rule is a yes/no question about a function, a call, a JSX element, or a whole file. Each match is sent to Jev with the question, and the plugin reports an error when the yes-probability clears your cutoff. In CI, set ci: "fail" so a run that could not reach Jev fails instead of passing quietly. Add the plugin and its one rule, jev/ask, to .oxlintrc.json. Your English rules go in the options.

Quoted from the project's README. Read the full README.

Highlights

  • Four targets only: whole function, call expression, JSX element or file, with no selector syntax.
  • File rules can add a second question to aim editor diagnostics and GitHub annotations at the violation.
  • A single request per file carries every match, and answers cache under node_modules keyed by the request.
  • Cutoff, timeout, match cap, snippet length and model id are all configurable, with the model defaulting to latest.

Watch out

The README carries an explicit experimental warning. If the key is missing, the request times out or the API errors, the plugin prints one warning and reports nothing for that file, and ci defaults to skip so a run can pass quietly. Answers are cached by request, so retuning a cutoff reuses cached answers while editing a question re-asks the file. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

1.5kGitHub stars
Open-source platform that puts ACP-compatible agents such as Claude Code, Codex, and Pi inside the team's Slack, Telegram, Discord, and GitHub workflows, with reusable Jev decisions for routing, response gating, and reviewer selection.
Jev Agents & MCP#community#jevbest
488GitHub stars
A coding agent built on pi that hands its non-code decisions — what enters the context, whether a command is safe, whether the work is done — to a small judge model at 35 decision points per turn.
Jev Agents & MCP#community#jevbest
210GitHub stars
An agent plugin for Pi, Claude Code, Codex CLI and Grok Build that asks Jev two classification questions to decide whether a session sits at a safe compaction boundary, then hints or compacts for you.
Jev Agents & MCP#community#jevbest
572GitHub stars
A CLI plus agent hooks that ask Jev one question per rule in your AGENTS.md on every edit or turn and return a probability, so a violating edit gets repaired inside the same turn. Claude Code, Codex, OpenCode, Pi.
Jev Agents & MCP#community#jevbest
147GitHub stars
A local-first desktop agent for macOS that carries work from a conversation through to a reviewable result, split into Home, Cowork and Crew. The part worth a developer's attention is Crew, where Jev suggests an assignee for a single unassigned task and you accept or ignore it.
Jev Agents & MCP#community#jevbest
116GitHub stars
Stanley is a CLI where you describe a code-review request in plain language and Jev routes it to one of ten bounded workflows. Each workflow is deterministic code that gathers bounded evidence and asks Jev fixed-choice questions per hunk; unmatched requests go to the Pi agent.
Jev Agents & MCP#community#jevbest
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai