shipwithjev

Catalog / Tools & apps

0366GitHub

JevLint

Checks code against conventions written in plain English, in a write-check-fix loop with your coding agent.

huntedman/JevLintREADME ↗
# JevLint

**Slop happens. Don’t ship it.**

Write coding conventions in plain English. JevLint checks what your code means, semantically, so your coding agent can fix what syntax rules miss.

Use it in a **write → check → fix → repeat** workflow: your agent writes code,
JevLint checks it against your conventions, and the agent uses the findings to
make the next edit. Run it from your terminal, an agent’s verification step, or CI.
Your agent or workflow controls when to run checks and how to fix findings;
JevLint supplies the judgments.

JevLint is powered by Jev, TypeSafe AI’s System One model. It sends selected source
files and plugin instructions to the Jev API, then reports the probability that
each file violates a rule. Findings are file-level signals for review, without
line-level diagnostics, generated replacement names, or automatic fixes. The
default finding threshold is `0.8` (80%).

[Website](https://jevlint.com) · [npm](https://www.npmjs.com/package/@jevlint/cli) ·
[GitHub](https://github.com/huntedman/JevLint)

## Get started

Requires **Node.js 24 or newer**. From your project root:

```sh
npm install --save-dev @jevlint/cli
npx jevlint init
```

`init` creates `jevlint.config.json` with `magic-strings` enabled,
`prettyPrint: true`, and exclusions for tests and TypeScript declaration files.
It never overwrites an existing config. Configuration is optional: without one, JevLint scans the current directory with `magic-strings`.

Add your key to `.env` in the directory where you run JevLint:

```dotenv
JEV_API_KEY=your-api-key
```

The CLI loads `.env` automatically; exported shell variables take precedence.
Then run:

```sh
npx jevlint
```

To choose targets, preview requests, or adjust the threshold:

```sh
npx jevlint src
npx jevlint 'src/**/*.ts' --ignore

Also filed under Tools & apps

  1. 0573

    Support chat: agent offered a human escalation path

    A frustrated customer hits a bot loop twice; the judge checks whether a human handoff was offered.

    everyai-com · Tools & apps

  2. 0572

    Subscription cancel: effective date is explicit

    An agent cancels a subscription; the judge checks the exact date the cancellation takes effect.

    everyai-com · Tools & apps

  3. 0571

    Sales quote: numbers match the official price list

    An agent quotes $29/seat against a price list; the judge checks the quote matches exactly.

    everyai-com · Tools & apps

  4. 0570

    Refund chat: agent stated the amount before issuing it

    A support agent issues a $42.50 refund; the judge checks the exact amount was stated before the refund was confirmed.

    everyai-com · Tools & apps