Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Clean Code Judge

PR reviewer where Jev answers a Clean Code question set for every changed file and a writing model turns the verdicts into review prose.

Servicebeta
View on GitHub ↗

Overview

Clean Code Review takes a public GitHub pull request, a diff or a file and has Jev answer a question set drawn from Robert C. Martin's Clean Code for every code file in the change; Luna, a writing model, then writes the review from those answers. Per the listing, each file is scored on 31 boolean code smells plus function size and nesting.

It runs on eve and deploys as one Next.js project, calling Jev through Vercel's AI Gateway with one evaluate() call per file in parallel. Reviews have permalinks, files and diff hunks are editable with re-judging of only the changed file, and terminal commands can judge presets or stream reviews. A hosted version is live. It needs Bun, Node 24 and a Vercel account.

What the decision model decides

TypeQuestionAnswers
Yes / noDoes this file show a given Clean Code smell? (31 boolean checks)yes · no
ScoreHow large are functions / how deep is nesting?—

How it works

  1. Fetch the PR, diff or file
  2. Jev answers the question set per file in parallel
  3. Writing model composes the review from verdicts
  4. Show results with a permalink

Strengths

  • Per-file, structured verdicts
  • Edits re-judge only changed files
  • Permalinks for sharing

Caveats

  • Clean Code rules are opinionated
  • Requires Vercel AI Gateway

Getting started

bun install, bunx eve link --non-interactive --project, then bun run dev

At a glance

Type
Service
Status
beta
Language
TypeScript
Runtime
Next.js + eve (Bun, Node 24)
Has code
yes

Use cases and integrations

How curated lists describe it

  • Code quality: scores every file of a pull request on 31 boolean Clean Code smells plus function size and nesting, then hands the verdicts to a writing model for the review prose.

    yibie/awesome-jev

  • Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

    hellogumbo/awesome-jev

  • Reviews every code file in a pull request against a question set drawn from *Clean Code*: Jev answers, Luna writes the review. Runs on eve with Jev through Vercel's AI Gateway; a hosted version is live.

    MrJev/awesome-jev

Frequently asked questions

Who writes the review text?

Luna, a writing model, from Jev's verdicts.

What does Jev check?

Clean Code smells and function size and nesting per file.

Can I run it from a terminal?

Yes, with bun run judge or bun run review.

Related projects

  • Supercov★ 154

    Coverage, security and quality CLI where Jev answers yes/no property questions per file so agents know what to fix first.

    CLIproductionRust
  • JevGate

    Rust code-review gate asking Jev small typed questions about functions and tests, failing CI only on rules measured 80% right.

    CLIproductionRust
  • Abide

    Coding-agent hook that asks Jev one yes/no per project rule on every edit or turn and makes the agent fix any violation.

    HookbetaTypeScript
  • code-quality

    Advisor for coding agents: git and Stop hooks flag test tampering, secrets and skipped hooks, with optional Jev review findings.

    Hookbeta
  • jeff (Alurith)

    Read-only Go CLI that checks files against your plain-language code rules with Jev, locally or in CI.

    CLIbetaGo
  • jev-codes

    CLI and agent commands auditing a git diff against YAML standards packs, scoring each hunk with Jev so agents fix only flags.

    Agent skillbetaTypeScript