Skip to content

AI Code Smell Detector

Scan code for AI-generated anti-patterns: hallucinated imports, over-abstraction, verbose error handling, redundancy, security smells and AI tells.

AI Code Smell Detector

7 findings, score 60 out of 100

Score60/100
7 findings3 high4 medium
TypeScript detected

Findings (7)

mediumHallucinated ImportsL2

Generic import path

Import from a suspiciously generic relative path that may be hallucinated.

import { merge } from "./utils/helpers";
highHallucinated ImportsL3

Suspicious package import

"smart-parser" is a commonly hallucinated npm package that does not exist.

import { parse } from "smart-parser";
mediumOver-AbstractionL8

Pass-through wrapper

Function "getSettings" appears to just wrap another function call.

function getSettings(userId: string) {
highVerbose Error HandlingL16

Empty catch block

Silently swallowing errors hides bugs.

} catch (err) {}
highAI TellsL1

Conversational comment

Comment contains AI assistant language (certainly, I'll help, etc.).

// Certainly! Here's a helper to load user settings.
mediumAI TellsL5

Numbered step comment

Numbered step comments (Step 1, Step 2...) are a strong AI-generation tell.

// Step 1: Initialize the config
mediumRedundancyL16

Dead code after return

This code is unreachable because it follows a return statement.

} catch (err) {}

Updated . Provided as is. Check the output before you rely on it in production.

How to use AI Code Smell Detector

  1. 1

    Paste your code

    Enter or paste any code snippet into the input area. The tool auto-detects the programming language from syntax patterns (JavaScript, TypeScript, Python, Go, Rust, or Java).

  2. 2

    Review detected smells

    The analysis runs automatically and displays findings grouped by category — hallucinated imports, over-abstraction, verbose error handling, AI tells, security smells, and redundancy — each with a severity badge.

  3. 3

    Read the overall score

    Check the overall code quality score (0-100). Scores above 80 indicate clean code, 50-80 suggests some AI-generated patterns to clean up, and below 50 flags significant issues.

  4. 4

    Copy the report

    Click Copy Report to get a markdown summary of all findings with line references and fix suggestions, ready to paste into a PR comment or code review.

Questions and answers

What is AI Code Smell Detector?
AI code smells are patterns code assistants tend to leave behind: imports of packages that do not exist, needless wrappers, catch-and-log error handling, step-numbered comments. This detector checks JS, TS, Python, Go, Rust or Java with heuristic rules in six categories and gives a scored report by line.
How does detection work without an AI model?
The tool uses 30+ heuristic pattern matchers (regex and structural analysis) to identify known AI code smells. No LLM API calls are made — all analysis happens deterministically in your browser.
Does it send my code to a server?
No. All analysis happens entirely in your browser. Your code never leaves your device.
What languages are supported?
JavaScript, TypeScript, Python, Go, Rust, and Java. The tool auto-detects the language from syntax patterns.
For AI agents: how to call this tool

Machine-readable contract, endpoints and examples. Humans can ignore this section.

Best Path For Builders

Browser workflow

Runs instantly in the browser with private local processing and copy/export-ready output.

Browser Workflow

This tool is optimized for instant in-browser execution with local data handling. Run it here and copy/export the output directly.

/ai-code-smell-detector/

For automation planning, fetch the canonical contract at /api/tool/ai-code-smell-detector.json.