Urgent.News

What's breaking now, across thousands of outlets.

AI

I built a tool that roasts your code with regex — no AI involved

The problem In 2026, devs spend 11.4 hours a week reviewing AI-generated code — more time than they spend writing it. We're burning cycles fixing bugs our own AI tools wrote. I started calling this "AI debt": the maintainability tax that piles up when nobody's actually reading the code the assistant just spat out. I wanted a fast, brutal way to see how much debt was hiding in a file before I even…

In 2026, developers spend an estimated 11.4 hours per week reviewing AI-generated code, a task that consumes more time than the initial coding process itself. This phenomenon has given rise to the term "AI debt," referring to the maintainability challenges that accumulate when no one scrutinizes the code produced by AI tools. Recognizing this issue, a developer devised a tool called Roast My Code, which aims to provide a swift and straightforward means of assessing the maintainability debt embedded within a code snippet before it is submitted for review.

Roast My Code operates by allowing users to input a code snippet and subsequently receiving an AI Debt Score ranging from 0 to 100, along with constructive criticisms pinpointing specific areas for improvement. The assessment is performed using a collection of 118 regex patterns spanning eight programming languages, including JavaScript, Python, Go, Rust, Java, PHP, and C++.

These scores are categorized into five key areas: Readability, Structure, Error Handling, Safety, and Style. Each identified issue is accompanied by three brutal one-liner critiques and actionable remediation suggestions.

What sets Roast My Code apart is its reliance on client-side regex pattern matching, meaning it does not necessitate any server-side processing or external API integrations. Consequently, the entire analysis occurs within the user's browser, ensuring that the code remains confidential and does not traverse any network. This approach not only enhances security but also eliminates any latency or costs associated with API calls, resulting in instantaneous feedback upon submission.

The tool is designed primarily to serve as a preliminary sanity check, offering a quick glimpse into potential maintainability concerns rather than a comprehensive code review.

The ethos behind Roast My Code is firmly rooted in simplicity and efficiency, eschewing the complexity and potential pitfalls of AI-driven solutions. By avoiding reliance on large language models or backend services, the tool sidesteps unnecessary dependencies and provides an efficient alternative that is readily accessible and fast.

Users are encouraged to experiment with the tool by visiting the live application or accessing the source code, which is available on GitHub under the MIT license, inviting contributions and feedback.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

My Hook's Path Fix Passed Its Own Test. It Broke My README's Other Install Method.

Four days ago I fixed a bug in a git hook I wrote: hooks/prepare-commit-msg , which shells out to a small script ( git_commit.py ) that asks Claude to pre-fill a Conventional Commit message.

  • Bug fixed in git hook, script path corrected
  • README.md contains two install methods, fix only worked for one
  • Proposed solution uses git's rev-parse --show-toplevel command

Architecture Decisions Before Writing a Single Line

The most valuable thing Claude has done for my work is help me make better architectural decisions before I start building.

  • Claude provided architectural guidance for hotel reservation system
  • Multi-currency pricing and timezone conversion separated into services
  • 20-minute discussion improved critical thinking and system design

More from Tuesday 4 August →