scanaislop/aislop

Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks, and more. 50+ deterministic rules across 10 language targets, with CLI, CI, and GitHub Actions. No LLM at runtime. MIT.

What it solves

AI coding agents often produce code that passes tests and linting but contains "slop"—patterns like narrative comments, hallucinated imports, dead code, and oversized functions that an experienced engineer would not write. aislop detects these patterns to prevent code rot in AI-assisted development.

How it works

It uses six deterministic engines (Formatting, Linting, Code Quality, AI Slop, Security, and Architecture) based on Regex, AST, and standard tooling. It does not use LLMs in its runtime path, ensuring that the same code always produces the same score. The tool scans code across 10 language targets (including TypeScript, Python, Go, Rust, and C#) and assigns a quality score from 0 to 100.

Who it’s for

Developers and teams using AI coding agents (such as Claude Code, Cursor, or Codex) who want to maintain high code quality standards and prevent AI-generated technical debt.

Highlights

  • Deterministic Scoring: Provides a 0-100 score without relying on LLMs or API calls.
  • Multi-language Support: Works across 10 different languages and frameworks.
  • Automated Fixes: Offers mechanical auto-fixes for issues like unused imports and dead code.
  • Agent Integration: Can be handed off to coding agents via prompts or integrated as an MCP server for tools like Claude Desktop and Cursor.
  • CI/CD Ready: Includes a quality gate that can fail builds if the score drops below a specified threshold.
  • Post-edit Hooks: Can install hooks that run after every agent edit to provide immediate feedback.

Related

  • Dispatch
    Combating AI Slop: A Deterministic Approach to AI-Generated Code Smells

    Explore aislop, a CLI tool designed to detect and fix common antipatterns left by AI coding agents without relying on LLMs for the analysis.

  • Project
    yetone/kill-ai-slop

    A tool and field guide designed to identify and remove generic, AI-generated design patterns (AI slop) from web projects.

  • Project
    Nutlope/hallmark

    A design skill for AI coding assistants that uses a rigorous anti-pattern rule-set and 21 themes to create professional UI that avoids the generic AI-generated look.

  • Project
    berelevant-ai/slopless

    A deterministic linter and textlint preset that flags common LLM writing patterns (AI-slop) so writing agents can iteratively rewrite text to sound more human.

  • Project
    agiwhitelist/auteur

    An AI agent skill that directs the creation of cinematic, high-performance websites using a disciplined pipeline of art direction, asset generation, and strict anti-slop linting.