{
  "markdown": "# Overview\n\"Code Slob\" refers to the subtle technical debt, unnecessary verbosity, and over-complexity often introduced by AI coding agents or rapid development. While functional, \"slob\" code is harder to maintain and prone to future regressions. The **Code Slob Cleanup** project builds an automated toolchain—packaged as a coding agent skill—to identify, refactor, and rigorously verify Python code to remove this debt.\n\nCurrently, the project only supports python codebases.\n\n# Installation\n\nLinux/Mac Auto Install/Uninstall/Update for Gemini/Claude/Codex:\n```bash\ncurl -LsSf https://raw.githubusercontent.com/Jazz23/CodeSlobCleanup/refs/heads/main/install.sh | sh\n```\n\nGemini CLI:\n```bash\ngemini extensions install https://github.com/Jazz23/CodeSlobCleanup\n```\n\n# How to use\n\nClick [here](https://jazz23.github.io/CodeSlobCleanup/) for a guide on how to use Code Slob Cleanup.\n\n# Core Objectives\n1.  **Automated Identification**: Detect refactoring targets using static analysis metrics (Cyclomatic Complexity, LoC, nesting depth) and semantic analysis via the agent to identify redundant logic.\n2.  **Safe Refactoring**: Employs your agent to perform code transformations such as function decomposition, visibility enforcement (Converting public to private), and dead code removal.\n3.  **Rigorous Verification**: Ensure behavioral equivalence using **Property-Based Testing**: Leveraging **Hypothesis** to verify `Original(input) == Transformed(input)` across thousands of inputs.\n4.  **Autonomous Self-Correction**: Integrate verification feedback directly into the refactoring loop, allowing the agent to \"fix its own fixes\" based on counter-examples found during testing.\n\n# Architecture\nThe system follows an iterative loop:\n*   **Scanner**: Traverses the codebase and finds code slob.\n*   **Refactor Agent**: Analyzes flagged code and generates a cleaned-up version.\n*   **Verifier**: An isolated orchestrator executes Hypothesis tests, and benchmarks performance.\n*   **Feedback Loop**: If verification fails, the failing test cases are fed back to your agent for a retry.\n*   **Committer**: Applies the change if verification passes and performance is not regressed.\n\n# Technologies\n*   **Language**: Python 3.14+\n*   **Package Management**: `uv` (PEP 723 for standalone scripts)\n*   **Testing**: Hypothesis (Property-based), Pytest\n*   **Benchmarking**: Matplotlib/Numpy for performance comparison\n",
  "bytes": 2411,
  "sha": "1d99d93e89553a93ffeaff47cb5f4438fd8e2cf8f33480aa439d9aac56bc688a",
  "repo_slug": "jazz23/codeslobcleanup",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_jazz23_codeslobcleanup_b8fba6f4/readme"
}