cleancode

Use this agent after writing or editing code to silently review it for clean code violations. This agent runs non-blocking — it never refuses or rewrites, only appends suggestions. Use this agent when Claude has just written, edited, or generated code in any file; when a code change has been completed and the user hasn't explicitly asked for a review; or when code contains visible quality concerns like long functions, deep nesting, or missing interfaces. <example> Context: Claude just wrote a 60-line function to handle user registration in TypeScript. user: "Add a user registration function to auth.ts" assistant: "I've added the registerUser function to auth.ts. Let me have the cleancode-reviewer check this." <commentary> Claude just wrote code — the cleancode-reviewer should automatically scan it for violations (function is too long at 60 lines, may be missing an interface) and append non-blocking suggestions. </commentary> </example> <example> Context: Claude edited an existing file that is now approaching the 300-line limit. user: "Add error handling to the payment processor" assistant: "I've added error handling to paymentProcessor.ts. Running a quick clean code check..." <commentary> A file edit was completed. The reviewer should flag if the file is now approaching or over the 300-line limit and suggest splitting. </commentary> </example> <example> Context: User asks Claude to generate a new service class without specifying clean code requirements. user: "Create a UserService class that handles CRUD operations" assistant: "I'll create the UserService. Before finishing — let me check this against clean code standards." <commentary> New code was generated. Reviewer checks: does the class have an interface? Is each method under 40 lines? Does the class do one thing? </commentary> </example> <example> Context: Claude helped refactor a Python module. user: "Refactor the data processing module to be more efficient" assistant: "I've refactored dataProcessor.py. Cleancode review appended below." <commentary> After a refactor, reviewer verifies the result still meets clean code standards — checking function lengths, naming, and nesting in the updated file. </commentary> </example>

This skill should be used when the user asks to "analyze this file", "check this code", "scan for violations", "find clean code issues", "review code quality", "check file length", "audit this project", "what's wrong with this code", or when a file looks messy or overly long. Scans files for clean code violations and outputs a grouped report of critical issues, warnings, and style suggestions.

This skill should be used when the user asks to "fix everything", "fix all violations", "clean this up", "auto-fix", "apply all fixes", "clean my code", "fix the whole project", or wants a one-shot fixer that runs every cleancode fixer in order across the codebase. Orchestrates analyze + each fixer skill (safety, untangle, test, refactor) in severity order across every source file, produces a full project-wide plan, asks for confirmation, and applies fixes.

This skill should be used when the user asks for "project health", "code health", "clean code score", "cleanliness score", "how bad is my code", "show metrics", "code quality dashboard", or wants a top-level view of the codebase's cleanliness. Produces a read-only dashboard of violation counts, worst offenders, and a 0-100 cleanliness score. Read-only by design — for fixing, use the specific skills.

This skill should be used when the user asks to "set up clean code rules", "initialize clean code", "init cleancode", "add clean code to this project", "set up code standards", "configure clean code rules", or when a new project is opened and no .cleancode-rules.md file exists. Generates the canonical ruleset and platform config files so all AI assistants follow clean code throughout the project.

This skill should be used when the user asks to "refactor this file", "clean up this code", "extract this function", "break this function apart", "pull this out into a method", "simplify this switch", "turn this into a table", "inline this", "replace magic number", or mentions a specific refactoring by name. Applies one named, surgical refactoring from the textbook catalog (Extract Method, Table-Driven, Replace Conditional with Polymorphism, etc.) and shows exactly what changed.

2 hooks across 2 events