Codebase analysis MCP server for AI agents: complexity metrics, size thresholds, prop drilling, and code smell detection built on tree-sitter and tokei.
Audits and tightens AGENTS.md / CLAUDE.md (and their @path imports) against Anthropic's Claude Code best practices (short, scannable, project-specific, free of derivable or stale content). Prunes and sharpens without inventing policy. Use when AGENTS.md has grown bloated, after adding a rule, or as a polish-pipeline…
Scans source files and fixes code comments; adds missing one-line JSDoc, improves existing JSDoc, and cleans up inline comments (WHY not WHAT, removes obvious or stale ones). Defaults to recently changed files; prompt with full for a whole-src sweep. Use when asked to clean up, fix, or standardize comments.
Audits all documentation against the actual codebase and fixes discrepancies in paths, tool names, parameters, npm scripts, versions, and code examples. Use after refactoring, feature additions/removals, or renames, or when documentation staleness is suspected.
Runs lint, typecheck, and prettier, then fixes all warnings and errors until every check passes. Use proactively after writing or modifying code and before commits.
Finds changed markdown files via git status and fixes all markdownlint warnings and table formatting. Use proactively after creating or modifying .md files and before commits.
Runs checks and tests, then fixes all warnings, errors, and failing tests, consulting recent git changes to decide whether the code under test or the test itself is wrong. Use proactively after code changes to confirm everything still passes.
Analyzes the codebase for coding-standards violations (file/function length, nesting depth, parameter counts, TODO/FIXME markers) using the scopewalker tools, then refactors to fix them while keeping checks and tests green. Use proactively after significant code changes or for a full standards audit.