A senior developer's code review for AI-generated projects. Scans codebases for structural mess, code quality issues, and AI artifacts - then reports or automatically fixes them.
Scans codebases for AI-generated junk, structural mess, and code quality issues that linters miss.
/plugin marketplace add willmarkman/vibe-janitor/plugin install willmarkman-vibe-janitor@willmarkman/vibe-janitorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
detectors/ai-artifact-detector.mddetectors/code-quality-detector.mddetectors/structural-detector.mdmodes/auto-fix-mode.mdmodes/interactive-mode.mdmodes/report-mode.mdreferences/config-schema.mdreferences/severity-rules.mdreferences/types.mdscanner-skill.mdA senior developer's code review for AI-generated projects. Scans codebases for structural mess, code quality issues, and AI artifacts - then reports or automatically fixes them.
What it does: Finds the junk that linters miss - hardcoded secrets, orphaned files, debug artifacts, placeholder content, skeleton code. The issues that require understanding intent, not just syntax.
Load these for type definitions and rules:
Load based on scan scope:
For full codebase scanning with orchestration:
To scan a codebase:
1. Load @skills/vibe-janitor/scanner-skill.md
2. Run the scanning process steps
3. Review ScanResult output
For specific detection only:
1. Load the relevant detector (structural/code-quality/ai-artifact)
2. Run patterns against target files
3. Collect Issue objects
| Level | Meaning | Examples |
|---|---|---|
| Critical | Must fix before shipping | Hardcoded secrets, exposed credentials, broken imports |
| Warning | Should fix | Debug artifacts, dead code, empty catch blocks |
| Info | Nice to fix | Stale TODOs, lorem ipsum, minor naming issues |
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.