Exhaustive multi-dimensional project auditor covering code, runtime, infrastructure, security, performance, business logic, and human processes across 12 dimensions with confidence-tracked findings and explicit blind spot documentation. Includes dead code detection (Knip/depcheck), file size/token limit analysis for AI editing compatibility, and honest system health reporting.
Exhaustive multi-dimensional project auditor covering code, runtime, infrastructure, security, performance, business logic, and human processes across 12 dimensions with confidence-tracked findings and explicit blind spot documentation. Includes dead code detection (Knip/depcheck), file size/token limit analysis for AI editing compatibility, and honest system health reporting.
keywords
audit, code quality, dead code, unused files, unused exports, unused dependencies, file size, token limit, system health, performance, security, documentation, test coverage, accessibility
triggers
audit my project, check code health, dead code detection, find unused code, file too large, system status, comprehensive audit, codebase health
Comprehensive Honest Project Auditor - Maximum Coverage Edition
Overview
An exhaustive multi-dimensional project auditor that covers code, runtime behavior, infrastructure, security, performance, business logic, and human processes. Provides confidence-tracked findings across 12 audit dimensions with explicit blind spot documentation.
Quick Start
Natural Language Commands:
"Run comprehensive audit on my project"
"Audit my code for security and performance issues"
"Check my documentation accuracy and test coverage"
"Analyze my project's blind spots and confidence levels"
# Full audit (dry-run by default)
node .claude/skills/📊\ comprehensive-auditor/scripts/orchestrator.js audit
# Execute safe removals only
node .claude/skills/📊\ comprehensive-auditor/scripts/orchestrator.js execute --safe-only
# Single detector
node .claude/skills/📊\ comprehensive-auditor/scripts/orchestrator.js detect --detector file-size
# CI mode
node .claude/skills/📊\ comprehensive-auditor/scripts/orchestrator.js audit --ci
File Size & Token Limit Detection
Detects files that exceed token limits for AI editing tools like Claude Code.
Why this matters: Files over ~25,000 tokens become difficult or impossible for AI tools to edit effectively, causing truncation, context loss, and failed edits.
performance_benchmarks.md - Performance standards and thresholds
business_logic_rules.md - Common business rule patterns
assets/
config_schemas/ - JSON schemas for configuration validation
report_templates/ - Template system for different report formats
threshold_definitions/ - Default thresholds and benchmarks
Integration with Existing Tools
This auditor integrates seamlessly with:
Document Sync Skill - For documentation accuracy verification
QA Testing - For test coverage and quality analysis
Security Scanner - For vulnerability detection
Performance Profiler - For runtime performance analysis
Safety and Performance
Parallel Execution - All dimensions run concurrently for speed
Incremental Mode - Only scan changed files for quick updates
Configurable Depth - Adjust analysis depth based on time constraints
Memory Efficient - Streaming analysis for large codebases
Non-Destructive - Read-only analysis, never modifies code
This is as comprehensive as technically possible while remaining honest about limitations.
MANDATORY USER VERIFICATION REQUIREMENT
Policy: No Fix Claims Without User Confirmation
CRITICAL: Before claiming ANY issue, bug, or problem is "fixed", "resolved", "working", or "complete", the following verification protocol is MANDATORY:
Step 1: Technical Verification
Run all relevant tests (build, type-check, unit tests)
Verify no console errors
Take screenshots/evidence of the fix
Step 2: User Verification Request
REQUIRED: Use the AskUserQuestion tool to explicitly ask the user to verify the fix:
"I've implemented [description of fix]. Before I mark this as complete, please verify:
1. [Specific thing to check #1]
2. [Specific thing to check #2]
3. Does this fix the issue you were experiencing?
Please confirm the fix works as expected, or let me know what's still not working."
Step 3: Wait for User Confirmation
DO NOT proceed with claims of success until user responds
DO NOT mark tasks as "completed" without user confirmation
DO NOT use phrases like "fixed", "resolved", "working" without user verification
Step 4: Handle User Feedback
If user confirms: Document the fix and mark as complete
If user reports issues: Continue debugging, repeat verification cycle
Prohibited Actions (Without User Verification)
Claiming a bug is "fixed"
Stating functionality is "working"
Marking issues as "resolved"
Declaring features as "complete"
Any success claims about fixes
Required Evidence Before User Verification Request
Technical tests passing
Visual confirmation via Playwright/screenshots
Specific test scenarios executed
Clear description of what was changed
Remember: The user is the final authority on whether something is fixed. No exceptions.