vigiles
Audit, test, and measure Claude Code agent skills and hooks
Visit vigiles.sh ↗What is vigiles?
vigiles is a CLI tool that verifies agent harnesses by grading skills, hooks, and subagents for correctness and safety. It checks whether your CLAUDE.md configuration is real—that tools exist, events are valid, and linter rules match your config—then runs deterministic audits without uploading code or requiring API keys.
Designed for developers building with Claude Code, vigiles measures whether skills actually fire using recall and precision metrics. It catches false confidence (guards that look functional but silently fail), flags safety issues like prompt injection risks, and integrates with your local linter rules across JavaScript, Python, Rust, Ruby, JVM, and Go. The maker built it with Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered vigiles automatically. Evidence: GitHub zernie/vigiles; repo has .claude, CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients