A Claude Code skill that tells Claude when not to use Claude
Traffic-light audit system beats vague 'optimize your LLM spend' advice from competitors.
Audit & observability for your agent skills — usage heat, doctor with fixes, relationship graph
Flutter doctor for Claude skills with live-refresh TUI and relationship graphs.
Claude Code users and AI agent developers
Traffic-light audit system beats vague 'optimize your LLM spend' advice from competitors.
Real-time cost tracking for Claude Code sessions; saves money intuition before you ship.
ARC framework grades DevOps health but it's still a Claude Code skill wrapper.
LLM-on-LLM scanning catches obfuscation and semantic attacks before skills execute.
Persistent memory across sessions lets it remember what you tried six months ago.
Seccomp+iptables+mount isolation blocks the ClawdHub credential stealer in practice.