WANTKYY/hardstop
🛑 Stop dangerous commands and credential reads with Hardstop, a safety layer that protects your system from AI errors.
🛑 Stop dangerous commands and credential reads with Hardstop, a safety layer that protects your system from AI errors.
npx add-skill WANTKYY/hardstop🛑 Stop dangerous commands and credential reads with Hardstop, a safety layer that protects your system from AI errors.
Connect Claude Code to WeChat for terminal chat, with QR login and long-poll WeChat iLink Bot support
Agent-compatible AI automation repository.
🤖 Define Artificial Superintelligence with a focus on behavioral coherence, ensuring reliable evaluation and safety in real-world applications.
A Claude Code skill bundle for bug hunting and external red-team work - 51 skills, 15 slash commands, 574+ disclosed-report patterns curated across 24 vulnerability classes, plus enterprise identity + infrastructure attack matrices.
Store Claude Code memory in files for persistent context across sessions, projects, and devices without a database or cloud
Agent skill repository for AI-assisted workflows.