Evil-Bane/argus
The all-seeing, multi-agent, vision-verified auditor for Claude Code. Tests every control for real, adversarially verifies, ranks fixes. Ships /customer-audit and /overnight.
The all-seeing, multi-agent, vision-verified auditor for Claude Code. Tests every control for real, adversarially verifies, ranks fixes. Ships /customer-audit and /overnight.
npx add-skill Evil-Bane/argusThe all-seeing, multi-agent, vision-verified auditor for Claude Code. Tests every control for real, adversarially verifies, ranks fixes. Ships /customer-audit and /overnight.
Tier-1 strategy-consultant frameworks (MECE, Issue Trees, Hypothesis-Driven, Pareto, So What?) packaged as Claude Skills + LLM-agnostic prompts. Drop in any LLM and get whiteboard-style structured analysis. Adapted from Analyst Academy on YouTube.
Codex Skill for setting up Ubuntu VMs that can be controlled from the ChatGPT/Codex mobile app
Open source Claude Code plugin — 52 invisible engineering skills turn vibe coding into production-ready software. Auto specs, TDD, security hooks, quality gates, self-improving retrospective. 97% vs 41% on blind benchmark.
Lionclaw is a local control plane for AI coding agents. It runs AI agents as durable, auditable workers with explicit state, skills, channels, schedules, and bounded permissions.
🛑 Stop dangerous commands and credential reads with Hardstop, a safety layer that protects your system from AI errors.
MCP (Model Context Protocol) server for HawkAPI — auto-exports routes as agent tools