Claude Code plugin to bootstrap and govern AI agent architectures (Claude Code, Cursor, Codex) — roles, task lifecycle, local auditing, and a secrets anti-leak guardrail.
A Codex and Claude Code plugin that reads your repository, settles decisions through native question forms, then implements and verifies the agreed result.
Behavior discipline for coding agents: read-before-write enforcement, failure convergence, write verification with auto-rollback, and a high-risk command gate. Ships FULL plugin/hook adapters for DSH, Claude Code, Codex, and Pi, plus a host-agnostic SOFT skill with ADAPTIVE adapter guidance.
Laravel AI skills that actually know when to stay out of the way. 72 focused skills, smarter sparse routing, automatic project memory, and better specialist selection for Codex, Claude Code, and other AI coding assistants.
Comprehensive R analytics skill for Claude Code with 93 package-level skills covering data manipulation, visualization, machine learning, web development, spatial analysis, and more.