Single source of truth for AI coding agent configuration — skills, commands and rules shared across OpenCode and Pi.

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

A reusable agent workflow kit with personas, skills, rules, and memory files.

A ruleset that turns AI coding assistants (e.g. Claude Code) into disciplined Linux, FreeBSD & macOS sysadmins. Manages servers via SSH and localhost with safety guardrails, checklists, and team support. Named after the Heinzelmännchen — helpful kobolds who do the housework while you sleep.

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate.

A practical, no-hype workflow for AI coding agents: context, plan, implement, review, QA, ship, retro. Templates, two Claude Code skills, and a 40% context rule - every claim traced to official docs.

Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.

Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation

Agentic game development taken to the next level: plan, build and test across major engines with any coding agent🤖

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development