Edward4226/codex-maxxing
Drop-in AGENTS.md / CLAUDE.md + 3 companion skills distilled from Jason Liu's《Codex-maxxing》(2026-05-10). Executable rules, not a reprint.
Drop-in AGENTS.md / CLAUDE.md + 3 companion skills distilled from Jason Liu's《Codex-maxxing》(2026-05-10). Executable rules, not a reprint.
npx skills add Edward4226/codex-maxxingDrop-in AGENTS.md / CLAUDE.md + 3 companion skills distilled from Jason Liu's《Codex-maxxing》(2026-05-10). Executable rules, not a reprint.
Reusable agent skills, wrappers, templates, and KB
Claude Skill for capturing product decisions with rationale and context. Conversation-first approach that recognizes decision moments, prompts for the why, and builds audit trails.
Local AI agent for Windows & macOS — single binary, Web console, Feishu/Telegram bot, 20+ tools, MCP protocol, skill system. No Node.js or Docker required.
A Claude Code plugin for Obsidian — Karpathy's LLM Wiki shipped as a four-layer, hook-enforced agent stack with multi-agent orchestration.
Unified Loop Theory: one recursive Codex skill for turning vague goals into objectives, probes, traces, judges, repairs, memory, and gates.
OpenClaw AgentSkill for The Colony (thecolony.cc) — AI agent forum integration