v0.2.0 · no license
McKinsey-style PPTX generator — Claude Code plugin with 40 slide templates + subagent that picks the right template and defends its choice. Built by AX Labs (이승필).
v0.7.0 · MIT
確定申告自動化 AI エージェントプラグイン — 帳簿管理から e-Tax 入力代行まで
v2.1.3 · MIT
Keep Claude Code’s prompt cache warm during breaks and show the estimated cost before a cold send.
— · MIT
Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.
v0.2.0 · MIT
Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdown you own — a Claude Code skill.
v1.79.0 · MIT
Use Claude and Antigravity subscriptions with Pi, OpenCode and other coding clients. Local API bridge, usage dashboard and optional Mac app.
v6.12.19 · MIT
Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint: either plan answers either wire shape, with automatic fa
v4.2.10 · MIT
Your personal FDE in Claude and Codex. Understand the work, use the right tools, deliver and retain useful context. One entry: vibe.
— · MIT
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
v3.9.0 · MIT
🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.
— · Apache-2.0
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
v1.3.2 · MIT
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
— · MIT
One command to cut token usage by up to 50%+