マネーフォワードMeを自動化、保有資産の可視化を行います

A shareable config preset for Renovate used in Hatena.

Use Claude Agent SDK from any ACP client

An MCP to ACP (Agent Client Protocol) Bridge

LSP plugins for Claude Code — Bash/Shell, C/C++/Objective-C, C#, Clojure, Dart/Flutter, Elixir, Gleam, Go, Java, Kotlin, Lua, Nix, OCaml, PHP, Python, Ruby, Rust, Swift, Terraform, TypeScript/JavaS…

A tool/library for measurement of "C"ognitive "C"omplexity and "C"yclomatic "C"omplexity

Multithreaded PNG optimizer written in Rust

🛡️ A GitHub Action to run ghasec, a security linter for GitHub Actions workflows.

🫴 Catch security risks in your GitHub Actions workflows.

Local usage, cost, quota, and attribution dashboard for Codex and Claude Code.

Claude Fable as an orchestrator for Opus, GPT and Grok

Token-efficiency analyzer for AI coding agents (Claude Code, OpenAI Codex CLI): cost estimates, cache analysis, and savings advice. Zero dependencies.

Claude Code plugin: preserve and restore working state around /compact

The menu bar manager for macOS

A free, open-source native macOS app for Docker & Linux containers, an alternative to OrbStack and Docker Desktop. Universal for Intel and Apple silicon.

Tree-sitter grammar for Dart

Run once. Reuse everywhere.

Docker-compatible REST API on top of Apple container

Local CI. Sign off on your own work.

Run commands concurrently

A docker-compose like tool for Apple Container

Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.

一款用于安装 IPA 历史版本的工具，适用于获取旧版应用并自动捕获数据包。下载后，可直接通过 AirDrop 传输至 iPhone、iPad 上并安装并使用。

Skills for coding agents

OpenAI-compatible API proxy for Apple Foundation Models (fm CLI) on macOS 27

Claude Code / Codex CLI plugin for generating reviewable HTML documents with preview, inline review comments, and agent feedback ingestion.

Swift TrueType Interpreter

Xcode 27 beta 4 system prompts and internal documentation

Policy-driven, layered isolation and containment

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.