This is a public open-source repo: all repo artifacts are English, always — commit messages, CHANGELOG entries, PR titles/bodies, code comments, and docs. This OVERRIDES the global ~/.claude/CLAUDE.md Korean-commit/comment convention for this repository. New code comments are written in English; do not mass-rewrite existing Korean comments (respect the "don't improve adjacent code" rule), just stop adding new Korean ones. Chat/reports with the owner may stay Korean. Always read DESIGN.md before making any visual or UI decisions. All chrome/layout contracts, color…
A macOS menu bar app that monitors Claude / Codex subscription usage. Swift + SwiftUI + AppKit, targeting macOS 13+. - App/: entry point, MenuBarManager (coordinates UI and data), icon rendering (MenuBarIconRenderer/ShapeIconRenderer) - Services/: ClaudeAPIService (cookie and OAuth dual paths), CodexAPIService (two-step auth), OAuthTokenCache (actor: token caching + refresh single-flight), KeychainManager (uses UserDefaults in DEBUG!), OAuth/ (PKCE + local callback server) - Models/: UserSettings is the settings facade; accounts/refresh policy/launch-at-login/appearance have been split out into AccountStore/SmartRefreshPolicy/LaunchAtLoginManager/AppearanceManager - Helpers/DataRefreshManager.swift: scheduled refresh,…
Agent Viewer is a web-based kanban board for managing multiple Claude Code AI agents running in tmux sessions. It provides a central UI to spawn, monitor, message, and clean up…
New here? Start with the root README — it covers what Nudgebee is, how to bring up a local stack, and the per-service entry points. This file (CLAUDE.md) is primarily…
Read CONTRIBUTING.md — that is the canonical guide for working in this repository. Human contributors and AI agents follow the same rules. The previous content of this file (working agreement, parity standing rule, verification commands, ShareOne publishing recipe, documentation map) has been migrated into CONTRIBUTING.md so the rules apply to every contributor by default, not just to Claude. This file remains as a thin pointer because Claude Code reads it on startup by convention; the pointer ensures the agent finds…
You are operating as part of Sutando — a personal AI agent that belongs entirely to the user. This is the Sutando implementation overview. You are Sutando's task execution engine. Handle anything delegated: research, writing, email, scheduling, code, financial tasks, web browsing, file management, content creation. Complete tasks the way the user would — match their voice and working style. For irreversible actions (sending email, deleting files, financial transactions), confirm before executing unless standing approval has been given. Be concise…
Blueprint keeps shared repository policy in AGENTS.md and only Claude-specific setup here. Install Blueprint with npx skills add owainlewis/blueprint. Use /architecture, /design, /architecture-review, /plan, /test, /review, and /improve for one kind of engineering work. Use /task-to-pr to deliver one or more code changes. Use /codex-issue-coordinator only in Codex to coordinate a large GitHub issue batch through separate worker threads and gated merges. Everything you call in Blueprint is a skill. /task-to-pr accepts tasks, tickets, pull requests, or a milestone and…
Qual is a Tauri 2 desktop application for B2B lead research and qualification. It uses Claude CLI as an AI backend for company/person research, scoring, and conversation generation. Research/scoring jobs spawn Claude CLI subprocesses: Location: ~/.local/share/qual/data.db Tables: leads, people, prompts, scoringconfig, leadscores
Adaptive Technical Learning and Architecture System Software Engineer Entity. Solution Architect. Software Architect. Tech Lead. I carry FAANG experience for scale and quality, and startup experience for pragmatism and shipping…
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
openwong2kimCLAUDE.md
