$ show Yeachan-Heo/oh-my-claudecode
Oh-My-ClaudeCode (OMC) is a multi-agent orchestration layer for Claude Code, Anthropic's AI coding assistant. It extends Claude Code with a plugin system, custom MCP tools, a team collaboration engine, a real-time HUD, and a rich hook system. The system is implemented in TypeScript and runs as a CLI tool (`omc`), an npm package (`oh-my-claude-sisyphus`), and a Claude Code plugin. It manages autonomous coding pipelines (autopilot, ralph), multi-worker team sessions via tmux, skill learning and injection, and provides extensive tooling including LSP integration, AST analysis, Python REPL, and git-based checkpoints. Architecturally, OMC is a modular monolith with clear separation: a CLI entry point (Commander-based), a hook registry with ~20+ lifecycle hooks (session-end, pre-tool-use, persistent-mode, etc.), a team subsystem with state machines and tmux-based worker management, a HUD rendering engine, and a standalone MCP server exposing 33+ tools. The system integrates with multiple AI providers (Claude, Codex, Gemini, Grok, Cursor) and git hosting providers (GitHub, GitLab, Azure DevOps, Bitbucket, Gitea). External dependencies include `@anthropic-ai/claude-agent-sdk`, `@modelcontextprotocol/sdk`, `better-sqlite3`, `zod`, and `commander`. Key data flows include: user input → CLI or Claude Code hook → hook dispatcher → feature modules (autopilot, team, skills) → tool execution → state persistence (filesystem, SQLite). The system maintains extensive state on disk (`.omc/state/`, session transcripts, team events, skill files) and uses file-based locking for concurrency safety. The JEV shadow judgment system provides non-blocking evaluation of heuristic decisions against an external API for quality monitoring. The codebase demonstrates strong engineering practices: extensive test coverage (~3000+ tests), modular architecture with clear interfaces, atomic file operations, and security-conscious utilities (SSRF guard, token redaction, path traversal prevention). It is actively maintained with frequent releases and responsive issue triage.
The LLM identified 4 files worth highlighting for reuse:
Provides cross-process file locking using O_EXCL create semantics with timeout, retry, and stale lock detection. The `withFileLockSync` function acquires a lock file, executes a callback, and releases the lock, ensuring atomic read-modify-write operations. Includes stale lock detection by checking process liveness via `/proc` (Linux) or `kill -0` (macOS). Reusable in any Node.js project needing safe concurrent file access without external dependencies.
Implements Server-Side Request Forgery (SSRF) protection by validating URLs against a blocklist of private IP ranges, dangerous protocols (file, ftp, gopher), and encoded bypass attempts. Uses IP address resolution and CIDR matching to block requests to internal networks. Includes credential stripping and hostname normalization. Reusable as a standalone utility in any service that fetches external URLs.
A lightweight parser for JSON with Comments (JSONC) that strips JavaScript-style comments (// and /* */) and trailing commas from JSON strings before parsing. Handles edge cases like comments inside strings and escaped characters. Reusable in any project that needs to parse configuration files with comments, without pulling in a full JSONC library.
Provides token redaction for notification messages, detecting and masking common secret patterns including Slack tokens, Telegram bot tokens, Bearer tokens, and generic API keys. Uses regex-based detection with configurable replacement strings. Reusable in any application that needs to sanitize logs or notifications before sending to external services.