Peon-ping is a cross-platform sound notification system for AI coding agents (Claude Code, Cursor, Codex, OpenCode, etc.). It intercepts agent lifecycle events (session start/stop, task complete, error, permission requests) via shell hooks and IDE-specific adapters, translates them into a standardized CESP (Coding Event Sound Pack Specification) JSON format, and plays themed sound effects with optional desktop notifications and TTS speech. The architecture is event-driven and hook-based: each IDE has a thin adapter script that pipes CESP events to a core hook script (`peon.sh` on Unix, `peon.ps1` on Windows) which performs sound selection from configurable packs, asynchronous audio playback via platform-native players, state persistence (atomic file I/O), and notification dispatch (macOS overlay, system notifications, relay for remote/SSH sessions). Additional features include a trainer (exercise reminders), an MCP server for agent-controlled sound playback, and a sound pack registry with 160+ packs. The codebase applies an adapter pattern, atomic state I/O, structured debug logging (ADR-002), and a path-rules-based pack resolution system. It is heavily tested with BATS (Unix) and Pester (Windows) suites, managed via an agent-based gitban workflow with sprint planning and code reviews. Dependencies include Python3, audio players (afplay, ffplay, pw-play, PowerShell MediaPlayer), and platform-specific notification tools. Key concerns are the monolithic hook scripts (single ~5000-line files per platform), cross-platform code duplication, and the maintenance burden of 20+ IDE adapters.