What problem does it solve? Orchestrating an autonomous coding agent from a terminal requires handling interactive prompts, permission dialogs, session state, and output formats, which is error-prone when done manually. ## Core Features & Use Cases - Print Mode Automation: Run one-shot coding tasks with claude -p, structured JSON output, JSON schema extraction, piped input, and session resumption. - Interactive PTY Orchestration: Drive multi-turn Claude Code sessions through tmux, including workspace trust and permissions dialog handling. - Configuration & Extensibility: Covers CLI flags, settings hierarchy, CLAUDE.md memory files, custom subagents, hooks, MCP server integration, and parallel instances. - Use Case: Pipe a git diff into claude -p to get an automated PR review, or spawn parallel tmux sessions to fix a bug, write tests, and update docs simultaneously. ## Quick Start Ask the agent to run claude -p with your coding task, an allowedTools list, and a max-turns limit in your project directory.