What problem does it solve? Orchestrating an autonomous coding agent from another AI agent or automation pipeline requires knowing the exact CLI flags, output formats, and interactive dialog handling of Claude Code, which are easy to get wrong and cause hung sessions or runaway costs. ## Core Features & Use Cases - Print Mode Automation: Run one-shot non-interactive tasks with claude -p, structured JSON output, JSON schema extraction, session resumption, and cost caps via --max-turns and --max-budget-usd. - Interactive PTY Orchestration: Drive multi-turn Claude Code sessions through tmux, including handling the workspace trust and permissions-bypass confirmation dialogs with send-keys sequences. - Full CLI Reference: Covers subcommands, permission flags, hooks, MCP server configuration, custom subagents, slash commands, keyboard shortcuts, and CLAUDE.md memory hierarchy. - Use Case: From a CI pipeline, pipe a git diff into claude -p to get an automated code review as structured JSON, then resume that session later to request fixes. ## Quick Start Ask the agent to run a one-shot Claude Code task such as fixing a bug in a specific file using print mode with a turn limit and restricted allowed tools.