What problem does it solve? Orchestrating an autonomous coding agent from a terminal requires handling interactive prompts, permission dialogs, session state, and output formats. This Skill provides the operational knowledge to drive the Claude Code CLI reliably for features, refactors, code reviews, and PR workflows without manual babysitting. ## Core Features & Use Cases - Print Mode Automation: Run one-shot non-interactive tasks with claude -p, structured JSON output, JSON-schema extraction, piped input, and session resumption for CI/CD pipelines. - Interactive PTY Orchestration: Drive multi-turn Claude Code sessions through tmux, including handling workspace trust and permissions dialogs, monitoring progress via pane capture, and sending follow-up prompts. - Parallel & PR Workflows: Launch multiple independent Claude instances in parallel tmux sessions, review PRs via --from-pr or piped diffs, and isolate work in git worktrees. - Use Case: Pipe git diff main...feature-branch into claude -p to get an automated code review, or spawn three 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.