What problem does it solve? Coordinating multiple coding agents and terminal processes across panes, tabs, and workspaces is error-prone without a structured control interface. This Skill teaches an agent how to safely inspect and control a Herdr terminal multiplexer session through its CLI, avoiding common mistakes like targeting the wrong pane or misreading agent lifecycle states. ## Core Features & Use Cases - Session Discovery: List workspaces, tabs, panes, and live agents, parsing stable IDs from JSON responses instead of guessing them. - Agent Coordination: Start named coding agents in available shell panes, submit prompts with lifecycle-aware waits, and read their output through the agent surface. - Command Execution: Run ordinary commands in sibling panes, wait for matching output, and read logs using the appropriate snapshot source. - Use Case: While working in a Herdr pane, ask the agent to spin up a reviewer agent in a split pane, prompt it to review the current diff, and report back only actionable findings once it reaches an idle state. ## Quick Start Ask the agent to use Herdr to split the current pane, start a reviewer agent, and have it review the current diff.