ls-agent

Use when closing a herdr workspace or worktree. Confirms nothing in the checkout would be lost, then removes the worktree and closes the workspace.

Use when work belongs somewhere other than this session (a different repository, a standing personal agent, or a visual design tool), or before creating or changing a skill, to decide where it lives.

Use at the start of any task, before taking action, to load the always-on workflow rules covering skill invocation, communication, skill scripts, and the conventions of the environment the session is running in.

Invoke after the agent has stopped, whether the user interrupted it or it paused on its own, to have it resume and stop asking for permission it doesn't need for the rest of the conversation.

Use when a task needs its own checkout of a project — delegating work to another agent, or starting a branch that should run alongside the current one — and a herdr workspace has to be opened for it.

Use when a session's job is to hand work out to other agents rather than do it — running a set of tasks across several projects or worktrees, a few at a time.

Use when several tasks are going out to separate agents at once and the work needs splitting into what can run simultaneously and what has to wait, before any of it is kicked off.

Use when instructed to create a plan (feature, bug fix, or refactor).

Invoke when the conversation has drifted onto a tangent that deserves its own agent, so the tangent can be handed off and the main thread can get back on track.

Invoke when the agent's conversational replies have gotten too long or wordy and the user wants shorter answers for the rest of the conversation.

Use when working in a vibe-coded repository, where the user never reads the code and only runs the product and gives feedback, or when the user wants to start building a project that way.