espennilsen/pi / .pi/skills/herdr-operations
herdr-operations
VerifiedUse when inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or waits.
Herdr Operations
Inspect state before acting. Use the installed CLI help as the authority for the current version.
Safe discovery
herdr status
herdr session list --json
herdr workspace list
herdr pane list
herdr agent list
If one command fails, do not try invented alternatives. Run herdr --help, then the relevant command group's --help; if needed, use the upstream docs fallback.
Choose the right target
| Need | Use |
|---|---|
| Coding-agent state, output, or message | herdr agent … |
| Server, test, shell, or low-level terminal control | herdr pane … |
| Submit a shell command atomically | herdr pane run <pane_id> <command> |
| Read logs without soft wrapping | --source recent-unwrapped |
Common workflows
Inspect an agent, then use the installed agent-message command:
herdr agent list
herdr agent get <target>
herdr agent read <target> --source recent-unwrapped --lines 120
herdr agent --help
herdr agent <installed-message-command> <target> "<message>"
For example, documented releases have used agent send; newer releases may expose another message command. Use the spelling and argument order from local help.
Create an unfocused workspace or split pane so current work remains visible:
herdr workspace create --cwd <path> --label <label> --no-focus
herdr pane split <pane_id> --direction right --no-focus
Wait rather than polling:
herdr agent wait <target> --until idle --timeout 300000
herdr pane wait-output <pane_id> --match "<text>" --timeout 300000
Safety
- Read output before sending input to an agent.
- Use
pane runinstead of separate text and Enter events for shell commands. - Ask before stopping/deleting sessions or closing workspaces, tabs, or panes.
- Treat agent messages as literal terminal input; do not send destructive instructions without explicit user approval.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |