How do I install the Herdr Voice Dispatcher skill?

Run npx skillmds@latest add edmundmiller/herdr-voice-dispatcher in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Herdr Voice Dispatcher safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Herdr Voice Dispatcher?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Herdr Voice Dispatcher free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Herdr Voice Dispatcher?

edmundmiller (@edmundmiller) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Herdr Voice Dispatcher by edmundmiller

Name: Herdr Voice Dispatcher
Author: edmundmiller

Herdr Voice Dispatcher

Dispatches spoken or written prompts to live Herdr agents and reports their status or results. Use when the user says to list, check, ask, tell, prompt, steer, or wait for an OMP, Codex, or other agent running in Herdr.

edmundmiller Updated Sep 17, 2026

File contents

Herdr voice dispatcher

Translate conversational requests into bounded Herdr CLI actions. This skill is an external controller for Codex Voice or chat, so it intentionally works without HERDR_ENV=1.

Connect

Run the concise inventory without native session references:

python3 ~/.agents/skills/herdr-voice-dispatcher/scripts/list_agents.py

If Herdr is unavailable, report the exact error.
- For Operation not permitted, ask the user to run the Codex task with Full Access; a skill cannot bypass the sandbox.
Do not dump raw herdr agent list output. It includes noisy native session references.

Resolve the target

Use an exact live agent name or pane ID.

If the user names a project, title, or directory, filter the inventory:

python3 ~/.agents/skills/herdr-voice-dispatcher/scripts/list_agents.py --query dotfiles

Treat labels such as omp or codex as agent kinds, not unique targets, when several matches exist.
If more than one candidate remains, ask one concise clarification. Never guess a pane.

Act

List or check status: use the inventory helper. Use herdr agent get "$target" only when more detail about one resolved agent is necessary.

Dispatch work: preserve the user's requested outcome and constraints, then submit without waiting:

herdr agent prompt "$target" "$prompt"

Report only that Herdr accepted the prompt. If the target was already working, explain that Herdr lifecycle state does not correlate completion to an individual queued turn.

Read a result: check status, then read bounded output:

herdr agent read "$target" --source recent-unwrapped --lines 80

If recent output is incomplete because the agent uses an alternate screen, use --source visible. Do not claim success from unknown state or truncated output.

Wait when explicitly requested: keep Voice responsive with a bounded wait:

herdr agent wait "$target" \
  --until idle --until done --until blocked \
  --timeout 60000

If the agent becomes blocked, read and relay its question. Do not answer it for the user.

Guardrails

Prompt only the target and intent the user authorized.
Never start, stop, focus, interrupt, send keys, or answer an approval unless the user explicitly requests that exact action.
Treat dispatch as an external state change; a zero exit status proves submission, not task completion.
Do not expose agent session paths or unrelated terminal content.
Never wait indefinitely. Return control after 60 seconds and offer a fresh status check.

Spoken examples

“Which Herdr agents need attention?” → list and summarize blocked, working, and done.
“Tell the dotfiles reviewer to inspect the current diff without editing.” → resolve one target, dispatch once, and return immediately.
“What did the reviewer say?” → check its state, then read bounded output.
“The reviewer is blocked—what does it need?” → read and relay the question without answering it.

---name: herdr-voice-dispatcherdescription: Dispatches spoken or written prompts to live Herdr agents and reports their status or results. Use when the user says to list, check, ask, tell, prompt, steer, or wait for an OMP, Codex, or other agent running in Herdr.---# Herdr voice dispatcherTranslate conversational requests into bounded Herdr CLI actions. This skill isan external controller for Codex Voice or chat, so it intentionally workswithout `HERDR_ENV=1`.## Connect1. Run the concise inventory without native session references: ```bash python3 ~/.agents/skills/herdr-voice-dispatcher/scripts/list_agents.py ```2. If Herdr is unavailable, report the exact error. - For `Operation not permitted`, ask the user to run the Codex task with Full Access; a skill cannot bypass the sandbox.3. Do not dump raw `herdr agent list` output. It includes noisy native session references.## Resolve the target- Use an exact live agent name or pane ID.- If the user names a project, title, or directory, filter the inventory: ```bash python3 ~/.agents/skills/herdr-voice-dispatcher/scripts/list_agents.py --query dotfiles ```- Treat labels such as `omp` or `codex` as agent kinds, not unique targets, when several matches exist.- If more than one candidate remains, ask one concise clarification. Never guess a pane.## Act**List or check status:** use the inventory helper. Use `herdr agent get"$target"` only when more detail about one resolved agent is necessary.**Dispatch work:** preserve the user's requested outcome and constraints, thensubmit without waiting:```bashherdr agent prompt "$target" "$prompt"```Report only that Herdr accepted the prompt. If the target was already`working`, explain that Herdr lifecycle state does not correlate completion toan individual queued turn.**Read a result:** check status, then read bounded output:```bashherdr agent read "$target" --source recent-unwrapped --lines 80```If recent output is incomplete because the agent uses an alternate screen, use`--source visible`. Do not claim success from `unknown` state or truncatedoutput.**Wait when explicitly requested:** keep Voice responsive with a bounded wait:```bashherdr agent wait "$target" \ --until idle --until done --until blocked \ --timeout 60000```If the agent becomes `blocked`, read and relay its question. Do not answer itfor the user.## Guardrails1. Prompt only the target and intent the user authorized.2. Never start, stop, focus, interrupt, send keys, or answer an approval unless the user explicitly requests that exact action.3. Treat dispatch as an external state change; a zero exit status proves submission, not task completion.4. Do not expose agent session paths or unrelated terminal content.5. Never wait indefinitely. Return control after 60 seconds and offer a fresh status check.## Spoken examples- “Which Herdr agents need attention?” → list and summarize `blocked`, `working`, and `done`.- “Tell the dotfiles reviewer to inspect the current diff without editing.” → resolve one target, dispatch once, and return immediately.- “What did the reviewer say?” → check its state, then read bounded output.- “The reviewer is blocked—what does it need?” → read and relay the question without answering it.

Frequently asked questions