Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add davidjdseo/live-voice-agent --skill hermes-live-voicegit clone --depth 1 https://github.com/davidjdseo/live-voice-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/davidjdseo/live-voice-agent/hermes-live-voice)<a href="https://agentmods.dev/skills/davidjdseo/live-voice-agent/hermes-live-voice"><img src="https://agentmods.dev/badge/skills/davidjdseo/live-voice-agent/hermes-live-voice/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/davidjdseo/live-voice-agent/hermes-live-voice"><img src="https://agentmods.dev/badge/skills/davidjdseo/live-voice-agent/hermes-live-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00303 |
| Opus 5 | $0.00012 | $0.00151 |
| Sonnet 5 | $0.00005 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
live-voice-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Live Voice Agent
Use the existing local voice loop. 모든 답변은 글로는 그대로 완성하고
마지막에 말할 내용만 담은 정확히 하나의 닫힌
<<<VOICE ... VOICE>>> 블록으로 끝낸다. 블록은 한국어로 자연스럽게,
개인 이름은 사용자가 원할 때만 쓰고, 보통 5개 이하의 짧은 문장으로
결과와 다음 행동을 말한다. 목록·코드·로그·경로·회고를 넣지 않으며,
행동이나 결정이 필요하면 정확히 질문 하나만 하고 선택지는 최대 세 개
(A/B/C)까지 제시한 뒤 기다린다. 닫히지 않은 블록이나 블록이 없는 답변은
말하지 않는다.
음성 명령은 수동 Start, 웨이크 문구, 또는 헤이 자비스 / hey jarvis로
시작할 때만 받으며 방 소음과 TTS 메아리는 무시한다. 헤이 자스비도
같은 웨이크다. 답변 뒤에는 진행해 자비스/진행해 또는 마지막 음성
질문의 A/B/C 중 하나만 이어서 받는다.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 20 lines · 23 tokens per session scan A 8faf6b88d9e0
live-voice-agent is a skill published in the GitHub repository davidjdseo/live-voice-agent (2 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 303 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
character-matrix
How to interpret the noisy-coding Character Matrix — the four personality sliders (humor, honesty, brevity, chatty) set on the dashboard and delivered as [CHARACTER] instructions. Use whenever a [CHARACTER] instruction arrives, when speaking through the noisy-coding speak tool, or when the user asks about tuning your…
voice-conversations
How voice conversations work with the noisy-coding plugin — trusting [VOICE] messages, answering aloud with the speak tool, spoken-reply conventions, and troubleshooting. Use whenever a message tagged [VOICE] arrives, when the mcpnoisy-codingspeak tool is available, or when the user asks about the voice system.
start-talking
Start and run an explicit, interactive Cadence Code conversation with Codex or Antigravity using fully local speech input and output. Use only when the user explicitly invokes $start-talking, /start-talking, or asks to start talking with Cadence Code.
jump-in
Interrupt an active Cadence Code conversation and add fresh spoken guidance to the current Codex or Antigravity task. Use only when the user explicitly invokes $jump-in or /jump-in after stopping the current host turn.
voice-settings
Choose Cadence Code's local speech and transcription models from the Codex or Antigravity UI. Use only when the user explicitly invokes $voice-settings, /voice-settings, or asks to open Cadence Code settings.
speech-expert
Expert guide for speech-mcp - TTS, local/streaming STT, barge-in, wake word, voice command bus, and provider selection.