Vellum Assistant is a personal AI assistant that remembers information about users, learns their preferences, and takes actions across connected apps. It is intended for people who want an assistant that can manage conversations, unfinished work, and proactive notifications over time. The catalogue skills, hooks, instruction, and setting configure or extend how the assistant works.
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 vellum-ai/vellum-assistant --skill voice-setupgit clone --depth 1 https://github.com/vellum-ai/vellum-assistantWrote 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/vellum-ai/vellum-assistant/voice-setup)<a href="https://agentmods.dev/skills/vellum-ai/vellum-assistant/voice-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/voice-setup/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/vellum-ai/vellum-assistant/voice-setup"><img src="https://agentmods.dev/badge/skills/vellum-ai/vellum-assistant/voice-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 167 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00030 | $0.02396 |
| Opus 5 | $0.00015 | $0.01198 |
| Sonnet 5 | $0.00006 | $0.00479 |
| Haiku 4.5 | $0.00003 | $0.00240 |
Grade A, and why
voice-setup 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user set up and troubleshoot voice features entirely within this conversation. Use the client_os: line in <turn_context> to choose the macOS or Windows instructions below. Do not give macOS commands or key names to a Windows user, or Windows guidance to a macOS user.
Before using a desktop tool, check client_os:
- If it is
macosorwindows, follow that platform's branch. - If it is
web,ios,android, or absent, do not callopen_system_settingsor give desktop shortcut instructions. Explain that permissions and the Talk shortcut must be configured from the Mac or Windows desktop app. You can still complete provider, voice, language, and timeout configuration in the current conversation.
Available Tools
voice_config_updatechanges shared voice settings such as the legacy macOS PTT activation key, conversation timeout, speech providers, and TTS voice ID.open_system_settingsopens the correct macOS System Settings or Windows Settings privacy page. Call it only whenclient_osismacosorwindows, and pass that value asplatform.navigate_settings_tabopens Vellum settings. Use it for review, or when the desktop-owned Talk shortcut must be recorded in the app.assistant credentials promptcollects API keys securely for ElevenLabs or Deepgram.
The desktop Talk shortcut is client-owned. On current desktop clients, configure it in the Voice settings shortcut control instead of treating voice_config_update setting="activation_key" as a global shortcut editor. Use voice_config_update for the shared settings it owns. Use activation_key only for the legacy macOS PTT activation setting.
Setup Flow
Walk through each relevant section in order. Skip sections the user does not need, and ask before moving to the next section.
1. Microphone Permission
Microphone permission is not reported in <channel_capabilities>. Ask whether Vellum shows a microphone permission warning or whether the user already granted access.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 176 lines · 30 tokens per session scan A e749769c2ede
voice-setup is a skill published in the GitHub repository vellum-ai/vellum-assistant (1,214 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 2,396 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
make-viral-video
Build a short news-explainer video tuned for shareability. One striking moment per video; real fetched assets; self-heal validation; pluggable TTS (Gemini-free default, OpenAI fallback).
image-generation
Generate and edit images using Gemini Flash Image, and generate videos using Veo. Supports text-to-image, image editing, text-to-video, and image-to-video.
gemini-tts
Render text to mp3 via Google Gemini Flash TTS. Free-tier eligible (1500 req/day). Use for video narration, demo voiceovers, audio notes. Parallels openai-tts; default for make-viral-video.
audio-transcribe
Transcribes audio files and voice notes to text via Gemini 2.5-flash. Integrates with Slack, Discord, and Telegram bridges so voice clips surface as readable text in tasks.
screen-record
Start or stop a screen recording of the Mac via ffmpeg. Use when the user asks to record/capture their screen to a video file (a demo, a repro, a walkthrough) — not for a single still screenshot (use macos-tools screen capture for that).
openai-tts
Render text to mp3 via OpenAI's tts-1-hd. Use for video narration, demo voiceovers, audio notes.