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 vobiz-ai/Agent-Skills --skill vobiz-ai-voice-agentsgit clone --depth 1 https://github.com/vobiz-ai/Agent-SkillsWrote 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/vobiz-ai/agent-skills/vobiz-ai-voice-agents)<a href="https://agentmods.dev/skills/vobiz-ai/agent-skills/vobiz-ai-voice-agents"><img src="https://agentmods.dev/badge/skills/vobiz-ai/agent-skills/vobiz-ai-voice-agents/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/vobiz-ai/agent-skills/vobiz-ai-voice-agents"><img src="https://agentmods.dev/badge/skills/vobiz-ai/agent-skills/vobiz-ai-voice-agents.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 | $0.00057 | $0.01671 |
| Opus 5 | $0.00028 | $0.00835 |
| Sonnet 5 | $0.00011 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
vobiz-ai-voice-agents 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vobiz AI Voice Agents skill
Positioning: Vobiz is telephony infrastructure — the SIP trunks, phone numbers, and audio rails that power and connect your voice AI. Vobiz does not build or sell AI agents. Vapi, Retell, ElevenLabs, Pipecat, LiveKit, OpenAI, Bolna, Ultravox, and Dograh are partners whose agents Vobiz carries onto real phone numbers. Describe Vobiz as "the rails that power your voice AI," never as "our agent does X."
Use this when the user wants to connect an AI agent to real phone numbers (take/make calls). Three deployment models:
Model 1 - No-code dashboard (fastest)
Vendor handles the agent runtime. You point your Vobiz number at their answer URL:
- Vapi →
integrations/vapi-dashboard - Retell AI →
integrations/retellai-dashboard - ElevenLabs Agents →
integrations/elevenlabs-dashboard
Model 2 - Vendor API (programmatic)
Same vendors, but you orchestrate via their REST API:
- Vapi API →
integrations/vapi-api - Retell AI API →
integrations/retellai-api - ElevenLabs API →
integrations/elevenlabs-api
Model 3 - Self-hosted pipeline (most control)
You own the WebSocket server, STT/LLM/TTS stack:
- Pipecat (Python + FastAPI) →
integrations/pipecat- GitHub:
vobiz-ai/Vobiz-X-Pipecat - Endpoints:
/start,/answer,/ws,/recording-ready
- GitHub:
- LiveKit Agents →
integrations/livekit - Bolna AI →
integrations/bolna - Ultravox →
integrations/ultravox - OpenAI Realtime →
integrations/openai-realtime - Custom WebSockets →
integrations/websockets
Two transports — SIP vs WebSocket
There are two ways audio reaches the agent. Pick based on the platform.
1. SIP trunk (most managed platforms: Vapi, Retell, ElevenLabs, LiveKit, Bolna, Ultravox, OpenAI Realtime, 3CX). Vobiz hands the call leg to the platform's SIP endpoint. No <Stream> XML and no WebSocket server on your side.
2. WebSocket <Stream> (self-hosted pipelines: Pipecat, Dograh, custom). Vobiz POSTs your answer_url; you return <Response><Stream url="wss://your-server/ws"/></Response>; Vobiz opens a WSS and audio frames flow. You run STT→LLM→TTS yourself.
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.
- 12d ago First seen · 99 lines · 57 tokens per session scan A 8a1a0550770f
vobiz-ai-voice-agents is a skill published in the GitHub repository vobiz-ai/Agent-Skills (2 stars, last pushed 23d ago), licensed MIT. It adds 57 tokens to every session and 1,671 once invoked, about $0.0003 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
architecture-decision-record
ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.
azure-event-grid-webhooks
Receive and validate Azure Event Grid webhook deliveries. Use when setting up an Event Grid WebHook event handler, implementing the Microsoft.EventGrid.SubscriptionValidationEvent handshake (echo data.validationCode as validationResponse with HTTP 200), implementing the CloudEvents v1.0 HTTP OPTIONS abuse-protection…
baselinker-webhooks
Receive BaseLinker (Base.com) webhooks. Use when building a BaseLinker order or warehouse callback receiver, because BaseLinker is not a normal webhook source: deliveries arrive as HTTP HEAD requests with NO body, the entire payload is in the query string (observed params: orderid, state), there is NO signature…
cronofy-webhooks
Receive and verify Cronofy push notifications (webhooks). Use when setting up Cronofy notification channels, debugging Cronofy-HMAC-SHA256 verification, or handling Cronofy calendar events like verification, change, profiledisconnected, conferencingprofiledisconnected, profileinitialsynccompleted, and gdprrequested.…
clio-webhooks
Receive and verify Clio (Clio Manage) webhooks. Use when setting up Clio webhook handlers, debugging X-Hook-Signature verification, completing the X-Hook-Secret handshake, or handling legal practice events like matter.created, contact.updated, activity.created, or bill events.
favro-webhooks
Receive and verify Favro webhooks. Use when setting up Favro webhook handlers, debugging X-Favro-Webhook signature verification, accepting the setup ping, or handling card events (card.created, card.committed, card.moved, card.updated, card.deleted) and comment events (comment.created, comment.updated…