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 Cognigy/cognigy-plugin --skill voice-gateway-setupgit clone --depth 1 https://github.com/Cognigy/cognigy-pluginWrote 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/cognigy/cognigy-plugin/voice-gateway-setup)<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/voice-gateway-setup"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/voice-gateway-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/cognigy/cognigy-plugin/voice-gateway-setup"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/voice-gateway-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00812 |
| Opus 5.5 | $0.00012 | $0.00325 |
| Sonnet 5.5 | $0.00006 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
voice-gateway-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 14d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Gateway Setup Guide
Deploy an AI Agent as a voice-enabled endpoint with WebRTC support. Users can talk to the agent directly in their browser.
Prerequisites
- A Project — use
list_resources { resourceType: "project" }to find one, or letcreate_ai_agentcreate one automatically. - A Flow — the conversation logic the voice endpoint connects to. Use
list_resources { resourceType: "flow", projectId }to find existing flows. - An LLM — the agent needs an LLM to generate responses. Use
setup_llmif not configured.
Quick Start
1. Create a Voice Gateway endpoint
{
"projectId": "<24-char hex>",
"flowId": "<flow referenceId>",
"name": "My Voice Agent"
}
This automatically:
- Creates a
voiceGateway2endpoint - Provisions a WebRTC client
- Returns a
webrtcDemoUrlthe user can open in a browser
2. Customize the WebRTC widget (optional)
{
"projectId": "<24-char hex>",
"flowId": "<flow referenceId>",
"name": "My Voice Agent",
"webrtcWidgetConfig": {
"label": "Support Agent",
"theme": "AI_PURPLE",
"transcription": { "enabled": true },
"tagline": "How can I help you today?",
"avatarLogoUrl": "https://example.com/avatar.png"
}
}
3. Update an existing endpoint
{
"endpointId": "<24-char hex>",
"webrtcWidgetConfig": {
"theme": "CLEAN_WHITE"
}
}
Create vs update:
- Omit
endpointId→ a newvoiceGateway2endpoint is always created (projectId+flowIdrequired). The tool never auto-detects an existing endpoint. - Pass
endpointId→ that endpoint is updated and the settings you pass are merged into its existing configuration; everything else is preserved. Find it first withlist_resources { resourceType: "endpoint", projectId }.
WebRTC Widget Themes
| Theme | Description |
|---|---|
DARK_MODE |
Dark background (default) |
CLEAN_WHITE |
Light/white background |
AI_PURPLE |
Purple accent theme |
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.
- 14d ago Changed · +7 lines 7ca12488aeef
- 2mo ago First seen · 88 lines · 31 tokens per session scan A 98273201f031
voice-gateway-setup is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 812 once invoked, about $0.0001 per session on Opus 5.5. 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.
voice-gateway-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| voice-gateway-setupCognigy/cognigy-plugin | Skill | 18 | yesterday | MIT | A | 31 | Claude Code |
| x402browser-use/browser-use | Skill | 120k | yesterday | MIT | A | 175 | Claude Code |
| derive-clientvercel-labs/agent-browser | Skill | 46k | yesterday | Apache-2.0 | A | 100 | Claude Code |
| har-derived-api-clientNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 19 | Claude Code, Codex |
| cloudbrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 177 | Claude Code |
| sync-new-data-typechromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 36 | Claude Code, Codex |
| browserwing-executorMemTensor/MemOS | Skill | 12k | 2d ago | Apache-2.0 | A | 42 | Claude Code, Codex |