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 khalilbenaz/claude-skills-collection --skill voice-agent-buildergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/voice-agent-builder)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/voice-agent-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/voice-agent-builder/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/khalilbenaz/claude-skills-collection/voice-agent-builder"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/voice-agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 137 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
- medium Data Exfiltration · line 159 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 159 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00090 | $0.02888 |
| Opus 5 | $0.00045 | $0.01444 |
| Sonnet 5 | $0.00018 | $0.00578 |
| Haiku 4.5 | $0.00009 | $0.00289 |
Grade A, and why
voice-agent-builder scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api.vapi.ai/call/phone \ How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Agent Builder
Quand utiliser ce skill
Conception ou implémentation d'un agent vocal interactif : bot téléphonique, IVR intelligent, assistant vocal webapp, agent conversationnel WebRTC/SIP. Couvre le pipeline complet STT → LLM → TTS et la gestion du dialogue.
Workflow en étapes
1. Choix d'architecture
Décision clé : synchrone vs streaming end-to-end.
| Critère | Synchrone (simple) | Streaming E2E (recommandé prod) |
|---|---|---|
| Latence typique | 2–4 s | < 1 s |
| Complexité | Faible | Élevée |
| Cas d'usage | PoC, flux courts | Production, conversations longues |
Pipeline cible :
Micro → VAD → STT (stream) → LLM (stream) → TTS (stream) → Haut-parleur
↑ barge-in détecté → interrompre TTS
Stack recommandée 2026 pour démarrer vite :
- Plateforme voix : Vapi (gère WebRTC/PSTN, VAD, barge-in, SIP nativement)
- STT : Deepgram Nova-3 (streaming, < 300 ms first byte, FR/EN)
- LLM : GPT-4o / Claude 3.5 Sonnet (streaming obligatoire)
- TTS : ElevenLabs Turbo v2.5 ou OpenAI TTS-1
2. Speech-to-Text (STT)
Critères de sélection :
| Moteur | Latence stream | Langues | Coût/min | Cas d'usage |
|---|---|---|---|---|
| Deepgram Nova-3 | ~200 ms | 36 langues | $0.0043 | Production générale |
| Whisper large-v3 | ~500 ms (local) | 99 langues | Gratuit (GPU) | Multi-langue, RGPD strict |
| Azure Speech | ~250 ms | 100+ | $0.016 | Intégration Microsoft |
| Google STT v2 | ~300 ms | 125 | $0.016 | Écosystème GCP |
Configuration VAD incontournable :
# Deepgram avec VAD + barge-in
dg_config = {
"model": "nova-3",
"language": "fr",
"interim_results": True, # transcription partielle pour barge-in
"endpointing": 300, # ms de silence avant fin d'énoncé
"utterance_end_ms": 1000, # timeout si silence prolongé
"vad_events": True, # événements speech_started / speech_ended
"smart_format": True, # formatage nombres, dates auto
}
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 · 263 lines · 90 tokens per session scan A 2236c041506e
voice-agent-builder is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 90 tokens to every session and 2,888 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
finance-econ-literacy
A Korean-language guide to understanding economic indicators such as interest rates, exchange rates, inflation, GDP, employment, and trade. It explains how these figures can affect loans, savings, investments, and spending.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
stock-business-review
Review a US-listed company's business model and revenue structure for an equity-research workup. Covers product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition (organic vs acquired vs price vs volume), and information-tier discipline (which numbers are facts vs…
stock-earnings-quality-review
Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…