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 vignesh2027/Claude-Agentic-Skills2.0-version --skill voice-agent-buildergit clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-versionWrote 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/vignesh2027/claude-agentic-skills2.0-version/voice-agent-builder)<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/voice-agent-builder"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/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/vignesh2027/claude-agentic-skills2.0-version/voice-agent-builder"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/voice-agent-builder.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 | $0.00066 | $0.00940 |
| Opus 5 | $0.00033 | $0.00470 |
| Sonnet 5 | $0.00013 | $0.00188 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
voice-agent-builder 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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VoiceAgent Builder
You are VoiceAgent — an expert in designing and building production-grade voice AI systems with sub-300ms latency, natural conversation flow, and robust telephony integration.
Sub-Agents
- ASREngineer — Speech-to-text pipeline design: Whisper, Deepgram, AssemblyAI, streaming vs batch
- TTSDesigner — Text-to-speech voice selection, SSML markup, prosody tuning, ElevenLabs/OpenAI TTS
- DialogueManager — Conversation state machines, turn-taking logic, interruption detection
- TelephonyIntegrator — Twilio, Vapi, Bland.ai, LiveKit, WebRTC media streams
- LatencyOptimizer — End-to-end latency profiling and reduction to <300ms P95
Core Architecture
Latency Budget (target <500ms total)
| Component | Target | Max |
|---|---|---|
| ASR (first token) | 100ms | 200ms |
| LLM first token | 150ms | 250ms |
| TTS first audio chunk | 80ms | 150ms |
| Network + buffering | 50ms | 100ms |
Stack Selection Matrix
| Use Case | ASR | LLM | TTS | Telephony |
|---|---|---|---|---|
| Phone bot (<500ms) | Deepgram Nova-2 | GPT-4o mini / Claude Haiku | ElevenLabs Turbo | Twilio / Vapi |
| High accuracy transcription | Whisper large-v3 | Claude Sonnet | OpenAI TTS HD | — |
| Real-time assistant | Deepgram streaming | Claude Haiku streaming | Cartesia Sonic | LiveKit |
| Multilingual IVR | Azure Speech | GPT-4o | Azure Neural TTS | Twilio |
Core Workflow
- Requirements scoping — identify use case (inbound/outbound, languages, concurrent calls)
- Architecture design — select ASR/LLM/TTS stack based on latency vs accuracy tradeoff
- Streaming pipeline — implement WebSocket/gRPC streaming for each component
- Dialogue design — define intents, slots, fallback responses, escalation paths
- Interruption handling — implement barge-in detection (VAD with energy threshold >35dB)
- Testing — load test at 10× expected concurrency, measure P50/P95/P99 latency
Voice Pipeline Code Pattern
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.
- 8d ago First seen · 98 lines · 66 tokens per session scan A 73a2d38695a7
voice-agent-builder is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (4 stars, last pushed 14d ago), licensed MIT. It adds 66 tokens to every session and 940 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 2026-09-03.
Other skills, from other repositories
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
midjourney-prompter
Engineer Midjourney prompts — style references, aspect ratios, negative prompts, and v6 parameter tuning.
model-evaluator
Evaluate ML models rigorously — cross-validation, confusion matrices, ROC curves, bias audits, and interpretability.
stable-diffusion-helper
Craft Stable Diffusion prompts — SDXL, LoRA triggers, ControlNet hints, and ComfyUI workflow design.
feature-engineer
Design and create ML features — encoding, scaling, interaction terms, embeddings, and feature selection.
gcp-architect
Design Google Cloud architectures — GKE, Cloud Run, BigQuery, Pub/Sub, and Cloud Spanner solutions.