agentmods.dev

conversationrelay

conversationrelay is a skill for Claude Code, Codex from wittyreference/twilio-claude-plugin. It costs 10 tokens per session (5,682 once invoked), scanned A, original, MIT.

A guide to building Twilio voice agents that connect phone calls to your own WebSocket server and language-model logic. Conversation Relay handles turning speech into text, speaking replies, interruptions, keypad tones, and live transcript updates.

In plain words
What is it for?
Use it to create real-time phone agents, choose speech recognition and voice providers, handle caller interruptions, detect keypad input, stream partial transcripts, play audio, or change languages during a call.
Why use it?
It clarifies which parts Twilio provides and which parts your server must implement when building a phone-based AI assistant.

Skill for Claude CodeCodex

Part of the twilio-claude-plugin plugin — 67 skills, 18 commands, 7 agents, 5 hooks shipped together

not rated 2 3mo ago A scan 10 tokens original MIT
View the source file wittyreference/twilio-claude-plugin
Install

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.

agentmods
npx agentmods add skills/wittyreference/twilio-claude-plugin/conversationrelay
Any agent
npx skills add wittyreference/twilio-claude-plugin --skill conversationrelay
Clone the repo
git clone --depth 1 https://github.com/wittyreference/twilio-claude-plugin

Made for: Claude Code, Codex.

Or install twilio-claude-plugin, the plugin that ships this one along with the rest of its 67 skills, 18 commands, 7 agents, 5 hooks.

Wrote 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.

agentmods badge for conversationrelay

README.md
[![agentmods](https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/conversationrelay.svg)](https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conversationrelay)
Your own site
<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conversationrelay"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/conversationrelay.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,682 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.05682
Opus 5 $0.00005 $0.02841
Sonnet 5 $0.00002 $0.01136
Haiku 4.5 $0.00001 $0.00568

Measured 4d ago against content hash ae3e47948f5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conversationrelay 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 4d 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.

skills/conversationrelay/SKILL.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

name: conversationrelay description: Twilio ConversationRelay voice AI guide. Use when building LLM-powered voice agents, connecting phone calls to WebSocket servers, configuring STT/TTS providers, handling real-time speech, or choosing between ConversationRelay and Media Streams. allowed-tools: mcp__twilio__*, Read, Grep, Glob, Bash

ConversationRelay Skill

Decision-making guide for building voice AI agents with Twilio ConversationRelay. ConversationRelay handles STT, TTS, interruption, and DTMF — you provide a WebSocket server with your LLM logic.

All claims backed by live testing (2026-03-28, account ACxx...xx). See references/test-results.md for call SIDs.

Scope

What ConversationRelay Does

  • Real-time bidirectional text communication between phone calls and your WebSocket server
  • Built-in STT (Google, Deepgram) and TTS (Google, Amazon Polly, ElevenLabs)
  • Automatic interruption handling (caller speech stops TTS playback)
  • DTMF detection and sending
  • Welcome greeting with configurable interruptibility
  • Partial transcript streaming (partialPrompts)
  • Audio playback via play message (URL-based)
  • Mid-session language switching via language message
  • Voice Intelligence v2 integration via intelligenceService attribute
  • Debug telemetry (round-trip latency, speaker events, tokens played)
  • X-Twilio-Signature on WebSocket handshake for request validation
  • Custom parameters passed from TwiML to WebSocket setup message
  • Session handoff with data passed to <Connect action> callback
  • Studio widget for no-code integration

What ConversationRelay Does NOT Do

  1. No raw audio access — text in, text out. For raw audio use <Connect><Stream> (see media-streams skill)
  2. No custom STT/TTS engines — limited to Google + Deepgram (STT) and Google + Amazon + ElevenLabs (TTS)
  3. No WebSocket auto-reconnection — if WS drops, call disconnects. Implement recovery via <Connect action> URL
  4. No mid-session voice/provider changes — voice and provider are set at TwiML time. Only language can be switched mid-session via the language WebSocket message
  5. No SMS/messaging — voice only. For omnichannel, see Agent Connect (public beta)
  6. No built-in memory/context — BYO conversation history and context management
  7. Not PCI compliant with Voice Intelligence v2 — do not enable intelligenceService in PCI workflows
  8. No LLM integration — pure transport layer. You bring your own LLM via the WebSocket server
  9. Cannot mix with Media Streams — <Connect><Stream> and <Connect><ConversationRelay> are mutually exclusive on the same call
  10. No server-side recording — use <Start><Recording> or call-level record parameter separately. Recording must be set up before <Connect> in TwiML
  11. ElevenLabs requires account enablement — accounts without ElevenLabs access get error 64101 with block_elevenlabs. Voice IDs (not human names) required: e.g., UgBBYS2sOqTuMpoF3BR0

Read the full file on GitHub · 470 lines

Files

What ships with it

4 files 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.

Changes

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.

  1. 4d ago First seen · 470 lines · 10 tokens per session scan A ae3e47948f5d

Subscribe to this mod's changes

conversationrelay is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 5,682 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens