agentmods.dev

agent-connect

agent-connect is a skill for Claude Code, Codex from wittyreference/twilio-claude-plugin. It costs 10 tokens per session (3,457 once invoked), scanned A, original, MIT.

A development guide and tool set for building AI voice and SMS agents with Twilio Agent Connect. Twilio is a communications platform; Agent Connect links an AI model to phone calls and text conversations while managing related session data.

In plain words
What is it for?
Use it when creating TypeScript or Python agents that handle voice calls through ConversationRelay or SMS through Twilio Conversations, with customer-memory and conversation-intelligence features.
Why use it?
It avoids having to build channel connections, session handling, customer-memory retrieval, and conversation tracking separately.

Skill for Claude CodeCodex

Part of the twilio-claude-plugin plugin — 31 skills, 18 commands, 7 agents, 5 hooks shipped together

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/agent-connect
Any agent
npx skills add wittyreference/twilio-claude-plugin --skill agent-connect
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 31 skills, 18 commands, 7 agents, 5 hooks.

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.03457
Opus 5 $0.00005 $0.01729
Sonnet 5 $0.00002 $0.00691
Haiku 4.5 $0.00001 $0.00346

Measured 3d ago against content hash 425ad681b4d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-connect 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 3d 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.

4. **Verify ngrok tunnel before debugging**: A dead tunnel returns HTML 404 that mimics server 404. Verify: `curl -s -o /dev/null -w "%{http_code}" -X POST https://DOMAIN/health` must return 200. [conversations-invariant
skills/agent-connect/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

name: agent-connect description: Twilio Agent Connect (TAC) SDK development guide. Use when building LLM-powered voice/SMS agents with automatic Customer Memory retrieval and Conversations Orchestrator integration. Do NOT use for direct Conversations layer API calls (use /customer-memory, /conversations-v2, /conversational-intelligence instead). allowed-tools: mcp__twilio__*, Read, Grep, Glob, Bash

Twilio Agent Connect (TAC)

SDK middleware that orchestrates voice (ConversationRelay) and SMS (Conversations API) channels with automatic Customer Memory retrieval and Intelligence analysis. You bring the LLM; TAC handles channel I/O, session management, memory retrieval, and conversation tracking.

Generally available — TypeScript (Node 20+) and Python (3.9+). Not PCI/HIPAA compliant.

Evidence: Assertion audit sourced from TAC documentation (2026-03-25) + live integration testing. See references/assertion-audit.md for provenance. Note: assertions are DOC-VERIFIED, not SID-backed. Live testing recommended for production decisions.

Scope

CAN

  1. Orchestrate voice calls via ConversationRelay WebSocket — STT/TTS handled by Twilio
  2. Orchestrate SMS via Conversations API webhooks — message routing automated
  3. Retrieve Customer Memory (observations, summaries, communications) per message/utterance
  4. Provide unified callback: same handleMessageReady(userMessage, context, memoryResponse?) across channels
  5. Create and manage conversations automatically via Conversations Orchestrator
  6. Write to Customer Memory via MemoryClient (observations, traits — added post-initial-docs)
  7. Handoff to human agents via createHandoffTool() and onHandoff callback
  8. Support any LLM provider (OpenAI, Anthropic, Bedrock, LangChain)
  9. Active voice ingestion via TWILIO_TAC_ENABLE_VOICE_ACTIVE_HYDRATION=true

CANNOT

  1. No custom STT/TTS — Uses ConversationRelay defaults; cannot specify Deepgram, ElevenLabs, etc. For custom providers, use ConversationRelay directly.
  2. No raw audio access — WebSocket is abstracted; only transcribed text exposed. Use Media Streams if you need audio.
  3. No ConversationRelay protocol events — setup, interrupt, dtmf events are not passed through to your callback. Only transcribed speech arrives.
  4. No WhatsApp/Email/Chat channels — Only voice and SMS. For other channels, use the Conversations layer API directly (see Twilio Conversations documentation and the /conversations-v2 skill).
  5. No MCP tools — TAC SDK is not wrapped in the MCP server. Interact via the SDK directly in your application code.
  6. No mid-conversation provider switch — Cannot change LLM or TTS mid-call through TAC.
  7. Voice memory auto-retrieval is broken — TWILIO_TAC_ENABLE_VOICE_ACTIVE_HYDRATION is documented but has a known bug where context returns undefined. Use manual Recall via Customer Memory API at call setup instead.

Read the full file on GitHub · 259 lines

Files

What ships with it

2 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. 3d ago First seen · 259 lines · 10 tokens per session scan A 425ad681b4d8

Subscribe to this mod's changes

agent-connect 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 3,457 once invoked, about $0.0001 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 2026-08-31.

Backend and APIsBuilding agents
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