Twilio for AI provides coding agents with skills and an MCP server for using Twilio services and documentation. The MCP server searches Twilio documentation and API specifications and retrieves full schemas for selected operations, while the skills supply procedural guidance to agents. Its catalogue add-ons are intended for Claude Code, Cursor, Codex, and other tools that support the Agent Skills standard.
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 twilio/ai --skill twilio-call-recordingsgit clone --depth 1 https://github.com/twilio/aiWrote 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/twilio/ai/twilio-call-recordings)<a href="https://agentmods.dev/skills/twilio/ai/twilio-call-recordings"><img src="https://agentmods.dev/badge/skills/twilio/ai/twilio-call-recordings/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/twilio/ai/twilio-call-recordings"><img src="https://agentmods.dev/badge/skills/twilio/ai/twilio-call-recordings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Data Exfiltration · line 226 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 | $0.00069 | $0.02413 |
| Opus 5 | $0.00034 | $0.01207 |
| Sonnet 5 | $0.00014 | $0.00483 |
| Haiku 4.5 | $0.00007 | $0.00241 |
Grade A, and why
twilio-call-recordings 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 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.
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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Twilio offers multiple recording methods. Choosing the wrong one is the #1 developer mistake in voice — using <Record> when you mean <Dial record> produces voicemail behavior instead of call recording.
| Method | What it does | Use when |
|---|---|---|
<Record> verb |
Records the CALLER only (voicemail-style) | Leaving a message, capturing input |
<Dial record> |
Records BOTH parties on a call | Call recording for two-party calls |
<Start><Recording> |
Starts a recording alongside other verbs | ConversationRelay, multi-verb flows |
Conference record |
Records the conference mix | Multi-party calls |
| Recordings REST API | Programmatic control mid-call | Pause during payment (PCI) |
Prerequisites
- Twilio account with a voice-capable phone number — see
twilio-account-setup TWILIO_ACCOUNT_SIDandTWILIO_AUTH_TOKEN— seetwilio-iam-auth-setup- SDK:
pip install twilio/npm install twilio - A webhook endpoint for recording status callbacks
- Compliance check: Recording consent requirements vary by jurisdiction — see
twilio-compliance-traffic
Quickstart
Record a Two-Party Call (Most Common)
Use <Dial record> — NOT <Record>.
Python (Flask)
from flask import Flask, request
from twilio.twiml.voice_response import VoiceResponse
app = Flask(__name__)
@app.route("/voice", methods=["POST"])
def incoming_call():
response = VoiceResponse()
response.say("This call may be recorded for quality assurance.")
dial = response.dial(
record="record-from-answer-dual", # dual-channel: agent on one, caller on other
recording_status_callback="https://yourapp.com/recording-status"
)
dial.number("+15558675310") # agent's phone
return str(response)
Node.js (Express)
app.post("/voice", (req, res) => {
const response = new VoiceResponse();
response.say("This call may be recorded for quality assurance.");
const dial = response.dial({
record: "record-from-answer-dual",
recordingStatusCallback: "https://yourapp.com/recording-status",
});
dial.number("+15558675310");
res.type("text/xml").send(response.toString());
});
What ships with it
3 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.
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 · 281 lines · 69 tokens per session scan A b28ac7f3e4fb
twilio-call-recordings is a skill published in the GitHub repository twilio/ai (32 stars, last pushed 26d ago), licensed MIT. It adds 69 tokens to every session and 2,413 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…