twilio-conversation-memory

twilio-conversation-memory is a skill for Claude Code, Codex from twilio/ai. It costs 55 tokens per session (2,898 once invoked), scanned A, original, MIT.

A Twilio service for saving and retrieving customer conversation context across sessions and communication channels. It stores profiles, traits, observations, and summaries, then finds relevant information through search.

In plain words
What is it for?
Use it to save conversation summaries and customer facts, manage profiles and traits, and retrieve relevant history for future interactions.
Why use it?
It prevents an AI or human agent from losing important customer context when a conversation ends or moves to another session or channel.

Skill for Claude CodeCodex ✓ vendor

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the ai plugin — 57 skills shipped together

Good fit Use it to save conversation summaries and customer facts, manage profiles and traits, and retrieve relevant history for future interactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/twilio/ai/twilio-conversation-memory
View source ↗ twilio/ai
About the project

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.

twilio/ai · 30 stars · on GitHub

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.

Any agent
npx skills add twilio/ai --skill twilio-conversation-memory
Clone the repo
git clone --depth 1 https://github.com/twilio/ai

Made for: Claude Code, Codex.

Or install ai, the plugin that ships this one along with the rest of its 57 skills.

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 twilio-conversation-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/twilio/ai/twilio-conversation-memory.svg)](https://agentmods.dev/skills/twilio/ai/twilio-conversation-memory)
Your own site
<a href="https://agentmods.dev/skills/twilio/ai/twilio-conversation-memory"><img src="https://agentmods.dev/badge/skills/twilio/ai/twilio-conversation-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 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 Data Exfiltration · line 65
    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 98
    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 124
    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 154
    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 250
    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.
How audits are shown
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 5.1 $0.00055 $0.02898
Opus 5 $0.00028 $0.01449
Sonnet 5 $0.00011 $0.00580
Haiku 4.5 $0.00006 $0.00290

Measured 8d ago against content hash 1b35849b61ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

twilio-conversation-memory 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

store = requests.post(
skills/twilio/twilio-conversation-memory/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Conversation Memory gives agents persistent, cross-session context about customers. A Memory Store holds profiles, observations, summaries, and traits. Data enters two ways:

  1. Automatic: Link a Conversation Orchestrator config to a store. Profiles are auto-created per caller. At conversation close, observations and summaries are extracted from the transcript and saved. Conflicting data is automatically reconciled.

  2. Direct API: POST observations, summaries, or traits yourself for any use case.

Data comes out via Recall — hybrid semantic + lexical search that surfaces the most relevant profile data. For voice agents where latency is critical, use GET /Observations directly instead.

Base URL: https://memory.twilio.com

Authentication: HTTP Basic — Authorization: Basic {base64(accountSid:authToken)}

Rules for agents:

  • Always poll statusUrl after any 202 response — all writes are async
  • Always create a trait group before writing traits of that group
  • Always use E.164 format for phone numbers (+15558675310)
  • Always verify store status is ACTIVE before operating on it
  • Never use /v1/Services/ paths — correct paths are /v1/ControlPlane/Stores (config) and /v1/Stores/{storeId}/... (data)
  • Never exceed 10 observations per batch or 4096 characters per observation
  • Never assume writes are immediately readable — indexing is async
  • Never send PCI or HIPAA data — not yet compliant

Prerequisites

  • Twilio account with Account SID and Auth Token — A credit card must be added to the account — See twilio-account-setup for initial setup — See twilio-iam-auth-setup for credential best practices
  • Environment variables:
    • TWILIO_ACCOUNT_SID
    • TWILIO_AUTH_TOKEN
  • SDK: pip install twilio / npm install twilio
  • For automatic extraction: a Conversation Orchestrator configuration — see twilio-conversation-orchestrator

Quickstart

Step 1 — Create a Memory Store

Python

import os, requests
from requests.auth import HTTPBasicAuth

account_sid = os.environ["TWILIO_ACCOUNT_SID"]
auth_token = os.environ["TWILIO_AUTH_TOKEN"]
base_url = "https://memory.twilio.com"
auth = HTTPBasicAuth(account_sid, auth_token)

store = requests.post(
    f"{base_url}/v1/ControlPlane/Stores",
    auth=auth,
    json={"displayName": "my-store", "description": "Customer memory"}
).json()

print(store["id"])  # mem_store_xxx — save this
# Poll store["statusUrl"] until status is ACTIVE

Read the full file on GitHub · 341 lines

Files

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.

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. 8d ago First seen · 341 lines · 55 tokens per session scan A 1b35849b61ca

Subscribe to this mod's changes

twilio-conversation-memory is a skill published in the GitHub repository twilio/ai (30 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 2,898 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

mem0-status

Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.

mem0ai/mem0 · 44 tokens

supermemory

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…

supermemoryai/supermemory · 81 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

browserwing-executor

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

MemTensor/MemOS · 42 tokens

potpie-repo-baseline

Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…

potpie-ai/potpie · 75 tokens

ai-persistence/server

Server chat state with withPersistence from @tanstack/ai-persistence. Authoritative transcript, run lifecycle, durable interrupts/approvals, chatParamsFromRequest, reconstructChat, snapshotStreaming. Use when the server owns history, multi-device, or durable tool approvals. NOT client localStorage (see…

TanStack/ai · 83 tokens