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 agentmods add skills/wittyreference/twilio-claude-plugin/customer-memorynpx skills add wittyreference/twilio-claude-plugin --skill customer-memorygit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWrote 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/wittyreference/twilio-claude-plugin/customer-memory)<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/customer-memory"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/customer-memory.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.04908 |
| Opus 5 | $0.00005 | $0.02454 |
| Sonnet 5 | $0.00002 | $0.00982 |
| Haiku 4.5 | $0.00001 | $0.00491 |
Grade A, and why
customer-memory 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 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.
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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: customer-memory description: Twilio Customer Memory development guide. Use when building customer context persistence, personalized AI agents, omnichannel profile management, or integrating memory into ConversationRelay or messaging flows. allowed-tools: mcp__twilio__*, Read, Grep, Glob
Twilio Customer Memory
AI-powered contextual data layer for customer profiles. Stores traits (structured facts), observations (unstructured insights auto-extracted from conversations), summaries, identifiers, and events. Provides semantic + lexical hybrid Recall search. Integrates with Twilio Conversations (SMS, WhatsApp, Voice) for automatic profile hydration.
Generally available — Not PCI or HIPAA compliant. AI models: OpenAI GPT-5-mini + text-embedding-3-large.
Evidence date: 2026-03-26.
Scope
CAN
- Create memory stores as profile containers (max 15/account, 10K profiles/store)
- Auto-extract observations from closed/inactive conversations (after conversation config set up)
- Auto-hydrate SMS profiles from configured phone numbers via Conversation Configuration
- Recall with semantic + lexical hybrid search across observations, summaries, and communications
- Recall without explicit query — returns recent observations (fast: ~37ms vs 800-10000ms with semantic query)
- Structured traits via trait groups with validation rules (STRING, BOOLEAN, INTEGER, arrays)
- Auto-promote traits to identifiers via
idTypePromotion(phone, email, chat, whatsapp) - Identity resolution across channels with EXACT matching and profile merging
- Observation reconciliation: contradictions update in-place, enrichments merge, unsupported discard
- Delete profiles (async, HTTP 202)
- Date-range filtering and relevance threshold on Recall
- Lookup profiles by identifier via
GET /Profiles?idType=X&value=Y - Bulk upsert up to 1000 profiles per request (async)
- CSV import up to 1M rows with automatic trait mapping (Console only)
- Profile events for tracking actions (up to 1000/batch, 10 properties each)
- Custom trait groups with custom trait definitions
What ships with it
5 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.
- 3d ago First seen · 295 lines · 10 tokens per session scan A 858d32eb7762
customer-memory 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 4,908 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.
Other skills, from other repositories
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.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…