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/conversations-v2npx skills add wittyreference/twilio-claude-plugin --skill conversations-v2git 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/conversations-v2)<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conversations-v2"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/conversations-v2.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 | $0.00013 | $0.03011 |
| Opus 5 | $0.00006 | $0.01505 |
| Sonnet 5 | $0.00003 | $0.00602 |
| Haiku 4.5 | $0.00001 | $0.00301 |
Grade B, and why
conversations-v2 scanned grade B 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const config = await fetch('https://conversations.twilio.com/v2/ControlPlane/Configurations', { method: 'POST', How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: conversations-v2 description: Twilio Conversations v2 (Conversation Orchestrator) development guide. Use when building omnichannel conversation tracking, managing participants and communications, configuring capture rules, or debugging conversation lifecycle issues. Do NOT use for Customer Memory (use /customer-memory) or Intelligence analysis (use /conversational-intelligence). allowed-tools: mcp__twilio__*, Read, Grep, Glob
Twilio Conversations v2 (Conversation Orchestrator)
Omnichannel conversation tracking API. Captures conversations across SMS, Voice, WhatsApp, RCS, Chat, and Email channels. Automatically resolves customer profiles via linked Memory Store, groups communications into logical conversations, and feeds data to Intelligence v3 for analysis.
Generally available — HTTP-only (no SDK). Requires Customer Memory Store for configuration. Not PCI/HIPAA compliant.
Evidence: Claims sourced from live testing (2026-03-26). MCP tools verified in conversations-v2.ts of the Twilio MCP server.
Scope
CAN
- Capture conversations across 6 channel types: SMS, VOICE, WHATSAPP, RCS, CHAT, EMAIL
- Group conversations by participant addresses (cross-channel) or by addresses + channel type
- Auto-resolve customer profiles from phone/email via linked Memory Store identity resolution
- Track 3 participant types: CUSTOMER, HUMAN_AGENT, AI_AGENT
- Inject communications programmatically (for channels not auto-captured)
- Close conversations manually (PUT with
status: CLOSED) - Link up to 5 Intelligence Configurations for automated analysis
- Configure capture rules per channel (which numbers/addresses trigger capture)
- Enable PII redaction at the configuration level
- Enable memory extraction (auto-extract observations when conversations close)
- Configure status callbacks (webhooks for conversation lifecycle events)
- Filter conversations by status, channelId, or participant addresses
CANNOT
- No participant deletion — Once a Participant is added to a Conversation, it cannot be removed. Plan additions carefully. [Live-tested]
- No communication editing or deletion — Communications are append-only. No UPDATE or DELETE. [Live-tested]
- No grouping type change post-creation —
conversationGroupingTypeis immutable after Configuration creation. Must create a new Configuration to change it. [conversations-invariants.md] - No SDK support — All operations require raw HTTP with
Content-Type: application/jsonand Basic auth. - No standalone without Memory Store —
memoryStoreIdis required when creating a Configuration. You must create a Memory Store first (even if you don't use memory features). - No form-encoded requests — Returns 422 "Unsupported Format" if you send form-encoded data. JSON only.
- No page-number pagination — Token-based only. Cannot jump to page N.
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.
- 4d ago First seen · 261 lines · 13 tokens per session scan B 68d75bd5ba6f
conversations-v2 is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 3,011 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…