conference

conference is a skill for Claude Code, Codex from wittyreference/twilio-claude-plugin. It costs 8 tokens per session (3,942 once invoked), scanned A, original, MIT.

A development guide for Twilio Conference, a service for connecting several people in one phone call. It covers call controls such as holding, muting, transfers, and private coaching.

In plain words
What is it for?
Use it when building multi-person call flows with hold, mute, warm transfers, coaching, whispering, or barging into a call.
Why use it?
It helps avoid incorrect assumptions about how conference calls, audio, and participant states work. It also documents limits of the service and when its status data may be misleading.

Skill for Claude CodeCodex

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

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/conference
Any agent
npx skills add wittyreference/twilio-claude-plugin --skill conference
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.

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 conference

README.md
[![agentmods](https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/conference.svg)](https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conference)
Your own site
<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/conference"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/conference.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00008 $0.03942
Opus 5 $0.00004 $0.01971
Sonnet 5 $0.00002 $0.00788
Haiku 4.5 $0.00001 $0.00394

Measured 3d ago against content hash 824d732be73a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conference 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.

skills/conference/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: conference description: Twilio Conference development guide. Use when building call orchestration with hold/mute, warm transfers, coaching/whisper/barge, or any call flow needing Conference or Participants API. allowed-tools: mcp__twilio__*, Read, Grep, Glob

Conference Development Skill

Comprehensive decision-making guide for Twilio Conference. Load this skill when building call flows that need hold, mute, warm transfer, coaching, or any multi-party orchestration.

WARNING: Conference REST API state can be misleading. The REST API may report a conference as in-progress with participants muted: false when audio is actually muted (all participants have startConferenceOnEnter=false). Do not trust API state alone for audio-level verification. Use Conference Insights for authoritative post-call state. See Gotcha #2.

Evidence date: 2026-03-24 | Account: ACxx...xx | Intelligence Service: GA7d01ec... (conference-validation)

What Conference Cannot Do

Explicit list of things developers commonly assume work but don't:

  • Cannot use <Gather> inside a conference — DTMF goes into the audio mix, not a handler
  • Cannot rely on speaker events for app logic — fire too frequently to be actionable
  • Cannot get post-flight participant data from REST API — completed conferences return empty; Insights is the only source
  • Cannot verify coaching via conference recording — coach audio is NOT in the conference mix recording; only REST API and Insights events confirm coaching [Evidence: GT6e8b15..., 2026-03-24]
  • Cannot filter Insights list endpoint by processing_state — must fetch by SID directly
  • Cannot use PII in friendlyName — compliance requirement, not just a suggestion
  • Cannot create a conference with 0 call legs and get Insights data — Insights requires ≥1 participant call attempt
  • Cannot poll Insights immediately after conference end — takes 15-30+ minutes even for in_progress state
  • Cannot do CRM screen pops — Conference provides call events; displaying caller context in a CRM is your application's JavaScript (Voice SDK call event → extract caller info → open CRM URL). Flex has built-in CRM panels; custom contact centers must build this.
  • Cannot compute EWT — Conference and TaskRouter provide queue statistics but not Estimated Wait Time calculations or announcements. You must poll queue stats, compute estimates, and serve them via a custom waitUrl handler.

Read the full file on GitHub · 247 lines

Files

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.

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 · 247 lines · 8 tokens per session scan A 824d732be73a

Subscribe to this mod's changes

conference is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 8 tokens to every session and 3,942 once invoked, about $0.0000 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.

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