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 commands/wittyreference/twilio-claude-plugin/help-twiliogit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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 | $0.00029 | $0.02031 |
| Opus 5 | $0.00015 | $0.01015 |
| Sonnet 5 | $0.00006 | $0.00406 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
help-twilio 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twilio Skill Navigator
Help the user find the right skill(s) for their use case.
How to Use
If the user provided a use case or question, match it to the relevant skills below and invoke them. If no arguments, show the full index.
Skill Index
Voice & Calling
| Skill | Use When |
|---|---|
/voice |
Building IVR, call routing, TwiML flows, outbound calls, AMD, limits |
/voice-use-case-map |
Choosing between Twilio voice products (Programmable Voice, Elastic SIP, Voice AI) |
/voice-sdks |
Browser softphones, mobile calling apps, AccessTokens, TwiML Apps, edge locations |
/android-sdk |
Android native Voice + Video — Gradle, FCM push, ConnectionService, permissions, emulator testing |
/voice-trust |
Spam/blocked calls, answer rates, SHAKEN/STIR, StirVerstat, CallToken, Branded Calling, Voice Integrity, CNAM |
/whatsapp-business-calling |
Voice calls over WhatsApp endpoints, <Dial><WhatsApp> |
/media-streams |
Real-time audio processing, transcription, bidirectional streaming |
/recordings |
Call recording methods, channel assignment, pause/resume, Voice Intelligence transcription |
/sip |
Programmable SIP — SIP Domains, registration, custom headers, auth models, <Dial><Sip> |
/sip-byoc |
SIP trunking, Bring Your Own Carrier, Elastic SIP Trunking |
/elastic-sip-trunking |
Deep Elastic SIP Trunking — trunk lifecycle, routing, recording, security, auth, diagnostics |
AI Agents & Middleware
| Skill | Use When |
|---|---|
/agent-connect |
Connecting LLM apps to Twilio voice/SMS via TAC middleware, Customer Memory integration |
/conversationrelay |
Building voice AI agents with ConversationRelay — TwiML attributes, WebSocket protocol, STT/TTS providers, ngrok setup, CI integration |
/synthetic-calls |
Generating bulk synthetic calls with customer personas, stress-testing voice AI, building demo data at scale |
/coval |
Coval voice AI evaluation — benchmarking with simulated calls, LLM-judge metrics, personas with noise/interruptions, production call monitoring, A/B testing, scheduled regression |
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.
- 2d ago First seen · 141 lines · 29 tokens per session scan A d28915359b80
help-twilio is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 2,031 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.