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/deepgramnpx skills add wittyreference/twilio-claude-plugin --skill deepgramgit 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 | $0.00010 | $0.02067 |
| Opus 5 | $0.00005 | $0.01033 |
| Sonnet 5 | $0.00002 | $0.00413 |
| Haiku 4.5 | $0.00001 | $0.00207 |
Grade A, and why
deepgram 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: deepgram description: Deepgram STT integration with Twilio Voice. Use when configuring speech recognition with Deepgram for ConversationRelay, Gather, or real-time Transcription. allowed-tools: Read, Grep, Glob
Deepgram Integration Skill
Decision-making guide for using Deepgram speech-to-text within Twilio Voice products. Load this skill when choosing or configuring Deepgram as the STT provider for ConversationRelay, <Gather>, or <Start><Transcription>.
All claims in this skill are backed by live testing (2026-03-24, account ACxx...xx). See references/test-results.md for the full evidence matrix with call SIDs.
Scope: What Deepgram Does (and Doesn't Do) in Twilio
Deepgram is a speech-to-text (STT) provider only in Twilio's voice platform. It is not available for:
- TTS — Use Google, Amazon Polly, or ElevenLabs for text-to-speech
- Batch/post-call transcription — Voice Intelligence uses its own engines
- Media Streams —
<Connect><Stream>delivers raw audio; no native Deepgram routing
No Deepgram API key is required. Twilio manages the Deepgram integration — you configure it through TwiML attributes only.
Attribute Name Map
Each product uses a different mechanism to select Deepgram and a different model name format. This is the single most important table in the skill.
| What you want | ConversationRelay | <Gather> |
<Start><Transcription> |
|---|---|---|---|
| Select Deepgram | transcriptionProvider="Deepgram" |
Implied by deepgram_ prefix on speechModel |
transcriptionEngine="deepgram" |
| Choose model | speechModel="nova-3-general" |
speechModel="deepgram_nova-3-general" |
speechModel="nova-3" |
| Smart formatting | deepgramSmartFormat="true" |
N/A | N/A |
| Language | transcriptionLanguage="en-US" |
language="en-US" |
languageCode="en-US" |
| Hints | hints="pizza, pepperoni" |
hints="pizza, pepperoni" |
hints="pizza, pepperoni" |
What ships with it
4 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.
- 2d ago First seen · 167 lines · 10 tokens per session scan A 46ffb0439bc0
deepgram 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 2,067 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
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…