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/media-streamsnpx skills add wittyreference/twilio-claude-plugin --skill media-streamsgit 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/media-streams)<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/media-streams"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/media-streams.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 | $0.00012 | $0.03614 |
| Opus 5 | $0.00006 | $0.01807 |
| Sonnet 5 | $0.00002 | $0.00723 |
| Haiku 4.5 | $0.00001 | $0.00361 |
Grade A, and why
media-streams 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 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.
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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: media-streams description: Twilio Media Streams WebSocket guide. Use when building voice AI with custom STT/TTS, real-time audio processing, bidirectional audio, or integration.
Media Streams Skill
Guide for Twilio Media Streams (<Connect><Stream>) — raw audio WebSocket integration for bring-your-own STT/TTS. Load this skill when building voice AI with custom speech processing, real-time audio analysis, or third-party STT/TTS engines.
When to Use Media Streams vs ConversationRelay
| Criteria | Media Streams | ConversationRelay |
|---|---|---|
| Audio access | Raw mulaw 8kHz frames | No audio — text in/out |
| STT/TTS | Bring your own | Built-in (Google, Polly) |
| Protocol complexity | High (binary audio) | Low (JSON text) |
| Latency control | Full | Twilio-managed |
| DTMF detection | Bidirectional only | Built-in |
| Interruption handling | Manual | Built-in |
| Custom audio processing | Yes (analysis, effects) | No |
| Time to prototype | Longer | Shorter |
Use Media Streams when: you need raw audio access, custom STT/TTS engines, real-time audio analysis (sentiment from tone, speaker diarization), or integration with platforms that expect audio input (Google Cloud Speech, AWS Transcribe, Azure Speech).
Use ConversationRelay when: you want text-based LLM integration with minimal audio plumbing. ConversationRelay handles STT, TTS, interruptions, and barge-in automatically.
TwiML Setup
Bidirectional Stream (<Connect><Stream>)
Bidirectional streams allow both receiving and sending audio. The <Connect> verb blocks subsequent TwiML until the stream ends.
const twiml = new Twilio.twiml.VoiceResponse();
// Optional: start background recording before stream
const start = twiml.start();
start.recording({
recordingStatusCallback: `https://${context.DOMAIN_NAME}/callbacks/call-status`,
recordingStatusCallbackEvent: 'completed',
});
twiml.say({ voice: 'Polly.Amy' }, 'Connecting you to our assistant.');
const connect = twiml.connect();
connect.stream({
url: 'wss://your-server.com/audio-stream',
// Optional: pass custom parameters to the WebSocket
// name: 'my-stream',
});
return callback(null, twiml);
What ships with it
1 file 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.
- 4d ago First seen · 413 lines · 12 tokens per session scan A 3e33c3ec66ec
media-streams is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 3,614 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…