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/zoom/zoom-plugin/rtmsnpx skills add zoom/zoom-plugin --skill rtmsgit clone --depth 1 https://github.com/zoom/zoom-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 | $0.00041 | $0.05927 |
| Opus 5 | $0.00020 | $0.02964 |
| Sonnet 5 | $0.00008 | $0.01185 |
| Haiku 4.5 | $0.00004 | $0.00593 |
Grade A, and why
zoom-rtms 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.
This is a copy
91% identical to zoom-rtms — 35 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoom Realtime Media Streams (RTMS)
Background reference for live Zoom media pipelines. Prefer build-zoom-bot first, then use this skill for stream types, capabilities, and RTMS-specific implementation constraints.
Zoom Realtime Media Streams (RTMS)
Expert guidance for accessing live audio, video, transcript, chat, and screen share data from Zoom meetings, webinars, Video SDK sessions, and Zoom Contact Center Voice in real-time. RTMS uses a WebSocket-based protocol with open standards and does not require a meeting bot to capture the media plane.
Read This First (Critical)
RTMS is primarily a backend media ingestion service.
- Your backend receives and processes live media: audio, video, screen share, chat, transcript.
- RTMS is not a frontend UI SDK by itself.
- Processing is event-triggered: backend waits for RTMS start webhook events before stream handling begins.
Optional architecture (common):
- Add a Zoom App SDK frontend for in-client UI/controls.
- Stream backend RTMS outputs to frontend via WebSocket (or SSE, gRPC, queue workers, etc.).
Use RTMS for media/data plane, and use frontend frameworks/Zoom Apps for presentation + user interactions.
Official Documentation: https://developers.zoom.us/docs/rtms/ SDK Reference (JS): https://zoom.github.io/rtms/js/ SDK Reference (Python): https://zoom.github.io/rtms/py/ Sample Repository: https://github.com/zoom/rtms-samples
Quick Links
New to RTMS? Follow this path:
- Connection Architecture - Two-phase WebSocket design
- SDK Quickstart - Fastest way to receive media (recommended)
- Manual WebSocket - Full protocol control without SDK
- Media Types - Audio, video, transcript, chat, screen share
Complete Implementation:
- RTMS Bot - End-to-end bot implementation guide
Reference:
- Lifecycle Flow - Complete webhook-to-streaming flow
- Data Types - All enums and constants
- Webhooks - Event subscription details
- Environment Variables - credential modes and runtime knobs
- Quickstart Notes - Secondary quickstart guide
- Integrated Index - see the section below in this file
What ships with it
14 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.
- concepts/connection-architecture.md 9.1 KB
- concepts/lifecycle-flow.md 13 KB
- examples/ai-integration.md 11 KB
- examples/manual-websocket.md 17 KB
- examples/rtms-bot.md 26 KB
- examples/sdk-quickstart.md 9.3 KB
- references/connection.md 8.0 KB
- references/data-types.md 14 KB
- references/environment-variables.md 1.3 KB
- references/media-types.md 6.0 KB
- references/quickstart.md 6.6 KB
- references/webhooks.md 9.5 KB
- RUNBOOK.md 2.6 KB
- troubleshooting/common-issues.md 10 KB
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 · 587 lines · 41 tokens per session scan A db5131cbe970
zoom-rtms is a skill published in the GitHub repository zoom/zoom-plugin (7 stars, last pushed 26d ago), licensed MIT. It adds 41 tokens to every session and 5,927 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to zoom-rtms, differing in 35 lines, and is treated as a copy.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-topology-viz
Turn a network topology into one stylized, AI-generated still image via a self-hosted ComfyUI instance — reuses the same topology model as threejs-network-viz (any of 8 topology-source integrations, or a freeform description). Use when the operator asks for a stylized, flashy, or AI-generated…