webrtc-livekit

webrtc-livekit is a skill for Claude Code from damionrashford/media-os. It costs 243 tokens per session (3,125 once invoked), scanned B, original, MIT.

A deployable WebRTC server based on LiveKit, which provides rooms where people can publish and receive camera, microphone, screen-share, and data tracks.

In plain words
What is it for?
It helps run meetings, live broadcasts, media ingestion, recordings, and applications built around LiveKit rooms and participants.
Why use it?
It provides the server pieces needed for real-time rooms, access tokens, media input, and recording or streaming output.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the media-os plugin — 121 skills, 11 agents, 5 hooks, 1 plugin shipped together

Good fit It helps run meetings, live broadcasts, media ingestion, recordings, and applications built around LiveKit rooms and participants.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/damionrashford/media-os/webrtc-livekit
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.

Any agent
npx skills add damionrashford/media-os --skill webrtc-livekit
Clone the repo
git clone --depth 1 https://github.com/damionrashford/media-os

Made for: Claude Code.

Or install media-os, the plugin that ships this one along with the rest of its 121 skills, 11 agents, 5 hooks, 1 plugin.

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 webrtc-livekit

README.md
[![agentmods](https://agentmods.dev/badge/skills/damionrashford/media-os/webrtc-livekit/github.svg)](https://agentmods.dev/skills/damionrashford/media-os/webrtc-livekit)
Your own site
<a href="https://agentmods.dev/skills/damionrashford/media-os/webrtc-livekit"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/webrtc-livekit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for webrtc-livekit

Your own site · 80×15
<a href="https://agentmods.dev/skills/damionrashford/media-os/webrtc-livekit"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/webrtc-livekit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 243 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00243 $0.03125
Opus 5 $0.00121 $0.01563
Sonnet 5 $0.00049 $0.00625
Haiku 4.5 $0.00024 $0.00313

Measured 8d ago against content hash 92f6cfee7a8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

webrtc-livekit scanned grade B with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/livekit.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

The script downloads the correct release from `github.com/livekit/livekit/releases` (server) and `github.com/livekit/livekit-cli/releases` (CLI) for your `uname -sm`, extracts it, and places the binary in `--dest`. No su
skills/webrtc-livekit/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

webrtc-livekit

Context: $ARGUMENTS

LiveKit is an Apache-2.0 WebRTC SFU written in Go — a single-binary deployment with a vast SDK matrix. Docs home: https://docs.livekit.io/home/. Repo: https://github.com/livekit/livekit.

Quick start

  • Install server binary for your platform: → Step 1 (livekit.py install-server)
  • Install the CLI (lk / livekit-cli): → Step 1 (livekit.py install-cli)
  • Start a dev server: → Step 2 (livekit.py start)
  • Mint a JWT access token: → Step 3 (livekit.py mint-token)
  • Record or stream-out a room: → Step 5 (livekit.py egress-start)
  • Ingest RTMP/WHIP/SRT into a room: → Step 6 (livekit.py ingress-start)

Data model

Room (per-meeting)
  ├── Participant (per-user)
  │     ├── TrackPublication (the publisher's declaration)
  │     │     └── Track (camera / mic / screen-share / data)
  │     └── Permissions  (from JWT grants)
  └── Metadata           (free-form, room-wide or per-participant)

Tokens are JWT (HS256). Each token carries a video grant describing which room and which permissions.

Step 1 — Install the binaries

# Server
uv run ${CLAUDE_SKILL_DIR}/scripts/livekit.py install-server --dest ~/bin
# CLI ("lk", formerly "livekit-cli")
uv run ${CLAUDE_SKILL_DIR}/scripts/livekit.py install-cli --dest ~/bin

The script downloads the correct release from github.com/livekit/livekit/releases (server) and github.com/livekit/livekit-cli/releases (CLI) for your uname -sm, extracts it, and places the binary in --dest. No sudo required if --dest is writable. Homebrew and the official install.sh exist upstream — pick whichever fits your OS.

Step 2 — Start a dev server

uv run ${CLAUDE_SKILL_DIR}/scripts/livekit.py start --dev

--dev launches with a built-in dev API key / secret (devkey / secret) and enabled self-signed TURN on 443. For production, write a YAML config:

# livekit.yaml (abridged — see references/deployment.md for the full set)
port: 7880
bind_addresses: ['']
rtc:
  port_range_start: 50000
  port_range_end: 60000
  tcp_port: 7881
  use_external_ip: true
keys:
  devkey: secret
redis:
  address: redis:6379

Read the full file on GitHub · 274 lines

Files

What ships with it

3 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. 8d ago First seen · 274 lines · 243 tokens per session scan B 92f6cfee7a8d

Subscribe to this mod's changes

webrtc-livekit is a skill published in the GitHub repository damionrashford/media-os (19 stars, last pushed 3mo ago), licensed MIT. It adds 243 tokens to every session and 3,125 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.