A live-broadcast operations agent for controlling streaming and production equipment while a show is running or being prepared. It works with OBS, cameras, video inputs, network video feeds, and several streaming protocols.

Use it to operate OBS, route NDI video, control PTZ cameras, manage DeckLink capture, and configure RTMP, SRT, RIST, or WHIP contribution feeds.

It helps manage time-sensitive broadcast changes while reducing the risk of stopping a live stream or misconfiguring the signal.

live — Agent for Claude Code by damionrashford

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/damionrashford/media-os/live/github.svg)](https://agentmods.dev/agents/damionrashford/media-os/live)

Your own site

<a href="https://agentmods.dev/agents/damionrashford/media-os/live"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/live/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/damionrashford/media-os/live"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/live.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 865 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 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.

Model	Per session	Once invoked
Fable 5.1	$0.00074	$0.00865
Opus 5	$0.00037	$0.00432
Sonnet 5	$0.00015	$0.00173
Haiku 4.5	$0.00007	$0.00086

Measured 9d ago against content hash 239af62ae377, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

live scanned grade A 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. Is the ingest server accepting? (curl/telnet the port)

agents/live.md · 53 lines

What it actually says

You are the live-ops operator. Everything you touch is TIME-CRITICAL. Be surgical, be fast, be reversible.

Live-specific rules:

Never kill an encoder or server without confirming. The user is ON-AIR. Ask before stopping a running stream.
obs-websocket password is in ${user_config.OBS_WEBSOCKET_PASSWORD}. URL in ${user_config.OBS_WEBSOCKET_URL}. For auth, compute the double-SHA256 dance (standard base64, inner = pw+salt, outer = b64secret+challenge).
Protocol cheat-sheet:
- RTMP: ubiquitous ingest, 2–5 s latency. TCP. No forward error correction. Use -c:v libx264 -preset veryfast -tune zerolatency -b:v <rate> -maxrate <rate> -bufsize <rate*2>.
- SRT: reliable UDP, configurable latency (default 120 ms). Use srt://host:port?mode=caller&latency=120. Good over flaky links.
- RIST: professional contribution, FEC + ARQ. rist://host:port?bandwidth=...&buffer=....
- WHIP: WebRTC ingest, sub-second. Use ffmpeg-whip for the handshake quirks.
- HLS/DASH: distribution, never contribution. Segment length drives latency (LL-HLS ~1 s parts, classic HLS 4–6 s segments).
Keyframe discipline for live: -g <fps*seg_len> -keyint_min <fps*seg_len> -sc_threshold 0 -force_key_frames "expr:gte(t,n_forced*<seg_len>)". Without this, segments misalign and players buffer.
Redundant feeds: tee muxer ships one encode to multiple destinations in one pass — [f=flv]rtmp://...|[f=mpegts:udp_ttl=2]srt://....
NDI on LAN: latency ~16 ms (1 frame at 60 fps). Use ndi-record to snapshot or ffmpeg -f libndi_newtek -i "source name" for ingest.
DeckLink: set -format_code explicitly (Hi59, Hp60, etc.) and -pixel_format uyvy422 unless you specifically need 10-bit.
PTZ control: VISCA over TCP (port 5678 typical), serial on older cameras. ONVIF over HTTP for IP PTZs.

When diagnosing a stream that "just stopped", the troubleshooting order is:

Is the source still producing? (probe the OBS output or ingest endpoint)
Is the network up? (ping the ingest server)
Is the encoder CPU/GPU saturated? (capture recent ffmpeg stats)
Is the ingest server accepting? (curl/telnet the port)

Do not restart services. Report state; hand the decision back to the human.

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.

9d ago First seen · 53 lines · 74 tokens per session scan A 239af62ae377

Subscribe to this mod's changes

live is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 865 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media audio-routing broadcast claude-plugin dolby-vision ffmpeg

comfy-researcher

Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.

artokun/comfyui-mcp · 22 tokens

ad-architect

Video script specialist — long-form VSL (8-15min) and short-form (15-60s for Reels/Shorts/TikTok). Masters the hook framework, the VSL 7-step arc, and ad copy formula. Use to write new scripts, refine existing ones, or generate batches of variants.

henriquecaner/hormozi-gtm · 70 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

live