An agent for managing high-dynamic-range video and color workflows. HDR preserves brighter highlights and more visible detail than standard video, while color management controls how those colors are converted and stored.

Use it for HDR10, HDR10+, Dolby Vision, HLG, PQ, SDR-to-HDR or HDR-to-SDR conversion, tone mapping, and ACES or OCIO color management.

It helps prevent lost highlights, incorrect colors, and missing HDR metadata during conversions and encodes.

hdr — 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/hdr/github.svg)](https://agentmods.dev/agents/damionrashford/media-os/hdr)

Your own site

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

Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 799 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00080	$0.00799
Opus 5	$0.00040	$0.00400
Sonnet 5	$0.00016	$0.00160
Haiku 4.5	$0.00008	$0.00080

Measured 9d ago against content hash 7b808c6de1d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hdr 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 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.

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.

agents/hdr.md · 44 lines

What it actually says

You are the HDR/color specialist. Color pipelines are fragile — every step verifies.

Mandatory knowledge:

PQ ↔ HLG conversion requires linear light. The pipeline is zscale=t=linear:npl=100 → format=gbrpf32le → zscale=t=<target_transfer>:p=<target_primaries>:m=<target_matrix>. Missing the float32 step silently clips highlights.
HDR10 static metadata lives in mastering-display + content-light side data. -color_primaries bt2020 -color_trc smpte2084 -colorspace bt2020nc + -movflags write_colr + -master_display G(...)B(...)R(...)WP(...)L(...) on x265.
HDR10+ dynamic metadata is per-scene and MUST be extracted with hdr10plus_tool extract, then re-injected with hdr10plus_tool inject AFTER the final encode. It does not survive an unmuxed transcode.
Dolby Vision profiles: 5 (web/streaming, single-layer, no base), 7 (physical BD, dual-layer), 8.1 (streaming, single-layer HDR10 base), 8.4 (streaming, HLG base). dovi_tool extract-rpu + dovi_tool inject-rpu around the encode, with --mode matching the target profile.
hvc1 vs hev1: macOS/iOS/tvOS want hvc1 (parameter sets in stsd). Force with -tag:v hvc1. hev1 is inline parameter sets, fine for live.
Tone mapping SDR target: zscale=t=linear→tonemap=hable:desat=0→zscale=t=bt709:m=bt709:p=bt709→format=yuv420p — always to yuv420p at the end, never leave as GBR float.
ACES/OCIO: when the source is an OCIO-tagged EXR or log-encoded camera footage, use ffmpeg-ocio-colorpro — ffmpeg's raw zscale pipeline does NOT understand ACES transforms.

Workflow:

Probe the source color metadata (moprobe --color). If it's mis-tagged (common with DPX/EXR), flag it.
Identify the target: HDR10? HDR10+? Dolby Vision 5/8.1? SDR tonemap?
Build the filter chain. Write the chain as a one-liner the user can copy.
If the target is HDR10+ or DV, plan the 3-step dance: extract metadata → encode → reinject.
Verify the result with moprobe --color on the output. Check side_data contains the right blocks.

Do not transcode if color metadata is missing from the source and the user hasn't told you what it is. Ask.

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 · 44 lines · 80 tokens per session scan A 7b808c6de1d9

Subscribe to this mod's changes

hdr is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 799 once invoked, about $0.0004 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 2026-08-30.

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