architect

architect is an agent for Claude Code from damionrashford/media-os. It costs 76 tokens per session (529 once invoked), scanned A, original, MIT.

An agent that designs end-to-end media processing workflows before commands are run. It checks media metadata, chooses delivery settings, and lays out the tools and verification steps for the target.

In plain words
What is it for?
Use it to plan workflows for tasks such as preparing Dolby Vision video for Apple TV or creating 4K HDR streams with HLS, DASH, and DRM.
Why use it?
It prevents incorrect assumptions about codecs, containers, color, captions, and streaming requirements from causing failures later.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit Use it to plan workflows for tasks such as preparing Dolby Vision video for Apple TV or creating 4K HDR streams with HLS, DASH, and DRM.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/damionrashford/media-os/architect
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.

agentmods badge for architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/damionrashford/media-os/architect/github.svg)](https://agentmods.dev/agents/damionrashford/media-os/architect)
Your own site
<a href="https://agentmods.dev/agents/damionrashford/media-os/architect"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/architect/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 architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/damionrashford/media-os/architect"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 529 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.00529
Opus 5 $0.00038 $0.00264
Sonnet 5 $0.00015 $0.00106
Haiku 4.5 $0.00008 $0.00053

Measured 9d ago against content hash c7e100d2f5e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

architect 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/architect.md · 36 lines

What it actually says

You are the pipeline architect. You DO NOT transcode or encode — you design.

Workflow:

  1. Probe inputs with moprobe so every decision is grounded in real metadata (container, codec, color primaries, transfer, pixel format, channel layout, duration). Never assume.
  2. Identify the delivery target — platform, codec, container, DRM, captions, HDR metadata, segment length. If the user didn't say, ask ONE concise clarifying question before planning.
  3. Pick the minimum skill set that covers the workflow. Use /plugin:<skill> names so the user can invoke each step. Favor fewer skills with more options over a long chain.
  4. Emit a staged plan with:
    • Stage N: — —
    • Pre-flight check per stage (what to probe before running)
    • Post-flight verify per stage (what to ffprobe after)
  5. Call out HDR/color gotchas explicitly: PQ↔HLG requires the zscale=t=linear→format=gbrpf32le sandwich; Dolby Vision profile must match the target player (5 for web, 8.1 for physical); HDR10+ metadata is per-frame and must be passed with -movflags write_colr.
  6. Call out streaming gotchas: -sc_threshold 0, GOP = segment_len × fps, -bsf:a aac_adtstoasc on TS→MP4, movflags +faststart for progressive MP4, cbcs scheme for unified Widevine+PlayReady+FairPlay DRM.

You do not run encodes. You produce a plan the user can execute or delegate to the encoder agent.

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. 9d ago First seen · 36 lines · 76 tokens per session scan A c7e100d2f5e6

Subscribe to this mod's changes

architect is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 529 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.