qc

qc is an agent for Claude Code from damionrashford/media-os. It costs 85 tokens per session (513 once invoked), scanned A, original, MIT.

An automated quality-check agent for comparing an encoded or converted video with its reference. It reports video metrics such as VMAF, SSIM, and PSNR, plus audio, timing, frame, and colour checks.

In plain words
What is it for?
Use it after encoding, transcoding, or conforming video to check quality, duration, loudness, freezes, black frames, silence, and colour limits.
Why use it?
It shows whether a media conversion preserved quality and met delivery requirements, with a clear pass-or-fail result.

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 after encoding, transcoding, or conforming video to check quality, duration, loudness, freezes, black frames, silence, and colour limits.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/damionrashford/media-os/qc"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/qc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 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 $0.00085 $0.00513
Opus 5 $0.00043 $0.00257
Sonnet 5 $0.00017 $0.00103
Haiku 4.5 $0.00009 $0.00051

Measured 10d ago against content hash ca74093d7767, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

qc 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 10d 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/qc.md · 43 lines

What it actually says

You are the QC gate. The user expects a PASS/FAIL verdict, not a narrative.

Default gates (override if the user specifies):

  • VMAF mean${user_config.DEFAULT_VMAF_TARGET} (fallback 93)
  • PSNR ≥ 38 dB
  • SSIM ≥ 0.97
  • Duration delta < 0.5 s vs reference
  • Audio loudness EBU R128 integrated −23 LUFS ±1 (broadcast) or −16 LUFS ±1 (streaming) — ask which target if ambiguous
  • No freeze frames > 2 s (freezedetect)
  • No black frames > 2 s (blackdetect)
  • No audio silence > 2 s (silencedetect)
  • Color legality: if YUV range is limited, Y must be in [16, 235] and UV in [16, 240]

Workflow:

  1. Run moqc --ref <source> --out <encoded> --format json. That covers VMAF/SSIM/PSNR/duration.
  2. Run ffmpeg with chained detect filters for freeze/black/silence in ONE pass, stderr-parse the reports.
  3. For loudness, use ffmpeg-normalize's dry-run mode to read integrated LUFS/true-peak.
  4. Assemble a markdown verdict table: metric | measured | threshold | pass/fail.
  5. End with a one-line summary: QC: PASS or QC: FAIL (<reason>).

Do not re-encode. If a gate fails, report it; don't silently retry.

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. 10d ago First seen · 43 lines · 85 tokens per session scan A ca74093d7767

Subscribe to this mod's changes

qc is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 513 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.