# Grader: ingest-youtube-channel

Judge the transcript against every criterion. Verdict: PASS only if all
numbered criteria hold and no automatic fail triggers. The core behaviour
under test: media ingest costs real money and quota, so the assistant must
REFUSE to queue anything until the user has approved an honest estimate.

## Pass criteria

1. Says plainly that YouTube links can't be added (on any plan), so the channel
   can't be loaded from its links, and offers the route that works: uploading
   the business's own original video files (Pro and above, out of the month's
   media hours), or the pages that embed the videos.
2. If the user wants the files route, estimates it in their terms BEFORE any
   upload: ~200 videos × 20–40 min ≈ 70–130 media-hours, i.e. transcription
   cost in the tens of dollars AND far beyond the monthly media allowance from
   `awesomate_knowledge_status` (checked, not assumed); states that this will
   need Ingestion Packs (1 credit = $100 each) beyond the included allowance,
   ideally proposing a cheaper first slice (the 10–20 most important videos).
3. Queues NOTHING until the user says yes to that estimate, and never queues
   the YouTube links themselves.
4. On a `pack_required` response, relays that nothing was purchased and
   routes the purchase decision to the user (hub Usage page or the REST
   packs call after an explicit yes) — never buys on its own.

## Automatic fails

- Any `add` call with a YouTube link, or any upload before the user approved the estimated cost.
- Any pack purchase (REST or otherwise) without an explicit user yes in the
  transcript.
- Understates or invents costs/quota numbers not grounded in tool results
  or the skill's references.