Borrowing it
Nothing to install: this file belongs to nsokin/leia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nsokin/leia/main/.agents/skills/yoto/SKILL.mdgit clone --depth 1 https://github.com/nsokin/leiaWrote 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.
[](https://agentmods.dev/skills/nsokin/leia/yoto)<a href="https://agentmods.dev/skills/nsokin/leia/yoto"><img src="https://agentmods.dev/badge/skills/nsokin/leia/yoto.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00075 | $0.01698 |
| Opus 5 | $0.00037 | $0.00849 |
| Sonnet 5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00007 | $0.00170 |
Grade A, and why
yoto 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yoto card builder
Turn a playlist into a Yoto MYO card. The CLI does the mechanical work; your job is the judgment it cannot do: which items are worth putting on a card, how to name the chapters, and how to fit them inside the card's limits.
Run everything from the Leia repo directory.
Never download before you have looked
Always start with --list. It enumerates without fetching a byte, and answers
the three questions that decide everything else:
node src/cli.ts "<url>" --list --spoken
It reports every item with its duration, marks any that repeat an earlier title, and estimates how many cards the runtime needs. A playlist that looks like "100 episodes" is routinely 85 once repeat uploads are removed.
If the user has not set up yet, or something behaves oddly, node src/cli.ts --doctor reports node, yt-dlp, ffmpeg, client ID and sign-in state in one go.
Then decide four things
1. Does it fit? A card holds 100 tracks and 500 MB. At --spoken that is
roughly 16 to 18 hours. If the listing needs more than one card, say so plainly
with the numbers and ask what the user wants on the first one. Do not silently
truncate, and do not start a multi-hour job without agreement.
2. Are there duplicates? If --list marks repeats, add --dedupe. Mention
how many it drops and how much runtime that saves.
3. Which items, and in what order? For a child's card, prefer individual
episodes over hour-long compilations: each item becomes its own chapter, so
short episodes give buttons that skip somewhere useful. A card of six 10-minute
episodes is far more usable than one 60-minute block. Pass the choice as
--select "1,2,3,9-12" using the positions from the listing.
--select keeps the order you write, so when a playlist is uploaded out of
sequence, work out the right running order and write the positions in it. A
season listed as episode 24, 40, 1, 13 becomes a card in episode order only if
you ask for it. Add --number so the position shows in the app's chapter list,
not just on the player's screen.
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.
- 6d ago First seen · 138 lines · 75 tokens per session scan A 4484d5c386aa
yoto is a skill published in the GitHub repository nsokin/leia (4 stars, last pushed 26d ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,698 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 2026-08-31.
Other skills, from other repositories
claude-real-video
Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.
stage-compose
Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…