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.
npx skills add tuan3w/obsidian-vault-agent --skill youtubegit clone --depth 1 https://github.com/tuan3w/obsidian-vault-agentWrote 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/tuan3w/obsidian-vault-agent/youtube)<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/youtube"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/youtube/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.
<a href="https://agentmods.dev/skills/tuan3w/obsidian-vault-agent/youtube"><img src="https://agentmods.dev/badge/skills/tuan3w/obsidian-vault-agent/youtube.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00080 | $0.01618 |
| Opus 5 | $0.00040 | $0.00809 |
| Sonnet 5 | $0.00016 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
youtube 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 11d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- User shares a YouTube URL and wants notes taken
- User says "take notes from this video"
- User pastes a YouTube link with /youtube
- User wants to add a video's insights to the vault </Use_When>
<Do_Not_Use_When>
- User wants to watch or download the video itself
- User has a local video file (not YouTube)
- Video has no transcript/captions at all
- User wants to process an existing vault note (use /process) </Do_Not_Use_When>
<Execution_Policy>
- Extract first, synthesize second, integrate third
- Always check vault for existing notes on the same video before creating
- Create note as type: post with processing_status: inbox
- The note is a starting point — user can /process it later for deeper engagement </Execution_Policy>
Stage 1: EXTRACT
Parse the YouTube URL/ID from $ARGUMENTS. If no URL provided, ask the user.
Run the extraction script. Redirect stdout to a temp file (stderr has progress messages that break piping):
SKILL_DIR="${CLAUDE_SKILL_DIR}"
YT_OUTPUT="$SKILL_DIR/_output.json"
uv run "$SKILL_DIR/scripts/fetch_youtube.py" "VIDEO_URL" --lang en > "$YT_OUTPUT"
Then read $YT_OUTPUT with the Read tool to get the JSON. Clean up the file after use.
The JSON contains:
title,channel,duration,upload_date,description,chapterstranscript.full_text,transcript.segments,transcript.languagetranscript.error(null if success)
If transcript.error is not null: inform the user and stop. No note without content.
If transcript is very long (>50,000 chars): warn the user this is a long video. Chunk the transcript for the agent if needed — send first 40,000 chars with a note about total length. For very long videos (>2hrs), consider suggesting the user watch key sections instead.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 198 lines · 80 tokens per session scan A 36fd74ef0c13
youtube is a skill published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 1,618 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.
Other skills, from other repositories
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
setup-vault-types
Use when configuring which document types a vault tracks: after installing ai-brain-starter, when a new kind of note appears (journals, books, meetings, clients, podcasts, travel, WhatsApp/Slack/iMessage exports), when extraction skips files because no extractor matches their type, or to add, list, or remove a custom…
ingest-health
Use when the user says /ingest-health, asks to import, sync, ingest, or load Apple Health / Apple Watch / HealthKit data, has a fresh export.zip from the iPhone Health app, a Simple Health Export CSV folder, or a Health Auto Export TCP live feed, or when health-mcp queries return empty because no data was ever…
takeout-pull
Stop a Google Takeout export from expiring undownloaded: detect the ready-to-download mails with a deterministic zero-token scan, report the live links with days remaining, then drive the download and vault import. Triggers: "/takeout-pull", "is my takeout ready", "pull my takeout".
whatsapp-sync
Refresh WhatsApp text into an Obsidian vault (data layer, dashboard, group labels, contact notes). Text only, never downloads media, and pulls the recent window the live companion bridge exposes rather than a full multi-year archive. Semi-automatic by design: it drives the live bridge and needs the phone nearby.…
gitbook-import
Import a GitBook space (company docs, a whitepaper) into an Obsidian vault as linked atomic notes plus a map-of-content, concept links and a RAG reindex. Idempotent re-import supported. Triggers: "/gitbook-import ", "import this gitbook", "gitbook to vault".