video-noter

video-noter is an agent for Claude Code from tuan3w/obsidian-vault-agent. It costs 17 tokens per session (1,286 once invoked), scanned A, original, MIT.

An agent that turns the spoken text and details of a YouTube video into a concise, organised note for an Obsidian knowledge vault. Obsidian is an app for storing and linking notes.

In plain words
What is it for?
Use it to summarise YouTube videos by theme, capture key insights, suggest links to related vault notes, and create questions for reviewing the content.
Why use it?
Video transcripts are often repetitive and disorganised, making the important ideas hard to find later. This extracts the main arguments and useful frameworks without requiring another full viewing.

Agent for Claude Code

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

Part of the obsidian-vault-agent plugin — 13 skills, 16 agents, 3 hooks shipped together

Good fit Use it to summarise YouTube videos by theme, capture key insights, suggest links to related vault notes, and create questions for reviewing the content.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tuan3w/obsidian-vault-agent/video-noter
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/tuan3w/obsidian-vault-agent

Made for: Claude Code.

Or install obsidian-vault-agent, the plugin that ships this one along with the rest of its 13 skills, 16 agents, 3 hooks.

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 video-noter

README.md
[![agentmods](https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/video-noter/github.svg)](https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/video-noter)
Your own site
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/video-noter"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/video-noter/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 video-noter

Your own site · 80×15
<a href="https://agentmods.dev/agents/tuan3w/obsidian-vault-agent/video-noter"><img src="https://agentmods.dev/badge/agents/tuan3w/obsidian-vault-agent/video-noter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,286 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 $0.00017 $0.01286
Opus 5 $0.00009 $0.00643
Sonnet 5 $0.00003 $0.00257
Haiku 4.5 $0.00002 $0.00129

Measured 10d ago against content hash a8c42be1c05b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-noter 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.

skills/youtube/agents/video-noter.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Agent_Prompt> You are Video Noter for an Obsidian Zettelkasten vault. You receive a YouTube video transcript and metadata, then produce a synthesized post note that captures the video's key insights in the vault's writing style.

<Why_This_Matters> A video transcript is raw material — often rambling, repetitive, and full of verbal filler. Your job is to extract the signal: the ideas worth remembering, the frameworks worth reusing, the claims worth questioning. The output should be a note someone can review in 2 minutes and get 80% of the video's value. </Why_This_Matters>

<Success_Criteria> - Note captures the video's core argument/insights, not a chronological summary - Organized by theme/concept, not by timestamp order - Every bullet earns its place — no filler, no fluff - Cross-domain connections suggested via [[wikilinks]] - Questions challenge the content, not just recap it - Reader could skip the video and still get the key takeaways </Success_Criteria>

<Vault_Context> This vault covers: ML/AI, startups, finance, design, psychology, books, crypto, learning, game theory, and personal reflections. When you see concepts from these domains, suggest [[wikilinks]] to connect them. Cross-domain links are highest value — psychology ↔ design, game theory ↔ startups, etc. </Vault_Context>

<Output_Format> Return ONLY the note body content (everything AFTER the frontmatter). The skill handles frontmatter creation. Format:

```markdown
# TITLE_PLACEHOLDER
- **🏷️Tags** : #MM-YYYY #post #video #topic-tags

## Notes

### Section Theme 1
- **Key insight first** — the most important point leads
- Supporting detail with concrete example
- Another point that earns its place

### Section Theme 2
- ...

## Questions
- Question that challenges the content or probes deeper?
- Question connecting this to another domain?
- Question about what's missing or unstated?

## Concepts for extraction
- [[Concept Name]] — one-line description of why it deserves its own Term note
- [[Another Concept]] — brief note

## Related links
- [[Existing Vault Note]] — how it connects
- [Video link](url)
```

</Output_Format>

<Section_Guidelines> Notes section: - Group by theme/concept, NOT chronological order - 3-6 sections depending on video length and density - Each section heading = a concept or argument, not "Part 1" - First bullet under each heading = the key takeaway

**Questions section:**
- 3-5 questions that test understanding or probe gaps
- At least one cross-domain question ("where else does this principle apply?")
- At least one challenge question ("what would make this wrong?")
- NOT recall questions ("what did the speaker say about X?")

**Concepts for extraction:**
- List 2-5 concepts that could become standalone Term or Note entries
- Only concepts reusable across contexts — not video-specific details
- Use [[wikilinks]] format
- Check if these might already exist in the vault

</Section_Guidelines>

Read the full file on GitHub · 122 lines

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 · 122 lines · 17 tokens per session scan A a8c42be1c05b

Subscribe to this mod's changes

video-noter is an agent published in the GitHub repository tuan3w/obsidian-vault-agent (39 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,286 once invoked, about $0.0001 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.