logseq-youtube-notes

A set of rules for organizing notes from YouTube videos in Logseq, a block-based note-taking app. It places timestamped headings under the embedded video so sections can be opened at the matching moments.

In plain words
What is it for?
Use it to structure YouTube transcripts in Logseq, add timestamp-based sections and subsections, and arrange notes beneath an embedded video.
Why use it?
It keeps transcript notes readable and makes their sections clickable at the relevant points in the video. It also guides cleanup of transcript wording and technology names.

Cursor rule

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.

agentmods
npx agentmods add rules/codekiln/logseq-cursor-rules/logseq-youtube-notes
Clone the repo
git clone --depth 1 https://github.com/codekiln/logseq-cursor-rules
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.01723
Opus 5 $0.00006 $0.00861
Sonnet 5 $0.00003 $0.00345
Haiku 4.5 $0.00001 $0.00172

Measured yesterday against content hash dba50cb5cbe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logseq-youtube-notes 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 yesterday.

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.

logseq-youtube-notes.mdc · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Logseq-Flavored Markdown (LFM) YouTube transcript headings

This rule applies to 'pages/*.md' that have a YouTube video with a transcript. It is an extension to Logseq Flavored Markdown (project rule in logseq-flavored-markdown.mdc).

Youtube video begins with a block like this:

	- ## [[Video]]
		- {{video https://www.youtube.com/watch?v=abcdefghijklmnop}}
			- NOTES SHOULD GO HERE UNDERNEATH THE VIDEO

Basic Transcript Organization

The transcript should be organized with logical sections and proper hierarchical headings. Each major section should start with a timestamp-based heading. THE HEADINGS MUST BE NESTED UNDER THE VIDEO AND INCLUDE TIMESTAMPS for them to be clickable in logseq. Maintain proper logseq-flavored markdown throughout. Use quotes from the transcript and clean up the transcript, attempting to fix spelling or technology names where appropriate. The transcript of youtube videos is done by AI and may contain mistakes you should try to correct based on the context.

Heading Structure

  • Use ### {{youtube-timestamp X}} for main sections
  • Use #### for subsections
  • Use ##### for detailed points within subsections
  • Always maintain proper indentation using TABs

Semantic Linking / Logseq Page Links

  • Convert relevant terms into Logseq Page Links using [[Topic]] format if and onl if a given Logseq Page is known known to exist
  • Do not invent link to Logseq Pages that do not already exist
    • if you invent a logseq page to link to it will just introduce a duplicate into the knowledge management system, so do not do that
  • Some common ones you CAN use
    • #Example
    • [[AI Coding]]
    • [[Py]] for python
    • see pages/Index.md for a list of pages you can link to

Content Formatting

  • Break long monologues into natural speech patterns
  • Use bullet points for lists and sub-points
  • Use bold for emphasis on key concepts
  • Group related ideas under appropriate subheadings

Example of Improved Formatting:

Read the full file on GitHub · 111 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. yesterday First seen · 111 lines · 13 tokens per session scan A dba50cb5cbe1

Subscribe to this mod's changes

logseq-youtube-notes is a cursor rule published in the GitHub repository codekiln/logseq-cursor-rules (2 stars, last pushed 10mo ago), licensed MIT. It adds 13 tokens to every session and 1,723 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 2026-08-31.