youtube-to-knowledge: Command for Claude Code

.claude/commands/kg_navigator.md

kg_navigator is a command for Claude Code from velmighty/youtube-to-knowledge. It costs 0 tokens per session (322 once invoked), scanned A, original, MIT.

A knowledge-graph command that tracks entities and specific relationships across processed videos. A knowledge graph is a structured collection of things and the connections between them.

In plain words
What is it for?
Use it to extract verifiable relationships, merge them into an existing graph, compare entities across videos, and find the most connected topics or people.
Why use it?
It helps combine findings from multiple videos without creating duplicate entities or replacing relationships already recorded.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is velmighty/youtube-to-knowledge's own configuration. It tells Claude Code how to work on youtube-to-knowledge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything youtube-to-knowledge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to velmighty/youtube-to-knowledge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/velmighty/youtube-to-knowledge/main/.claude/commands/kg_navigator.md
Clone the repo
git clone --depth 1 https://github.com/velmighty/youtube-to-knowledge

Made for: Claude Code.

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 kg_navigator

README.md
[![agentmods](https://agentmods.dev/badge/commands/velmighty/youtube-to-knowledge/kg_navigator/github.svg)](https://agentmods.dev/commands/velmighty/youtube-to-knowledge/kg_navigator)
Your own site
<a href="https://agentmods.dev/commands/velmighty/youtube-to-knowledge/kg_navigator"><img src="https://agentmods.dev/badge/commands/velmighty/youtube-to-knowledge/kg_navigator/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 kg_navigator

Your own site · 80×15
<a href="https://agentmods.dev/commands/velmighty/youtube-to-knowledge/kg_navigator"><img src="https://agentmods.dev/badge/commands/velmighty/youtube-to-knowledge/kg_navigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 322 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 $0.00000 $0.00322
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 9d ago against content hash b050eacb20db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kg_navigator 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 9d 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.

.claude/commands/kg_navigator.md · 27 lines

What it actually says

Knowledge graph specialist for entity relationships across videos.

Entity resolution

  • Use canonical full names: "Michał Sadowski" not "Mike". Check metadata.json for channel/speaker names.
  • Before adding a node, search existing graph.json for equivalent nodes (e.g., "AI" = "Artificial Intelligence").
  • Normalize: strip whitespace, consistent capitalization.

Triplet quality rules

  • Predicates MUST be specific verbs: "founded", "acquired", "recommends", "competes_with", "increased_by".
  • NEVER use vague predicates: "is related to", "is associated with", "is connected to", "involves".
  • Each triplet must be verifiable from the transcript. No inferences.

Depth tiers

  • light (8-12 triplets): Primary entities and direct relationships only.
  • standard (15-20 triplets): People, companies, tools, concepts.
  • deep (25-35 triplets): Add causal chains, temporal relations, attributed claims, quantities.

Graph operations

  • Update: python src/graph_extractor.py <dir> <dir>/triplets.json
  • Always load existing graph.json first — merge, don't replace.
  • Find hubs: nodes with highest degree are key entities.
  • Cross-video: check all vault/content/*/graph.json for shared nodes before extracting.

Data sources

  • Per-video: vault/content/<channel>/graph.json, graph.html
  • Triplets: vault/content/<channel>/triplets.json
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. 9d ago First seen · 27 lines · 0 tokens per session scan A b050eacb20db

Subscribe to this mod's changes

kg_navigator is a command published in the GitHub repository velmighty/youtube-to-knowledge (59 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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.