obsidian-untangle-knot

obsidian-untangle-knot is a skill for Claude Code, Codex from alexeyshishin/as-skill. It costs 226 tokens per session (8,653 once invoked), scanned A, original, MIT.

An Obsidian knowledge-base skill for untangling a hub note, or map of content, that has accumulated too many incoming links.

In plain words
What is it for?
Use it to create sub-maps from the hub's existing categories and redirect resource notes to the more specific maps.
Why use it?
It reduces the backlink noise that makes a general topic map hard to navigate, while keeping the original map as an entry point.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create sub-maps from the hub's existing categories and redirect resource notes to the more specific maps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexeyshishin/as-skill/obsidian-untangle-knot
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.

Any agent
npx skills add alexeyshishin/as-skill --skill obsidian-untangle-knot
Clone the repo
git clone --depth 1 https://github.com/alexeyshishin/as-skill

Made for: Claude Code, Codex.

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 obsidian-untangle-knot

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-untangle-knot/github.svg)](https://agentmods.dev/skills/alexeyshishin/as-skill/obsidian-untangle-knot)
Your own site
<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/obsidian-untangle-knot"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-untangle-knot/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 obsidian-untangle-knot

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/obsidian-untangle-knot"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-untangle-knot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,653 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 $0.00226 $0.08653
Opus 5 $0.00113 $0.04326
Sonnet 5 $0.00045 $0.01731
Haiku 4.5 $0.00023 $0.00865

Measured 11d ago against content hash c2b40b6cead6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

obsidian-untangle-knot 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.

domains/obsidian/skills/obsidian-untangle-knot/SKILL.md · 610 lines

How it starts

The opening of the file, as written. The whole thing — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.

obsidian-untangle-knot

Core idea

In a personal knowledge base, dozens or hundreds of notes end up linking to the same MOCs — that's natural: when you add an article, a book, or a new idea, it's easier to link to the general [[DevOps]] than to hunt for the specific sub-map. Over time the general MOC turns from a map into a backlink dump: you open it and drown in noise.

Out-links on a hub grow slowly (it's still a map, deliberately maintained). In-links grow spontaneously and fast. So the main signal of a tangle is high in-degree, not out-degree.

The skill:

  1. Finds/accepts a hub and counts its in/out links
  2. Relies on the hub's already-existing structure (subheadings, explicit categories) as ready-made landing points — it doesn't invent new categories when none were asked for
  3. Creates a sub-MOC for each category
  4. Main action: goes through incoming links from resource notes and switches them from the general MOC to the appropriate sub-MOC
  5. The original MOC stays — it remains the right entry point for the "don't know exactly where to link" case
before:                       after:
                             [hub] (~ stays, but fewer in-links)
[hub] ←── 200 in-links       ├── [sub-MOC A] ←── 60 in-links (former general ones)
  ├── 22 out-links           ├── [sub-MOC B] ←── 40
                             ├── [sub-MOC C] ←── 30
                             └── [sub-MOC D] ←── 25
                             (general, unclassified ~45 — stay on the hub)

Base rules (PARA, tags, templates, style, naming) — in .claude/rules/. In particular: knowledge-structures.md (MOC), note-types-frontmatter.md (frontmatter), workflows.md (plan → confirmation → action protocol), file-naming.md (names).

Vault root folder (<vault>/): set at install time (--vault or the OBSIDIAN_VAULT env var). See .claude/rules/vault-struct.md. Output language: Russian, technical terms in English.


When to use this and when not to

Read the full file on GitHub · 610 lines

Files

What ships with it

1 file 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.

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. 11d ago First seen · 610 lines · 226 tokens per session scan A c2b40b6cead6

Subscribe to this mod's changes

obsidian-untangle-knot is a skill published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 22d ago), licensed MIT. It adds 226 tokens to every session and 8,653 once invoked, about $0.0011 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.