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 alexeyshishin/as-skill --skill obsidian-untangle-knotgit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/obsidian-untangle-knot)<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.
<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>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 | $0.00226 | $0.08653 |
| Opus 5 | $0.00113 | $0.04326 |
| Sonnet 5 | $0.00045 | $0.01731 |
| Haiku 4.5 | $0.00023 | $0.00865 |
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.
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:
- Finds/accepts a hub and counts its in/out links
- 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
- Creates a sub-MOC for each category
- Main action: goes through incoming links from resource notes and switches them from the general MOC to the appropriate sub-MOC
- 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
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.
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 · 610 lines · 226 tokens per session scan A c2b40b6cead6
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.
Other skills, from other repositories
knowledge-ops
Use when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt queues, or governed Agent/Wiki promotion.
context-manager
Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing.
session-learn
Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a traceable next action.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
cds-stats
Show project memory statistics: session count, observation counts by type, entity count, top entities, and project planning status.
cds-search
Search past session observations using the sessions.search MCP tool. Falls back to CLI if the MCP server is not available.