obsidian-split-note

obsidian-split-note is a skill for Claude Code, Codex from alexeyshishin/as-skill. It costs 71 tokens per session (924 once invoked), scanned A, original, MIT.

An Obsidian refactoring skill that divides one large note into smaller atomic or topic-focused notes while preserving links between them.

In plain words
What is it for?
Use it to identify sections worth extracting, create child notes in the right PARA folders, and replace those sections with links to the new notes.
Why use it?
It makes a long note easier to navigate without losing the original note or its connections.

Skill for Claude CodeCodex

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

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 skills/alexeyshishin/as-skill/obsidian-split-note
Any agent
npx skills add alexeyshishin/as-skill --skill obsidian-split-note
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-split-note

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-split-note.svg)](https://agentmods.dev/skills/alexeyshishin/as-skill/obsidian-split-note)
Your own site
<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/obsidian-split-note"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/obsidian-split-note.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 924 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 5.1 $0.00071 $0.00924
Opus 5 $0.00036 $0.00462
Sonnet 5 $0.00014 $0.00185
Haiku 4.5 $0.00007 $0.00092

Measured 6d ago against content hash db2b9a5b972f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

obsidian-split-note 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 6d 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-split-note/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

obsidian-split-note

Splits one large note into several smaller ones (atomic or thematic) while preserving connectivity:

  • the original stays, its sections are replaced with a short description + [[wikilink]];
  • each new note is created in the correct PARA folder;
  • the frontmatter of the original and the new notes is kept consistent (up/down are set).

Base rules (PARA, tags, frontmatter, style, file names) — in .claude/rules/. In particular: tags.md (the "Structural tags" section), note-types-frontmatter.md, knowledge-structures.md (atomic notes), file-naming.md.


Algorithm

1. Read and identify candidates

Criteria for "extract / keep" — knowledge-structures.md (the "When to split a section into its own note" section). Determine the original's overall topic and the list of candidates.

2. Show the plan and wait for confirmation

Plan → confirmation → action protocol — workflows.md. Plan format:

Original: [[Title]] (topic: …)
Extract:
  1. [[New note 1 name]] → 03. Ресурсы/<Тема>/База знаний/ (#thought)
  2. [[New note 2 name]] → 02. Сферы/07. Карты/ (#moc)
Leave in the original: intro paragraph, short conclusion

3. Create the child notes

For each one:

  1. File name — see file-naming.md. For a series from one source: <Parent> – <Concept>.md. For a standalone one: a substantive claim-based name.
  2. Structural tag + folder — per tags.md (usually #thought03. Ресурсы/<Тема>/База знаний/).
  3. Frontmatter — from the matching template in _Система/templates/ (see template-usage.md). up gets a wikilink to the original.
  4. Body — transfer the section's content under the heading ## Суть (or ## Идея / ## Определение depending on type).
  5. Before creating — run rg -l "Concept name" . to avoid duplicates.

4. Update the original

Each extracted section is replaced with a short description + link:

### Виртуальная память

ОС создаёт иллюзию единого адресного пространства. Подробнее: [[Виртуальная память]]

Read the full file on GitHub · 88 lines

Files

What ships with it

2 files 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. 6d ago First seen · 88 lines · 71 tokens per session scan A db2b9a5b972f

Subscribe to this mod's changes

obsidian-split-note is a skill published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 17d ago), licensed MIT. It adds 71 tokens to every session and 924 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

loop-engineering

Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.

Mark393295827/third-brain-v7-skills · 35 tokens

obsidian

Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.1, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use…

gapmiss/obsidian-plugin-skill · 105 tokens

harness-engineering

Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.

Mark393295827/third-brain-v7-skills · 34 tokens

agent-teams-command

Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command scaled from 5 to 100+ agents.

Mark393295827/third-brain-v7-skills · 39 tokens

agentic-engineering

Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.

Mark393295827/third-brain-v7-skills · 33 tokens

anthropic-os

Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B creativity, experiments, and prediction-error learning.

Mark393295827/third-brain-v7-skills · 42 tokens