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 agentmods add skills/alexeyshishin/as-skill/obsidian-split-notenpx skills add alexeyshishin/as-skill --skill obsidian-split-notegit 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-split-note)<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>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 | $0.00071 | $0.00924 |
| Opus 5 | $0.00036 | $0.00462 |
| Sonnet 5 | $0.00014 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00092 |
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.
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/downare 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:
- File name — see
file-naming.md. For a series from one source:<Parent> – <Concept>.md. For a standalone one: a substantive claim-based name. - Structural tag + folder — per
tags.md(usually#thought→03. Ресурсы/<Тема>/База знаний/). - Frontmatter — from the matching template in
_Система/templates/(seetemplate-usage.md).upgets a wikilink to the original. - Body — transfer the section's content under the heading
## Суть(or## Идея/## Определениеdepending on type). - 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]]
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.
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.
- 6d ago First seen · 88 lines · 71 tokens per session scan A db2b9a5b972f
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.
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.
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…
harness-engineering
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.
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.
agentic-engineering
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.
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.