notes: Skill for Claude Code

.agents/skills/splitting-notes/SKILL.md

splitting-notes is a skill for Claude Code from sabertaz/notes. It costs 43 tokens per session (1,288 once invoked), scanned A, original, MIT.

A note-organization workflow that splits very large or hard-to-navigate note files into smaller topic-focused files with index files.

In plain words
What is it for?
Use it when notes exceed 1,000 lines, combine unrelated topics, or are difficult to search and navigate.
Why use it?
It reduces the effort needed to understand and find information in notes that are too long, mixed, or poorly organized.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is sabertaz/notes's own configuration. It tells Claude Code how to work on notes 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 notes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sabertaz/notes. 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/sabertaz/notes/main/.agents/skills/splitting-notes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sabertaz/notes

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 splitting-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/sabertaz/notes/splitting-notes/github.svg)](https://agentmods.dev/skills/sabertaz/notes/splitting-notes)
Your own site
<a href="https://agentmods.dev/skills/sabertaz/notes/splitting-notes"><img src="https://agentmods.dev/badge/skills/sabertaz/notes/splitting-notes/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 splitting-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/sabertaz/notes/splitting-notes"><img src="https://agentmods.dev/badge/skills/sabertaz/notes/splitting-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,288 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00043 $0.01288
Opus 5.5 $0.00017 $0.00515
Sonnet 5.5 $0.00009 $0.00258
Haiku 4.5 $0.00004 $0.00129

Measured 2mo ago against content hash 4c7ef43b425a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

splitting-notes 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 2mo 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.

.agents/skills/splitting-notes/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Splitting Notes

Overview

Split large monolithic note files into focused, single-topic files with index-based navigation. Reduces cognitive load and improves discoverability through progressive grouping.

When to Use

digraph when_refactor {
  "Note file size > 1000 lines?" [shape=diamond];
  "Topics mixing unrelated concepts?" [shape=diamond];
  "Hard to find specific information?" [shape=diamond];
  "Refactor notes" [shape=box];
  "Keep as-is" [shape=box];

  "Note file size > 1000 lines?" -> "Refactor notes" [label="yes"];
  "Note file size > 1000 lines?" -> "Topics mixing unrelated concepts?" [label="no"];
  "Topics mixing unrelated concepts?" -> "Refactor notes" [label="yes"];
  "Topics mixing unrelated concepts?" -> "Hard to find specific information?" [label="no"];
  "Hard to find specific information?" -> "Refactor notes" [label="yes"];
  "Hard to find specific information?" -> "Keep as-is" [label="no"];
}

Use when:

  • Note files exceed 1000 lines
  • Single file mixes unrelated topics
  • Navigation and search are difficult
  • Content needs better organization

Don't use when:

  • Files are already under 500 lines
  • Topics are tightly coupled
  • Splitting would harm coherence

Prerequisite

Complex multi-step refactoring - Must complete planning phase first.

If not currently in plan mode, invoke EnterPlanMode before starting.

  • In plan mode: Complete analysis and create migration plan
  • After plan mode: Execute split and verification

Core Pattern

Before - Monolithic file:

content/topic/large-file.md (1500+ lines)
├── H2 Chapter 1
├── H2 Chapter 2
├── H2 Chapter 3
└── ...10+ more sections

After - Modular structure:

content/topic/
├── topic.md (index, ~50 lines)
├── chapter-1.md (~200 lines)
├── chapter-2.md (~150 lines)
├── chapter-3.md (~180 lines)
└── ...remaining chapters

See examples.md for complete walkthroughs of:

  • Simple split (300 lines, Python)
  • Medium split (850 lines, Vue)
  • Complex split (1500 lines, React)

Read the full file on GitHub · 158 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. 2mo ago First seen · 158 lines · 43 tokens per session scan A 4c7ef43b425a

Subscribe to this mod's changes

splitting-notes is a skill published in the GitHub repository sabertaz/notes (48 stars, last pushed 22d ago), licensed MIT. It adds 43 tokens to every session and 1,288 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

splitting-notes compared with skills from other repositories

splitting-notes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
splitting-notessabertaz/notesSkill4822d agoMITA43Claude Code
preline-mcphtmlstreamofficial/prelineSkill6.5k2mo agononeA66Codex
preline-theme-generatorhtmlstreamofficial/prelineSkill6.5k2mo agononeA89Claude Code, Codex
prettier-docspledgeandgrow/pledge-skillsSkill103mo agoMITA34Claude Code, Codex
fund-holding-viewerwhjin/fundscopeSkill117d agononeA77Claude Code, Codex
accessibility-championAtulPurohit/Antigravity-Awesome-SkillsSkill43mo agononeA26Claude Code, Codex
angular-enterpriseAtulPurohit/Antigravity-Awesome-SkillsSkill43mo agononeA25Claude Code, Codex