split

split is a command for Claude Code from nguyennguyenit/MultiClaude. It costs 8 tokens per session (826 once invoked), scanned C, original, MIT.

A command that breaks a large IPA design document into smaller files organized in a folder. IPA refers to a structured software-documentation standard used here for requirements, APIs, databases, and interfaces.

In plain words
What is it for?
Use it to split API_SPEC, DB_DESIGN, or SRD documents by section and create supporting files such as an index and README. It can also detect all large documents automatically.
Why use it?
Smaller files are easier to navigate and update than one long document, especially when the document has at least 500 lines.

Command for Claude Code

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 commands/nguyennguyenit/multiclaude/split
Clone the repo
git clone --depth 1 https://github.com/nguyennguyenit/MultiClaude

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 split

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/split.svg)](https://agentmods.dev/commands/nguyennguyenit/multiclaude/split)
Your own site
<a href="https://agentmods.dev/commands/nguyennguyenit/multiclaude/split"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/split.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 826 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00008 $0.00826
Opus 5 $0.00004 $0.00413
Sonnet 5 $0.00002 $0.00165
Haiku 4.5 $0.00001 $0.00083

Measured 4d ago against content hash 817fb6fb852d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

split scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf docs/API_SPEC/
.claude/commands/ipa-docs/split.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Split large IPA documentation files (API_SPEC, DB_DESIGN, SRD) into modular folder structure when files exceed 500 lines.


Usage

# Split specific doc
/ipa-docs:split API_SPEC
/ipa-docs:split DB_DESIGN
/ipa-docs:split SRD

# Auto-detect and split all large docs
/ipa-docs:split

Output Structure

Before (Single File)

docs/
├── API_SPEC.md         # 800+ lines, hard to navigate

After (Modular)

docs/
├── API_SPEC/
│   ├── README.md       # Agent guide for this folder
│   ├── index.md        # Endpoint matrix (mục lục)
│   ├── auth.md         # /auth/* endpoints
│   ├── users.md        # /users/* endpoints
│   └── orders.md       # /orders/* endpoints

Workflow

Step 1: Analyze Document

  1. Read target doc (e.g., docs/API_SPEC.md)
  2. Check line count:
    • < 500 lines: Skip (no split needed)
    • ≥ 500 lines: Proceed with split
  3. Identify sections by headers (## or ###)

Step 2: Create Folder Structure

  1. Create folder: docs/{DOC_NAME}/
  2. Generate README.md:
# {DOC_NAME}

This folder contains modular IPA documentation split from {DOC_NAME}.md

## Files

| File | Description |
|------|-------------|
| index.md | Overview and navigation |
| {section}.md | {Section description} |

## Usage

Agent should read `index.md` first for overview, then specific files as needed.

Step 3: Generate index.md

Extract matrix/overview section:

  • For API_SPEC: Endpoint Matrix table
  • For DB_DESIGN: Table Matrix
  • For SRD: Requirements Matrix (FR-xx list)

Add links to detail files.

Step 4: Split Content

For each major section (identified by ## headers):

  1. Create {section-slug}.md
  2. Move section content
  3. Add backlink to index.md

Section Detection by Doc Type

API_SPEC.md

Split by API group:

  • Sections with /auth/*auth.md
  • Sections with /users/*users.md
  • Sections with /orders/*orders.md

DB_DESIGN.md

Split by domain:

  • User tables → users-tables.md
  • Order tables → orders-tables.md
  • System tables → system-tables.md

Read the full file on GitHub · 149 lines

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. 4d ago First seen · 149 lines · 8 tokens per session scan C 817fb6fb852d

Subscribe to this mod's changes

split is a command published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 23d ago), licensed MIT. It adds 8 tokens to every session and 826 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.