ruly:decompose

A command that splits one Markdown document into separate files based on its section headings, while keeping an index linking them together.

In plain words
What is it for?
Use it to organize rules, standards, troubleshooting notes, or other sectioned Markdown files into a directory of smaller documents.
Why use it?
It makes a long document easier to maintain without losing the original file's Git history.

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/patrickclery/ruly/decompose
Clone the repo
git clone --depth 1 https://github.com/patrickclery/ruly

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,059 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 $0.00021 $0.02059
Opus 5 $0.00010 $0.01030
Sonnet 5 $0.00004 $0.00412
Haiku 4.5 $0.00002 $0.00206

Measured yesterday against content hash 37e8860e8d6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruly:decompose 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 yesterday.

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.

.claude/commands/ruly/decompose.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ruly:decompose Command

Overview

The /ruly:decompose command splits a markdown file into a directory of separate files based on its section headers. It uses git mv to preserve history, moving the original file to become the index file (_common-{tag}.md) that references all extracted sections via anchor links.

Usage

/ruly:decompose <file> <directory>

Arguments

  • <file> - The markdown file to decompose
  • <directory> - The name for the output directory (e.g., "standards", "patterns")

Examples

# Decompose common.md into a "standards" directory
/ruly:decompose rules/workaxle/core/frameworks/common.md standards

# Decompose debugging.md into a "troubleshooting" directory
/ruly:decompose rules/bug/debugging.md troubleshooting

Example Transformation

Before (rules/core/common.md):

---
description: Common Ruby patterns
globs:
  - '**/*.rb'
---

# Ruby Language Patterns

## Code Style

Content about code style...

## Error Handling

Content about error handling...

## Testing

Content about testing...

After decomposition into standards/:

rules/core/standards/
├── _common-ruby-language-patterns.md  # Index (original file, moved via git mv)
├── code-style.md                      # Extracted section
├── error-handling.md                  # Extracted section
└── testing.md                         # Extracted section

standards/_common-ruby-language-patterns.md (index):

---
description: Common Ruby patterns
globs:
  - '**/*.rb'
requires:
  - ./code-style.md
  - ./error-handling.md
  - ./testing.md
---
# Ruby Language Patterns

## Code Style

See [Code Style](#code-style) for code style patterns.

## Error Handling

See [Error Handling](#error-handling) for error handling patterns.

## Testing

See [Testing](#testing) for testing patterns.

standards/code-style.md:

---
description: Code style guidelines
alwaysApply: false
---

# Code Style

Content about code style...

Read the full file on GitHub · 302 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. yesterday First seen · 302 lines · 21 tokens per session scan A 37e8860e8d6f

Subscribe to this mod's changes

ruly:decompose is a command published in the GitHub repository patrickclery/ruly (5 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 2,059 once invoked, about $0.0001 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.