ruly:compress

A command that examines Markdown rule files for repeated text, similar examples, duplicated explanations, and other patterns that could be consolidated.

In plain words
What is it for?
Use it on individual rule files or directories to find duplicate content, reusable code examples, repeated explanations, common structures, and cross-references. It can suggest consolidation and may apply the improvements.
Why use it?
Repeated guidance makes documentation harder to maintain and can cause rules to drift apart. The command identifies places where the files could follow the DRY principle, meaning “Don't Repeat Yourself.”

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

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,799 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 $0.00018 $0.01799
Opus 5 $0.00009 $0.00899
Sonnet 5 $0.00004 $0.00360
Haiku 4.5 $0.00002 $0.00180

Measured 2d ago against content hash 359424b7a007, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruly:compress 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 2d 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.

.claude/commands/ruly/compress.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ruly:compress Command

Overview

The /ruly:compress command analyzes Claude Code markdown rule files to identify redundancies, repeated patterns, and opportunities to make the documentation more DRY (Don't Repeat Yourself). It suggests consolidation strategies and can optionally apply the improvements.

Usage

/ruly:compress <directories/files...>

Arguments

  • <directories/files...> - One or more markdown files or directories containing rule files to analyze

Examples

# Analyze a single file
/ruly:compress rules/workaxle/core/essential/common.md

# Analyze an entire directory
/ruly:compress rules/workaxle/core/

# Analyze multiple directories
/ruly:compress rules/workaxle/core/ rules/github/pr/

# Analyze all rules
/ruly:compress rules/

Analysis Process

1. Pattern Detection

The command identifies:

  • Duplicate content blocks - Exact or near-exact text appearing in multiple files
  • Similar code examples - Code snippets with minor variations that could use a template
  • Repeated explanations - Concepts explained multiple times across files
  • Common patterns - Frequently used structures that could be extracted
  • Cross-references - Multiple files referencing the same concept

2. Redundancy Types

Content Duplication
# Found in 3 files:
"Always use Make commands, never run commands directly"
→ Suggestion: Create central command reference
Pattern Repetition
# Found in 5 files with slight variations:
Employee.dataset.not_deleted.where(company:)
→ Suggestion: Extract to common query pattern
Concept Re-explanation
# Soft-delete handling explained in:
- essential/common.md (full explanation)
- testing/specs.md (partial explanation)
- services/patterns.md (brief mention)
→ Suggestion: Single source with references

3. Compression Strategies

Strategy 1: Extract Common Patterns
  • Create a central patterns/ directory for reusable patterns
  • Reference patterns instead of duplicating them
  • REQUIRED: Add extracted file to requires: frontmatter (see below)

Read the full file on GitHub · 306 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. 2d ago First seen · 306 lines · 18 tokens per session scan A 359424b7a007

Subscribe to this mod's changes

ruly:compress is a command published in the GitHub repository patrickclery/ruly (5 stars, last pushed 7d ago), licensed MIT. It adds 18 tokens to every session and 1,799 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.