agent-md-refactor

Refactor bloated agent instruction files into a progressive disclosure system with linked guidelines.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/iFor-Lux/LuxuryCheats --skill agent-md-refactor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-md-refactor
Source: https://github.com/iFor-Lux/LuxuryCheats/tree/main/.agents/skills/agent-md-refactor
Command: npx skills add https://github.com/iFor-Lux/LuxuryCheats --skill agent-md-refactor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams avoid bloated agent instruction files by applying progressive disclosure, moving detailed guidelines into linked, categorized files while keeping a concise root document.

Core Features & Use Cases

  • Root minimalization: Keeps the root file compact with essentials.
  • Linked guideline files: Creates a dedicated .claude directory with topic-specific docs (typescript.md, testing.md, code-style.md, git-workflow.md, architecture.md).
  • Structured, actionable guidance: Each linked file is self-contained and actionable for teams integrating agent instructions.

Quick Start

Refactor my AGENTS.md into progressive disclosure by creating a minimal root file and a .claude directory with topic-specific guidelines.

Frequently Asked Questions about agent-md-refactor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I refactor a bloated AGENTS.md file into modular guidelines?

You refactor bloated agent docs by applying progressive disclosure, moving detailed instructions into linked, categorized files under a .claude directory while keeping a concise root reference.

What is progressive disclosure for agent instruction files?

Progressive disclosure is a structuring technique that minimizes the root agent document by linking out to self-contained, topic-specific guideline files, preventing context bloat and ensuring consistent execution.

How do I organize code style and git workflow guidelines for AI agents?

You organize guidelines by creating topic-specific markdown files such as code-style.md, git-workflow.md, and architecture.md inside a dedicated .claude directory, linking them from the root file.

When do I need to split agent instructions into linked files?

You need linked files when your root agent instructions become bloated, making it difficult to maintain actionable, self-contained guidance for categories like typescript, testing, and architecture.

Can I use a minimal root document with linked files for team agent guidelines?

Yes, keeping a minimal root document with linked, categorized guideline files enables teams to safely maintain structured, actionable instructions across topics like git workflow and code style.

What are the limitations of keeping all agent instructions in a single root file?

A single root file becomes bloated and hard to maintain, reducing execution consistency and making it difficult to safely update self-contained guidelines for specific topics like testing or architecture.