agents-progressive-disclosure

Name: agents-progressive-disclosure
Availability: InStock
Author: Caph

Refactor bloated agent instruction files into compact routing entrypoints with progressive disclosure.

72|3|Updated May 28, 2026

Search Tags:#prompt engineering #claude.md #progressive disclosure #agent instructions #documentation refactor #agnts.md #docs routing

Ready to run

npx skills add https://github.com/Caph-dev/agents-progressive-disclosure --skill agents-progressive-disclosure

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agents-progressive-disclosure
Source: https://github.com/Caph-dev/agents-progressive-disclosure/tree/main
Command: npx skills add https://github.com/Caph-dev/agents-progressive-disclosure --skill agents-progressive-disclosure

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you shrink oversized agent instruction files into a compact entrypoint plus focused on-demand reference docs, making them easier to load, read, and maintain.

Core Features & Use Cases

Instruction Refactoring: Rewrites bloated AGENTS.md, CLAUDE.md, and similar files into a small router-style root file.
Progressive Disclosure: Moves detailed project rules, workflows, and examples into targeted docs that are only read when needed.
Validation and Preservation: Checks for contradictions, keeps critical always-on rules in the entrypoint, and verifies that the original intent is still preserved.
Use Case: Use it when a project’s agent instructions have grown too large and need to be reorganized into a maintainable root file with supporting documentation.

Quick Start

Use the agents-progressive-disclosure skill to refactor the current AGENTS.md into a compact entrypoint plus focused docs that preserve the original rules.

Frequently Asked Questions about agents-progressive-disclosure

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

FAQPage Schema

How do I refactor bloated CLAUDE.md or AGENTS.md files?▼

To refactor bloated CLAUDE.md or AGENTS.md files, rewrite them into a compact routing entrypoint that splits always-on guidance from on-demand documentation. This progressive disclosure approach preserves original rule intent while making project-level instructions easier to load and maintain.

What is progressive disclosure for agent instructions?▼

Progressive disclosure for agent instructions is a documentation pattern that moves detailed project rules and workflows into targeted on-demand docs. It keeps a compact root file as a router, ensuring AI agents only load specific guidance when needed, reducing context bloat.

How do I split always-on rules from on-demand documentation?▼

Split always-on rules from on-demand documentation by clustering related instructions and classifying contradictions within the original file. Keep critical guidance in the root entrypoint and route detailed workflows to separate docs that agents read only when required.

Does this approach work with GEMINI.md and other project rule files?▼

Yes, this refactoring approach works with GEMINI.md and similar project-level rule files. It applies docs-based routing to any oversized agent instruction file, validating that the rewritten structure still tells future agents what to read while preserving the original rules.

When do I need to restructure my project's agent instruction files?▼

You need to restructure agent instruction files when they have grown too large to load and maintain effectively. If your AGENTS.md or CLAUDE.md contains bloated, contradictory, or clustered rules that hinder agent readability, progressive disclosure is required.

What is the best way to organize large agent documentation?▼

The best way to organize large agent documentation is creating a router-style root file that directs agents to focused reference docs. This prevents context overflow, validates rule preservation, and ensures agents read only necessary instructions for a specific task.