I want you to refactor my AGENTS.md file to follow progressive disclosure principles.
Follow these steps:
1. **Find contradictions**: Identify any instructions that conflict with each other. For each contradiction, ask me which version I want to keep.
2. **Identify the essentials**: Extract only what belongs in the root AGENTS.md:
- One-sentence project description
- Package manager (if not npm)
- Non-standard build/typecheck commands
- Anything truly relevant to every single task
3. **Group the rest**: Organize remaining instructions into logical categories (e.g., TypeScript conventions, testing patterns, API design, Git workflow). For each group, create a separate markdown file.
4. **Create the file structure**: Output:
- A minimal root AGENTS.md with markdown links to the separate files
- Each separate file with its relevant instructions
- A suggested docs/ folder structure
5. **Flag for deletion**: Identify any instructions that are:
- Redundant (the agent already knows this)
- Too vague to be actionable
- Overly obvious (like "write clean code")Fix A Broken AGENTS.md With This Prompt
If you're starting to get nervous about the AGENTS.md file in your repo, and you want to refactor it to use progressive disclosure, try copy-pasting this prompt into your coding agent
Services with a clipboard icon will copy the prompt to your clipboard first.
Version History
Prompt documentation
Related Prompts
moltbot(aka.ClawdBot) insipred skill - A disciplined approach to version control and iterative development that enables high-frequency commits while maintaining stability and traceability.
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
As a Senior Software Engineer with 7 years of experience at Amazon, Disney, and Capital One, having shipped code that impacts millions of users and built highly reliable systems, and now serving as CTO of a startup specializing in enterprise AI agents, I have extensively used Claude Code as my daily driver. Based on my experience building robust systems for complex enterprise workloads, I have compiled a beginner's playbook for effectively leveraging Claude Code. This playbook details strategies and techniques to maximize the quality and reliability of AI-generated code.
Comments (0)
Be the first to comment
to start the conversation.