Agentic Structure

A collaboration-first guideline framework for AI agents to make programming more efficient. The goal is to get better outcomes through user ↔ agent feedback, rather than the agent planning and executing everything alone.

Table of Contents

• How to use
• Guideline docs
• Contributing
• License
• Star History

How to use

This framework is available as a Claude Skill. Install it using Claude Code:

/plugin marketplace add BackGwa/Agentic-Structure
/plugin install agentic-structure@agentic-structure

Or manually add this repository's .claude-plugin folder to your project.

Guideline docs

Document	What it covers
DEVELOPMENT_PROCESS.md	Principles for clear, safe, production-ready, maintainable development
CODING_STANDARDS.md	Coding rules for clarity, structure, reuse, and maintainable change
ERROR_HANDLING.md	Error handling principles, boundaries, and security-minded failures
SECURITY_GUIDELINES.md	Secure defaults for secrets, hashing, auth, and production exposure
DISCUSSION_GUIDELINES.md	When and how to run discussions to reach aligned decisions
COMMENTING_GUIDELINES.md	Minimal, high-signal commenting rules and documentation boundaries
KNOWLEDGE_SHARING.md	Knowledge request protocol for handling information gaps

Contributing

Contributions are welcome! If you have suggestions for improving the guidelines or want to report issues:

1. Fork the repository
2. Create your feature branch
3. Make your changes
4. Submit a pull request

Please ensure your contributions align with the collaborative philosophy of this framework.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Star History