Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
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
This framework is available as a Claude Skill. Install it using Claude Code:
/plugin marketplace add BackGwa/Agentic-Structure
/plugin install agentic-structure@agentic-structureOr 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:
- Fork the repository
- Create your feature branch
- Make your changes
- 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.