mirror of
https://github.com/hyperdxio/hyperdx
synced 2026-04-21 21:37:41 +00:00
## Summary This PR backports the claude E2E skill and a few E2E script improvements to the open source repo from the EE repo. ### Screenshots or video ### How to test locally or on Vercel ### References - Linear Issue: n/a - Related PRs: |
||
|---|---|---|
| .. | ||
| architecture.md | ||
| code_style.md | ||
| development.md | ||
| README.md | ||
| tech_stack.md | ||
Agent Documentation Directory
This directory contains detailed documentation for AI coding agents working on the HyperDX codebase. These files use progressive disclosure - they're referenced from CLAUDE.md but only read when needed.
Purpose
Instead of stuffing all instructions into CLAUDE.md (which goes into every conversation), we keep detailed, task-specific information here. This ensures:
- Better focus: Only relevant context gets loaded per task
- Improved performance: Smaller context window = better instruction following
- Easier maintenance: Update specific docs without bloating the main file
Files
architecture.md- System architecture, data models, service relationships, security patternstech_stack.md- Technology choices, UI component patterns, library usagedevelopment.md- Development workflows, testing strategy, common tasks, debuggingcode_style.md- Code patterns and best practices (read only when actively coding)
Usage Pattern
When starting a task:
- Agent reads
CLAUDE.mdfirst (always included) - Agent determines which (if any) docs from this directory are relevant
- Agent reads only the needed documentation
- Agent proceeds with focused, relevant context
Maintenance
- Keep files focused on their specific domain
- Use file/line references instead of code snippets when possible
- Update when patterns or architecture change
- Keep documentation current with the codebase