Claude-Code
41 posts
Cache Interruption——When Does It Become Invalid?
Deep dive into Claude Code’s cache interruption detection mechanism: scenarios where cache becomes invalid such as tool changes, model switching, session timeout, and how to gracefully handle cache invalidation.
CLAUDE.md and Hooks——Building Your Personalized AI Butler
Deep dive into Claude Code’s CLAUDE.md configuration and Hooks mechanism: how to build a personalized AI butler through project-level AI manuals and custom interception points. Unveiling CLAUDE.md syntax, Hook lifecycle, and practical workflow customization cases.
Feature Flags Checklist - Complete Overview of 89 Feature Switches
Complete Claude Code Feature Flag checklist covering 89 feature switches across 5 domains: autonomous agents, remote control, context management, memory and knowledge, and UI/UX.
Permission System——Installing a "Safety Brake" for AI
Deep dive into Claude Code’s permission system: three-tier permission architecture, YOLO classifier automatic judgment, and Always Allow/Deny rules. Unveiling how AI stops itself before executing rm -rf /, and how production-grade safety control is implemented.
Token Budget - How to Spend 200K Wisely?
A deep dive into Claude Code’s token budget strategy: the 200K token allocation plan, dynamic adjustment mechanisms, and strategies for when the budget runs out.
Glossary - Claude Code Concept Quick Reference
Complete Claude Code glossary covering core concepts in architecture, context management, prompt engineering, permission system, and agent system with concise definitions.
When AI's "Brain" Isn't Enough——Compaction and Microcompact
Deep dive into Claude Code’s context compaction mechanism: differences between auto-compaction and microcompact, state preservation after compaction, and context collapse. Unveiling how AI elegantly makes tradeoffs when “memory runs out,” and why AI sometimes “forgets” previous content.
Environment Variables Reference - Complete Claude Code Configuration Guide
Complete Claude Code environment variables reference handbook, covering all configurable options for debugging, caching, permissions, memory, models, and more.
After Compaction, What Does AI Still Remember?——State Retention Mechanism
Deep dive into Claude Code’s context compaction state retention mechanism: lossy compression design, metadata preservation, the role of reference links, and how AI elegantly makes tradeoffs when “memory runs out.”
Prompt Caching——Claude Code's "Money-Saving Secret"
Deep dive into Claude Code’s prompt caching mechanism: cache breakpoint design, tool ordering stability, and cache interruption detection. Unveiling how prompt caching dramatically reduces API call costs, and why tool ordering must remain stable.
