https://rexai.top/en/ai/claude-code/Recent content in Claude Code on 梦兽编程Hugo -- 0.163.3en梦兽编程Sat, 11 Jul 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-hooks-interception-points/Sat, 11 Jul 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-hooks-interception-points/A deep dive into Claude Code's Hooks system: 26 lifecycle events, four hook types, execution models and exit code semantics, and how to customize AI Agent behavior.https://rexai.top/en/ai/claude-code/claude-code-microcompact-precision/Sat, 11 Jul 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-microcompact-precision/A deep dive into Claude Code's Microcompact mechanism: differences from auto-compaction, precise pruning strategies, relevance filtering, and fine-grained context management.https://rexai.top/en/ai/claude-code/claude-code-yolo-classifier/Sat, 04 Jul 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-yolo-classifier/A deep dive into Claude Code's YOLO classifier mechanism: how AI autonomously judges operation safety, two-stage review process, safety whitelist and rejection tracking, and intelligent permission control in Auto mode.https://rexai.top/en/ai/claude-code/claude-code-cache-optimization-patterns/Sat, 20 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-cache-optimization-patterns/A deep dive into Claude Code's cache optimization strategies: tool ordering stability, MCP tool management, session preservation techniques, and maximizing prompt cache benefits.https://rexai.top/en/ai/claude-code/claude-code-skills-system-ai-abilities/Sat, 20 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-skills-system-ai-abilities/Deep dive into Claude Code's skills system: built-in vs user-defined skills, how SkillTool works, differences and cooperation with MCP tools. Unveiling how to teach AI your secret techniques, reduce repeated prompts, and improve AI tool reusability.https://rexai.top/en/ai/claude-code/claude-code-cache-interruption-detection/Sat, 13 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-cache-interruption-detection/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.https://rexai.top/en/ai/claude-code/claude-code-claude-md-hooks-custom-butler/Sat, 13 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-claude-md-hooks-custom-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.https://rexai.top/en/ai/claude-code/claude-code-feature-flags-checklist/Fri, 12 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-feature-flags-checklist/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.https://rexai.top/en/ai/claude-code/claude-code-permission-system-safety-brake/Sat, 06 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-permission-system-safety-brake/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.https://rexai.top/en/ai/claude-code/claude-code-token-budget-strategy/Sat, 06 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-token-budget-strategy/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.https://rexai.top/en/ai/claude-code/claude-code-glossary/Fri, 05 Jun 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-glossary/Complete Claude Code glossary covering core concepts in architecture, context management, prompt engineering, permission system, and agent system with concise definitions.https://rexai.top/en/ai/claude-code/claude-code-compaction-microcompact/Sat, 30 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-compaction-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.https://rexai.top/en/ai/claude-code/claude-code-env-vars-reference/Fri, 29 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-env-vars-reference/Complete Claude Code environment variables reference handbook, covering all configurable options for debugging, caching, permissions, memory, models, and more.https://rexai.top/en/ai/claude-code/claude-code-state-retention-after-compaction/Sat, 23 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-state-retention-after-compaction/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."https://rexai.top/en/ai/claude-code/claude-code-prompt-caching-money-saving/Sat, 23 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-prompt-caching-money-saving/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.https://rexai.top/en/ai/claude-code/claude-code-file-index-handbook/Fri, 22 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-file-index-handbook/Claude Code core source code file index, organized by functional modules, with quick location guide for key classes, functions, and configuration files.https://rexai.top/en/ai/claude-code/claude-code-200k-context-memory-palace/Sat, 16 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-200k-context-memory-palace/Deep dive into Claude Code's context management mechanism: 200K tokens isn't "unlimited memory," how it auto-compacts, precisely prunes, and budget allocates. Unveiling how AI manages massive code information within a limited context window.https://rexai.top/en/ai/claude-code/claude-code-shortcomings-imperfections/Fri, 15 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-shortcomings-imperfections/An objective analysis of Claude Code's six major shortcomings: context window ceiling, tool latency accumulation, cost-quality tradeoffs, lack of offline capability, complex logic limitations, and memory system boundaries.https://rexai.top/en/ai/claude-code/claude-code-tool-descriptions-ai-manual/Sat, 09 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-tool-descriptions-ai-manual/Deep dive into Claude Code's tool description design: how to help AI accurately understand each tool's purpose and use cases. Unveiling how tool descriptions become "instructions for the model," how inputSchema affects parameter selection, and the application of dynamic descriptions.https://rexai.top/en/ai/claude-code/claude-code-production-grade-patterns/Fri, 08 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-production-grade-patterns/Six production-grade AI coding patterns extracted from Claude Code source code: Read Before Edit, Graduated Autonomy, Defensive Git, Structured Verification, Scope-Matched Response, and Tool-Level Prompts, plus the wisdom of dual-layer constraints.https://rexai.top/en/ai/claude-code/claude-code-prompt-behavior-guiding/Sat, 02 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-prompt-behavior-guiding/Deep dive into guiding AI behavior through prompts: from Few-shot examples to A/B testing, unveiling how Claude Code uses carefully designed prompts to turn an "impatient" AI into a "patient" one, and solving problems of AI being "over-eager" or "failing to ask when it should."https://rexai.top/en/ai/claude-code/claude-code-context-management-core-capability/Fri, 01 May 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-context-management-core-capability/An in-depth analysis of Claude Code's five context management principles: budget setting, content preservation, transparent disclosure, circuit breakers, and conservative estimation - and how to manage 200K tokens like a professional organizer.https://rexai.top/en/ai/claude-code/claude-code-system-prompts-behind-director/Sat, 25 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-system-prompts-behind-director/Deep dive into Claude Code's system prompt architecture: segmented composition design, division of identity/tools/format/safety modules, and the secrets of model-specific tuning. Unveiling why the same request gets completely different response styles from Claude Code versus ChatGPT.https://rexai.top/en/ai/claude-code/2026-04-19-claude-code-leak-rust-rewrite/Sun, 19 Apr 2026 10:00:00 +0800https://rexai.top/en/ai/claude-code/2026-04-19-claude-code-leak-rust-rewrite/In March 2026, Claude Code's 500k+ lines of TypeScript source code were accidentally leaked. Instead of panic, the developer community responded by rewriting the entire project in Rust. How did this mess turn into Rust's best advertisement for AI infrastructure?https://rexai.top/en/ai/claude-code/claude-code-agent-loop-ai-brain-mechanism/Sat, 18 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-agent-loop-ai-brain-mechanism/Deep dive into Claude Code's core Agent Loop: the complete lifecycle from user input to model response. Unveiling the query.ts state machine, tool execution orchestration, and continuation decision logic to understand how the AI coding assistant "thinks" and "acts."https://rexai.top/en/ai/claude-code/claude-code-model-specific-tuning/Wed, 15 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-model-specific-tuning/Deep dive into how Claude Code tunes prompts for different models: differences between Claude 3.5 Sonnet and Claude 3 Opus, application of A/B testing in prompt optimization, and prompt version management.https://rexai.top/en/ai/claude-code/claude-code-tools-system-how-ai-grows-hands/Sat, 11 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-tools-system-how-ai-grows-hands/Deep dive into Claude Code's tool system: how 40+ tools form an extensible capability architecture through unified interface contracts, three-tier filtering pipelines, and fail-closed defaults. From Tool.ts interface to buildTool factory, revealing the underlying mechanisms of AI tool calling.https://rexai.top/en/ai/claude-code/claude-code-tool-execution-orchestration/Wed, 08 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-tool-execution-orchestration/Deep dive into Claude Code's tool execution orchestration mechanism: the complete permission checking flow, concurrent execution scheduling strategy, streaming progress propagation, and the implementation principles of user interruption.https://rexai.top/en/ai/claude-code/claude-code-not-cli-but-living-system/Sat, 04 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-not-cli-but-living-system/A deep dive into Claude Code's underlying architecture: why it's not a traditional CLI tool but an intelligent system running in a 'distributed state.' From TypeScript to Bun runtime, three-tier architecture to Feature Flags, understand the core design philosophy of this AI coding assistant.https://rexai.top/en/ai/claude-code/2026-04-02-reverse-engineering-claude-code-cch/Thu, 02 Apr 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/2026-04-02-reverse-engineering-claude-code-cch/An in-depth reverse engineering analysis of Claude Code's API request signing mechanism, revealing how the cch hash and xxHash64 are implemented, the secrets of Bun's runtime, and how Anthropic protects API calls with native code.https://rexai.top/en/ai/claude-code/claude-code-channels/Fri, 20 Mar 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-channels/A hands-on look at Claude Code Channels, letting you control your AI coding assistant through Telegram, Discord, and more — no matter where you are.https://rexai.top/en/ai/claude-code/2026-02-28-claude-code-memory-system/Sat, 28 Feb 2026 10:00:00 +0800https://rexai.top/en/ai/claude-code/2026-02-28-claude-code-memory-system/Deep dive into Claude Code's memory mechanisms: Auto Memory vs CLAUDE.md, hierarchical memory structure, modular rules configuration, making your AI assistant truly remember your project habits.https://rexai.top/en/ai/claude-code/2026-02-28-claude-code-z80-emulator/Sat, 28 Feb 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/2026-02-28-claude-code-z80-emulator/Redis founder antirez used Claude Code to implement a complete Z80 emulator in 30 minutes, passing the ZEXALL full instruction test. He designed a strict clean-room experiment: first had AI organize documentation, then cut off the network and implemented from scratch. Result: 1200 lines of code, zero bugs, and顺便 also built ZX Spectrum and CP/M environments.https://rexai.top/en/ai/claude-code/2026-02-27-claude-code-tool-picks-research/Fri, 27 Feb 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/2026-02-27-claude-code-tool-picks-research/Amplifying.ai ran 2,430 tests on Claude Code and found that in 12 out of 20 categories, it prefers writing custom code over using existing tools. GitHub Actions 94%, Stripe 91%, shadcn/ui 90% selection rates are striking, while AWS, GCP, and Azure got zero primary picks.https://rexai.top/en/ai/claude-code/claude-rag-search-retrieval-guide/Tue, 10 Feb 2026 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-rag-search-retrieval-guide/A practical RAG tutorial: build an enterprise knowledge base Q&A system in 4 steps using embedding vector search and Claude. Contextual Retrieval cuts retrieval failure from 5.7% to 1.9%, with full Python code and Voyage AI model comparison.https://rexai.top/en/ai/claude-code/claude-code-lsp/Wed, 31 Dec 2025 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-lsp/Claude Code 2.0.74 now has native LSP support—it can jump to definitions and find references just like VS Code, no more blind grep searcheshttps://rexai.top/en/ai/claude-code/claude-4-5-sonnet-worlds-strongest-coding-model/Tue, 30 Sep 2025 10:00:00 +0800https://rexai.top/en/ai/claude-code/claude-4-5-sonnet-worlds-strongest-coding-model/Anthropic releases Claude 4.5 Sonnet, claiming world's strongest coding capabilities, 77.2% benchmark score, 30-hour continuous runtime, with Claude Code upgrade and new Agent SDKhttps://rexai.top/en/ai/claude-code/claude-code-ai-programming-assistant/Tue, 30 Sep 2025 10:00:00 +0800https://rexai.top/en/ai/claude-code/claude-code-ai-programming-assistant/Deep dive into Claude Code AI programming assistant - from local execution to natural language interaction, see how this Claude 4-based tool transforms developers' daily workflowhttps://rexai.top/en/ai/claude-code/claude-code-superpowers-beginner-guide/Sun, 12 Jan 2025 00:00:00 +0000https://rexai.top/en/ai/claude-code/claude-code-superpowers-beginner-guide/A beginner's guide to Superpowers: Whether you use Claude Code, Codex, or OpenCode, this AI coding skill pack transforms your assistant from 'chaotic mess' to 'methodical pro'. Includes OpenSpec and Spec-Kit comparison.