Most people use Claude Code like a chat box. It's actually a 7-layer system. Each layer compounds on the one below it. The bottom layer (CLAUDE. md) is where 90% of users stop. The top layer (Subagents) is where the real leverage starts. Here's the full stack, from foundation
TOOLS
-
Simonw asks about Copilot Pro and Microsoft 365 Premium naming
By
–
What's Copilot Pro? I found this story from October saying Microsoft weren't selling that any more, having replaced it with "Microsoft 365 Premium" https://
microsoft.com/en-us/microsof
t-365/blog/2025/10/01/meet-microsoft-365-premium-your-ai-and-productivity-powerhouse/
… (I cannot make any sense at all of Microsoft's product naming around this stuff) -
Firecrawl’s new parse endpoint turns documents into structured data for AI agents
By
–
Turn any document into structured data for AI agents! Firecrawl just released a new parse endpoint. Upload local files or non-public documents and get back clean, LLM-ready data. The parse endpoint converts PDF, DOCX, XLSX, HTML, and other formats into Markdown, JSON, or
-
Optimize AI Context Window Usage with /usage Command
By
–
Run /usage to see a detailed breakdown of the skills, plugins, mcps, and usage patterns that are draining your context window the most
-
Claude Agents View for Session Management
By
–
Use claude agents view, or Desktop app. It will categorize the status of each session for you to make sessions easier to juggle
-
Opus 4.7 No Longer Needs Plan Mode for Most Tasks
By
–
Opus 4.7 is intelligent enough that it no longer needs Plan Mode for most tasks. I often just jump in, and Claude will ask me questions if it needs to
-
Claude Code Supports Goal Loop Schedule Commands
By
–
Claude Code supports /goal, /loop, /schedule, etc.
-
Claude Code Auto Mode for Multi-Session Workflows
By
–
People often ask what my biggest tip is for getting the most out of Claude Code. These days my #1 tip is: use auto mode Auto mode means no more permission prompts. It is the key building block for multi-clauding: start a session, then while it runs, work on another session in
-
No Japanese models in top rankings, can fine-tune DeepSeek at home
By
–
None of these models rank high at all, no Japanese models even show up in the top. What's your point exactly? I can fine tune DeepSeek on my GPU at home
-
Engineer Builds Side Projects Using Claude Code from Phone
By
–
A software engineer with 10 years of experience says he builds entire side projects from his phone using Claude Code without reading a single line of code. Sounds reckless. Then you read his rules: → Always start in plan mode. Read the plan. Then read it again.
→ If any part