This XDA Developers article by Anurag Singh explains how a **CLAUDE.md** file at the root of a repository solves the problem of Claude Code repeatedly asking the same setup questions in every new session.
**The problem:** Each Claude Code session starts with a fresh context window, so it has no memory of previous conversations. It must re-inspect the repo and re-infer project conventions (package manager, test commands, directory rules, etc.), wasting time and tokens—and sometimes reaching different conclusions.
**The solution:** A `CLAUDE.md` file that Claude Code automatically loads at the start of every session. It acts as a persistent onboarding document containing:
- **Commands** (e.g., "Use pnpm," "Run `pnpm test` before completing a task")
- **Project structure rules** (e.g., "Reusable components go in `src/components/`," "Do not edit `src/generated/`")
- **Working rules** (e.g., "Reuse existing components," "Ask before installing a dependency," "Make the smallest change required")
**How to create it:** Either write it manually or run `/init` inside Claude Code, which auto-generates a starting file from the repo. If one already exists, `/init` suggests changes rather than overwriting.
**Best practices:**
- Keep it under ~200 lines (treat as a ceiling, not a target).
- Be specific—avoid vague instructions like "write clean code."
- Don't duplicate content Claude can discover by reading the repo (don't make it another README).
- Watch for conflicting rules across multiple instruction files.
**File hierarchy:**
| File | Scope |
|---|---|
| `~/.claude/CLAUDE.md` | Global, all projects |
| `CLAUDE.md` (repo root) | Project-level, commit to version control |
| `CLAUDE.local.md` | Personal, add to `.gitignore` |
The author notes that Claude Code's built-in "auto memory" is unreliable for critical rules because Claude decides what to save there; a hand-written CLAUDE.md is exact and shareable.
**The problem:** Each Claude Code session starts with a fresh context window, so it has no memory of previous conversations. It must re-inspect the repo and re-infer project conventions (package manager, test commands, directory rules, etc.), wasting time and tokens—and sometimes reaching different conclusions.
**The solution:** A `CLAUDE.md` file that Claude Code automatically loads at the start of every session. It acts as a persistent onboarding document containing:
- **Commands** (e.g., "Use pnpm," "Run `pnpm test` before completing a task")
- **Project structure rules** (e.g., "Reusable components go in `src/components/`," "Do not edit `src/generated/`")
- **Working rules** (e.g., "Reuse existing components," "Ask before installing a dependency," "Make the smallest change required")
**How to create it:** Either write it manually or run `/init` inside Claude Code, which auto-generates a starting file from the repo. If one already exists, `/init` suggests changes rather than overwriting.
**Best practices:**
- Keep it under ~200 lines (treat as a ceiling, not a target).
- Be specific—avoid vague instructions like "write clean code."
- Don't duplicate content Claude can discover by reading the repo (don't make it another README).
- Watch for conflicting rules across multiple instruction files.
**File hierarchy:**
| File | Scope |
|---|---|
| `~/.claude/CLAUDE.md` | Global, all projects |
| `CLAUDE.md` (repo root) | Project-level, commit to version control |
| `CLAUDE.local.md` | Personal, add to `.gitignore` |
The author notes that Claude Code's built-in "auto memory" is unreliable for critical rules because Claude decides what to save there; a hand-written CLAUDE.md is exact and shareable.
Simon Willison discusses using Claude Fable to assist in the development of sqlite-utils 4.0rc2. The AI helped identify critical bugs, specifically a transaction error in delete_where that could cause data loss, and facilitated significant code changes across dozens of files. Willison also employed GPT-5.5 to review the AI's work, discovering that cross-model verification is a highly effective technique for catching edge cases. The post includes a cost analysis of the AI development session and details the significant changes to the library's transaction model and error handling.
- Using coding agents for bug detection and large-scale refactoring
- The effectiveness of cross-model review using Claude and GPT
- Key breaking changes in sqlite-utils 4.0rc2 regarding transactions and error handling
- Cost breakdown of agentic AI development sessions
- Using coding agents for bug detection and large-scale refactoring
- The effectiveness of cross-model review using Claude and GPT
- Key breaking changes in sqlite-utils 4.0rc2 regarding transactions and error handling
- Cost breakdown of agentic AI development sessions
The AI coding tool market is shifting from a race for consolidation toward a model of composability. Instead of a single dominant product emerging, specialized tools are forming distinct layers that work together as a unified stack. This trend is exemplified by recent developments where Cursor provides orchestration, Claude Code and OpenAI Codex handle execution, and cross-provider plugins enable independent review.
Key points:
The emergence of an orchestration layer for managing multiple AI agents simultaneously.
An execution layer focused on the actual writing, debugging, and testing of code within terminals or sandboxes.
A new review layer that utilizes adversarial, cross-provider scrutiny to mitigate model bias and errors.
A shift in developer workflow where the text editor becomes secondary to agent management interfaces.
The move toward interoperability over vendor lock-in as companies embed tools into competitor ecosystems.
Key points:
The emergence of an orchestration layer for managing multiple AI agents simultaneously.
An execution layer focused on the actual writing, debugging, and testing of code within terminals or sandboxes.
A new review layer that utilizes adversarial, cross-provider scrutiny to mitigate model bias and errors.
A shift in developer workflow where the text editor becomes secondary to agent management interfaces.
The move toward interoperability over vendor lock-in as companies embed tools into competitor ecosystems.
This handbook provides a comprehensive introduction to Claude Code, Anthropic's AI-powered software development agent. It details how Claude Code differs from traditional autocomplete tools, functioning as an agent that reads, reasons about, and modifies codebases with user direction. The guide covers installation, initial setup, advanced workflows, integrations, and autonomous loops. It's aimed at developers, founders, and anyone seeking to leverage AI in software creation, emphasizing building real applications, accelerating feature development, and maintaining codebases efficiently. The handbook also highlights the importance of prompt discipline, planning, and understanding the underlying model to maximize Claude Code's capabilities.
AI coding tools are increasingly interacting directly with the system shell (terminal) rather than traditional code editors, driven by the rise of agentic AI and tools like Claude Code, Gemini CLI, and CLI Codex. This shift, highlighted by benchmarks like Terminal-Bench, is occurring as some code-based tools face challenges and offers a versatile interface for developers.
An overview of the top AI-powered coding tools available in 2025, including Cursor, Claude Code, Windsurf, VSCode, and others, highlighting their features and popularity among developers.
| **Tool** | **Developer** | **Key Features** | **Notes** |
|-------------------|----------------------------|---------------------------------------------------------------------------------|---------------------------------------------------------------------------|
| **Cursor** | Anysphere | AI-powered autocomplete, code rewriting, agent mode, integrates with Web resources | Most popular AI-focused IDE, fork of VSCode |
| **Claude Code** | Anthropic | Works in MacOS/Linux terminal, command-line interface, high control over workflow | Preferred by developers who like command-line tools |
| **Windsurf** | Codeium (acquired by OpenAI)| AI autocorrect, agentic AI, Cascade interface, works in other IDEs (e.g., Jetbrains) | Rebranded from Codeium, acquired by OpenAI for $3 billion |
| **VSCode** | Microsoft | Extensions support, GitHub Copilot (agent mode in preview), slow AI integration | Popular IDE, but slower to adopt AI features compared to startups |
| **Vibe Coding Tools** | Various (e.g., Lovable, Replit, Bolt, Firebase) | Chat interface, no software installation, browser-based, minimal coding required | Designed for "vibe coding," where users describe what they want to build |
| **Other Tools** | OpenAI, Mistral, Apple, etc. | Codex (OpenAI), Mistral Code, Apple’s AI tools, Zed, Devin (AI software engineer) | Rapidly evolving, many new tools emerging frequently |
| **Tool** | **Developer** | **Key Features** | **Notes** |
|-------------------|----------------------------|---------------------------------------------------------------------------------|---------------------------------------------------------------------------|
| **Cursor** | Anysphere | AI-powered autocomplete, code rewriting, agent mode, integrates with Web resources | Most popular AI-focused IDE, fork of VSCode |
| **Claude Code** | Anthropic | Works in MacOS/Linux terminal, command-line interface, high control over workflow | Preferred by developers who like command-line tools |
| **Windsurf** | Codeium (acquired by OpenAI)| AI autocorrect, agentic AI, Cascade interface, works in other IDEs (e.g., Jetbrains) | Rebranded from Codeium, acquired by OpenAI for $3 billion |
| **VSCode** | Microsoft | Extensions support, GitHub Copilot (agent mode in preview), slow AI integration | Popular IDE, but slower to adopt AI features compared to startups |
| **Vibe Coding Tools** | Various (e.g., Lovable, Replit, Bolt, Firebase) | Chat interface, no software installation, browser-based, minimal coding required | Designed for "vibe coding," where users describe what they want to build |
| **Other Tools** | OpenAI, Mistral, Apple, etc. | Codex (OpenAI), Mistral Code, Apple’s AI tools, Zed, Devin (AI software engineer) | Rapidly evolving, many new tools emerging frequently |
