AI Coding & Developer ToolsAI 編程與開發工具
228228 articles collected
This hub collects everything on the site about AI coding: hands-on notes on coding agents such as Claude Code and Cursor, and the working habits that make these tools useful in daily development.
The posts answer practical questions: how to arrange context and how long a system prompt should be, what the same prompt costs on different models, and what checks agent-written code should pass before it reaches the team.
Start with the must-read picks below; the full timeline lists every article in this hub, newest first.
MUST READS
- 01Anthropic's New Context Engineering Rules for Claude 5
Anthropic cut over 80% of Claude Code's system prompt for Claude 5 models with no measurable eval loss, and rewrote its context engineering guidance.
- 02Running Claude Code on a Spare Mac: The Value and Security Boundaries of an Isolated Agent Workstation
Learn how to set up a dedicated Mac for Claude Code to safely run AI agents, with practical advice on permissions, credential isolation, and recovery.
- 03LLM Tokenization: Why the Same Text Costs 2.65x More on Different Models
Token counts vary wildly across models. Learn how tokenization affects cost, why format matters more than model choice, and how to measure effective price.
- 04Cursor's Year-Long Lesson: The Hardest Part of Cloud Agents Isn't the Model, It's the Environment
Cursor shares hard-won lessons from building cloud agents: environment fidelity over model strength, Temporal for reliability, and decoupling agent logic from machine state.
- 05The Gates Come Before the Agent Fleet
A software factory is five gated stages, and the agent is the cheap part — review capacity is the real constraint.
- 06OpenRouter MCP: Live Model Data for Smarter Agent Decisions
OpenRouter's MCP server gives coding agents live model data, benchmarks, pricing, docs, and test inference. Eleven tools, only one billed; the OAuth key has a seven-day expiry and a ten-dollar cap.
TOPIC TIMELINE
All 228 articles in this hub, newest first.
- Your Brand Stops Living in Every PromptContent Creation
- Profile Your Workers in Production Instead of Guessing From MetricsCloudflare Workers
- DuckDB v2.0 Preview: Server Mode, New Parser, New StorageDeveloper Tools
- Go 1.27 Lands: Generic Methods, json/v2, Post-Quantum TLSDeveloper Tools
- Hunting SQLite's 16-Year-Old WAL Reset Bug at TailscaleDeveloper Tools
- Docker Sandboxes: microVM Isolation for AI Coding AgentsDeveloper Tools
- Mojo 1.0: A Stable Foundation for AI Systems ProgrammingDeveloper Tools
- Edge Ends Manifest V2: What uBlock Origin Users Do NowDeveloper Tools
- Firefox 153 Ships Vulkan Video Decoding and JPEG XLDeveloper Tools
- Full-Stack AI Explained: What It Means and How to Get StartedAI Infrastructure
- Microsoft ASSERT Turns Text Specs into AI Behavior TestsDeveloper Tools
- Uber Caps Employee AI Tool Spend at $1,500 a MonthEnterprise AI
- Figma Make Now Edits Your Production CodebaseDeveloper Tools
- Search Quality Shapes RL Outcomes: Why Your Agent's Backend Matters More Than You ThinkReinforcement Learning
- Reflex Benchmark: Computer Use Costs 45x More Than APIsAgent Benchmarks
- Ghostty Quits GitHub After a Month of Daily OutagesDeveloper Tools
- Android CLI: Google's Terminal-First Bet on Coding AgentsDeveloper Tools
- OpenAI Gives Students $100 in Codex CreditsOpenAI Codex
- Synopsys Rewires Chip Design With AI Agents and AnsysDeveloper Tools
- Google Opens AI Mode Canvas to All US UsersSearch Engine
- WordPress.com Builds Its AI Assistant Into the EditorContent Creation
- Google open-sources Gemini CLI, a free terminal AI agentDeveloper Tools
- iPadOS 26 brings Mac-style windowing to the iPadProduct Development
- Apple unveils Liquid Glass and year-based OS namesProduct Design