AI Coding Agent Security Flaws: Claude Code, Gemini, CodexAn AI coding agent reads files written by other people, runs commands with your privileges, and sees your secrets. AI coding agent security is therefore not a theoretical topic: between June 2025 and15 min read·thomastartrau.hashnode.dev1RSep 28
Jev Ultrafast MCP: an autonomous browser for Claude CodeI use Claude Code with two browser MCP servers: Claude in Chrome and Jev Ultrafast MCP. Both let Claude control a browser, but the approach is radically different. Claude in Chrome sends each click an8 min read·thomastartrau.hashnode.dev11MSep 21
The 5 Walls Between a 3M req/s HTTP Benchmark and ProductionAn HTTP framework advertised at 3 million requests per second never serves 3 million requests per second in production. The number is real, the measurement is honest, but it describes a scenario that7 min read·thomastartrau.hashnode.devSep 21
Why More Than 30 Skills Kill Your AI AgentThe more skills an agent has, the better it should work. That is the intuition. It is wrong. Past thirty or so skills or tools, adding one more capability often degrades the agent instead of improving7 min read·thomastartrau.hashnode.devSep 17
JSON vs Programmatic Tool Calling with ClaudeWhen building an application with the Claude API, connecting tools is the first step toward a functional agent. The model can call functions, query databases, send messages. But how you wire those too8 min read·thomastartrau.hashnode.devSep 11
