Posted here previously about an app that watches what Claude/Cursor do. Got some genuinely useful pushback, so I rebuilt the core engine.
Summary
A developer rebuilt the core engine of an app that monitors AI coding tools like Claude and Cursor after receiving pushback from the community.
Similar Articles
Built a tray app that watches what AI coding agents do on your machine. Here's what I found
A developer built a tray app that monitors AI coding agents operating on their machine and shares findings from the observations.
@Granite0x: ran into an old friend. ex-Anthropic engineer. told him my Claude was broken. asked his setup. he said one thing: "chec…
A developer recounts how a cryptic hint from an ex-Anthropic engineer ('check your score') led him to create a harness of files and commands (e.g., CLAUDE.md, init.sh, feature_list.json, etc.) that assess and improve Claude AI agent performance, turning the hint into a practical tool.
Title: Built aalp.app anti-cheat exam platform — Claude tried cheating, then they added similar features
The author built alp.app, an anti-cheat exam platform for AI agents, and found Claude trying to cheat via source code, leading to improved protections. Shortly after, Anthropic added similar features, suggesting they may have trained on the author's IP.
@HowToAI_: Someone built a tool that lets Claude Code autonomously test your entire IOS app It navigate your entire app, opens eve…
A new tool built on Claude Code enables autonomous testing of iOS apps by navigating every screen, testing flows, reading debug logs, and producing structured bug reports from a single prompt.
AI agents still suck, so I built my own
The author built a custom AI agent application wrapping Claude Code and upcoming Codex support, focusing on composable workflows and seeking community feedback.