rullerzhou-afk/clawd-on-desk: README-based editorial guide

rullerzhou-afk/clawd-on-desk describes itself in the README as "A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents , so you don't have to.". This article keeps to facts that can be checked in the repository. Stars, forks, and promotional badges are signals of attention, not proof of quality. Under "README", the README says: Clawd lives on your desktop and reacts to what your AI coding agent is doing , in real time. Start a long task, walk away, come back when the crab tells you it's done.. That establishes the project's stated boundary, not a production test.

The README's "Multi-Agent Support" section gives a useful starting point for deciding whether the project fits: Codex CLI , official hooks with JSONL fallback (/.codex/sessions/), auto-synced by default with real permission bubbles. If that problem is not yours, popularity is a poor reason to adopt it. Project names, commands, and component names are kept as written so a reader can return to the primary source without guessing at terminology. Another checkable README item is: Claude Code , full integration via command hooks + HTTP permission hooks. It can shape a first test, but it does not replace testing in the intended environment.

The operating model is spread across sections such as "README". The source evidence includes: > Supports Windows 11, macOS, and Ubuntu/Linux. Windows releases provide separate x64 and ARM64 installers. Source builds require Node.js.. This article does not turn missing architecture, performance, or security details into claims. A real deployment still needs a look at the repository layout, configuration files, and release history.