benchmark
01Command Claude Code
A command that produces a report measuring Computer Use capabilities, such as task completion and tool activity. Computer Use means controlling applications through an interactive computer interface.
Reasonix cross-platform desktop automation plugin (refactored). Precision layer first (UIA/AXAPI/AT-SPI2) with a visual fallback (EasyOCR), using normalized coordinates; all three platforms—Windows, Linux (X11), and macOS—are implemented with the same shared code. Wayland and unauthorized scenarios automatically fall back to the visual layer. Includes built-in MCP tools, skills, hooks, and memory system.
Command Claude Code
A command that produces a report measuring Computer Use capabilities, such as task completion and tool activity. Computer Use means controlling applications through an interactive computer interface.
Command Claude Code
A command that diagnoses the Computer Use plugin, its environment, and its mapped capabilities. Computer Use lets an agent interact with a computer through supported actions.
Command Claude Code
A command that starts a planned, isolated Windows computer-use task. It follows prepared steps, checks the computer setup, uses screenshots when needed, and reports what was actually verified.
Command Claude Code
A command for running general capability tests for computer-use features, which let an agent interact with supported computer applications. It uses a quick test by default and does not operate real user applications.
Command Claude Code
A command for viewing or exporting privacy-filtered Computer Use activity traces. A trace is a record of actions taken during a computer-use session, and the command supports status, listing recent traces, and confirmed export.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: