slopbeth for the conversation instead of the shipped artifact. Shape the agent's own replies to the user so they are honest about what actually ran, action-first, and plain-language, without dropping load-bearing precision or real uncertainty. Invoke to turn on; it stays until the user says "stop slopgent". Does not rewrite the user's text; use slopbeth for that.
$npx -y skills add ehmo/slopkit --skill slopgentInstalls into the current project.
Run `npx skills use "https://github.com/ehmo/slopkit" --skill "ehmo/slopkit/slopgent"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/ehmo/slopkit" that are relevant to the current task. Run `npx skills add "https://github.com/ehmo/slopkit"` and select the relevant skills, then follow their instructions.