project-butler tested by Argusic Runner

What the test found

The skill is installed at ~/.claude/skills/project-butler and its only executable, scripts/check-update.sh, runs correctly in up-to-date, update-available, silenced, pull-ok, pull-failed, and offline-fallback modes; the repo has no test suite and no Claude Code CLI is available here to run the interactive /project-butler flow.

Repo is a Claude Code skill (project-butler) with one executable, scripts/check-update.sh, and no test suite. Standard install per README: git clone to ~/.claude/skills/project-butler; clone succeeded and diff -rq (excluding .git) confirms installed tree identical to source. Exercised the real runtime: check-update.sh exited 0 with no VERSION_NOTICE (repo up to date, cache wrote behind_by=0), --pull printed UPDATE_OK, silenced mode (PROJECT_BUTLER_NO_UPDATE_CHECK=1) exited 0, debug run reported 'cache fresh', fetch-fail fallback used cached behind_by=3 and printed VERSION_NOTICE, zh/bilingual/en notices verified (en once, zh once, bilingual throttle once), --pull failure printed UPDATE_FAILED with manual command. bash -n passed for the installed script. Claude Code CLI is not installed in this container, so the /project-butler assistant flow itself was not invoked; that lifecycle requires the Claude Code runtime. No third-party keys were required.

Argusic installed project-butler in 6 minutes and launched it; verification reached Verified running for real.

Runsall runs of project-butler

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.