← ClaudeAtlas

vibe.testlisted

Use when verifying that a vibe install is intact or that CC and Codex are in sync — before a release, after changing skills/hooks/agents, or when a harness behaves inconsistently. Probes every shipped surface in the target install dir and writes a pass/fail report with STCV skill-quality verdicts.
su-record/vibe · ★ 0 · AI & Automation · score 75
Install: claude install-skill su-record/vibe
# /vibe.test **Vibe Self-Test** — probe every shipped surface (commands, skills, hooks, agents) in a vibe install dir and emit a pass/fail report. ## Usage ``` /vibe.test # Test current harness (auto-detect) /vibe.test cc # Force-test ~/.claude/ /vibe.test codex # Force-test ~/.codex/ ``` No subcommands. No CC-vs-Codex comparison semantics. One command, one report. ## Report Stored in vibe's global dir (not per-project): ``` ~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.json ~/.vibe/test-reports/<YYYYMMDD-HHmm>-<harness>.md ``` Markdown summary is also printed to the console when the run finishes. ## Process Execute the bundled implementation below with target harness: `$ARGUMENTS` - If `$ARGUMENTS` is empty, detect the current harness (CC vs Codex) and use that. - If the target install dir is missing, exit cleanly with guidance (not an error). Probe spec: below. Report schema: `references/report-template.md`. ## Done Criteria - [ ] Runs without any external LLM call — file reads + vitest only - [ ] A single probe failure never halts the overall run - [ ] JSON report matches `references/report-template.md` exactly - [ ] P1 failures auto-register via `/vibe.regress` --- ARGUMENTS: $ARGUMENTS ## Bundled implementation # test — Self-Test Probe every shipped vibe surface in one install dir and emit a pass/fail report. ## Why this exists When vibe ships new entry skills, skills, hooks, or agents, one side (CC or Codex) can end up out of sync w