Are You Exposed to the Opus 4.8 Dual Cluster? — 5-Question Diagnostic
5 questions · ~2 minutes · browser-only, no signup, no telemetry · CC0 · v1.0 (2026-06-01)
What this diagnoses: Between 2026-05-30 and 2026-05-31, 11 independent issues filed on anthropics/claude-code documented two structurally distinct Opus 4.8 regressions sharing the same version window (v2.1.156–v2.1.158). Cluster 22 candidate (6 filings, correctness hazard) — model asserts specific tool-output values before tools return. Cluster 23 candidate (5 filings, cost hazard) — routine coding turns burn 40-50k output tokens where Opus 4.6/4.7 produce 2-3k. This 5-question diagnostic estimates your exposure and routes you to the right operator-side response.
Disclosure: The recommendation routes high-exposure operators to the Token Book (¥2,500, Cluster 23 technical deep-dive) and 事故防止本 (¥800, operator-experience framing). The five defense hooks at cc-safe-setup (PR #519, #537, #529, #535) are MIT-licensed and free; the books are the deeper monthly-updated reference. Low-exposure operators get the free Path 1 recommendation only.
5 Questions
Your Opus 4.8 Dual Cluster Exposure Score
—
About the Score
The diagnostic produces a 0-90 score across five factors. The bands reflect both the probability you're hitting the cluster and the dollar magnitude of the impact:
Score 55-90 (High exposure): Multiple signals indicate active Cluster 22 and/or Cluster 23 firing. The Opus 4.7 switch (Path 1) typically pays for itself within hours via the per-turn token reduction. The cc-safe-setup hooks surface ongoing events for verification.
Score 25-54 (Moderate exposure): Some signals present but not load-bearing. Path 1 is still the highest-leverage move; the diagnostic logs and hooks help you decide whether to make the switch permanent.
Score 0-24 (Low exposure): You're either not on Opus 4.8, or your usage pattern doesn't trigger the cluster signatures. The free hooks at cc-safe-setup remain useful for other failure clusters but the Opus 4.8 dual cluster is not your highest-priority concern.
Source Material
This diagnostic draws on the 11 independent issue filings 2026-05-30 to 2026-05-31:
Cluster 22 candidate (6 filings, correctness hazard):#64048 (confabulated prompt-injection markers), #64055 (unwanted file modifications), #64065 (anchor: flight prices before web search), #64076 (model admits fabrication when pressed), #64095 (git log returning different SHAs), #64103 (parallel bash false success reports).