driftproof run — skill "code-review-and-quality" v0.0.0
  content_hash: 13d360d7f786de37…  suite: 1 cases (5d729f885294…)
  surface: claude-cli   models: claude-opus-5   samples/case: 3   concurrency: 1
  registry: claude-opus-5:registered   transcripts: retained-local
  judge: claude-opus-5   (--judge-model)
  isolation: same-user (--trusted-skill: self-authored skill)
  projected calls: 80/model × 1 model(s) = 80   per-model cap: 80
  projected cost: ~$1.30 (rough upper bound; budget $8.00, hard-stop $10.00)
  actual metered spend on claude-cli: $0.00 (subscription; the $ figure is the estimated-equivalent API cost, counted against the cap identically)

── model: claude-opus-5 ──
  severity-labeled-findings / with_skill: pass (0.90 ± 0.01)
  severity-labeled-findings / baseline: pass (0.86 ± 0.03)
  → transcripts (retained-local): transcripts/d7bd2fcd3dbea881a53581022cea4a311ed9e75b457aa6d91a7c4d1c3aaaecd0/
  → ../evidence/opus-5-5-20260923T062806Z/claude-opus-5/code-review-and-quality/receipts/code-review-and-quality-claude-opus-5-2026-09-23.json  (24 calls)
  → answered by: model claude-opus-5 (attested by the surface; the same-user spawn (--trusted-skill)); verification_level TESTED
  → skill lift +0.039 ± n/a (1 case)  (with 0.901 ± n/a (1 case) vs base 0.862 ± n/a (1 case); band = sample stddev of the per-case means)

Done. 1 receipt(s) emitted to ../evidence/opus-5-5-20260923T062806Z/claude-opus-5/code-review-and-quality/receipts/