Across two of the three Q1 2026 ventures Peter built with Claude (agentmodeai, Rhino-basketball; DealVex pending git-versioning), rework rate measured as deletions / total git churn ranged from 8.1% to 13.5% over the 90-day window from 28 Jan to 28 Apr 2026. The data is meaningfully lower than typical solo-developer projects but substantially higher than the 'AI codes it correctly the first time' marketing narrative implies, supporting the thesis that AI-paired development requires explicit measurement, not assumed productivity.

Build-log Issue 3. Methodology locked per decision 1.B (28 Apr 2026): deletions / (insertions + deletions) from git log --shortstat. agentmodeai: 187 commits, 92,385 ins / 14,412 del = 13.5%. Rhino-basketball: 376 commits, 392,025 ins / 34,401 del = 8.1%. DealVex not git-versioned. Two-part trackable assertion: (1) DealVex methodology lands by 27 Jul 2026, (2) Q2 rework rates stay within ±5pp of current or deviation is documented. Both hold → Holds. DealVex lands but rates diverge → Partial. DealVex does not land → Partial with explanation.