ai-agents-validation-and-qa

What counts as evidence in ai-agents and how to produce it. Covers the TESTING-RIGOR pos+neg+edge bar, test layout and collection reality, coverage proof commands, runtime-contract tests with negative controls, and ADR-034 QA skip semantics at session end. Use when you say what counts as evidence, how do I test this change, run skill tests, can I skip QA. Do NOT use for CI failure triage (use…