sumo-qa-reviewing-before-mergelisted

# Reviewing before merge Help the user decide whether a change is safe to ship by walking the review one section at a time: explore the diff, surface what was found, name the risks, run the verification, deliver the verdict. The user has product context (was this a deliberate behaviour change? is this consumer used externally?) the AI can't infer from the diff alone — surface it through questions, don't assume it. **Announce at start:** *"Reviewing the diff against fresh test evidence."* ## Output discipline (mandatory) Inherits the global discipline from `using-sumo-qa`: **output discipline** (never surface internal taxonomy labels — say *"behaviour change in pricing"*, not *"Classification: business_logic_change"*; this includes the raw keys of any loaded change-rules file — cite the rule in plain English, e.g. *"the documented-inventory rule"*, never by echoing its YAML key), **output economy** (spend output on findings not framing; no preamble or self-narration; one question per turn; no closing pleasantries), knowledge authority hierarchy, internal scaffolding stays internal, and specialty-tool fit. <HARD-GATE> Do NOT deliver a verdict before running tests in this turn. "CI was green earlier" is not fresh evidence. The Iron Law's only verdict source is the suite running RIGHT NOW against THIS diff, with the actual pass/fail counts surfaced. </HARD-GATE> ## The Iron Law **NEVER CLAIM SAFE-TO-MERGE WITHOUT FRESH VERIFICATION EVIDENCE.** "All tests pass" is necessary