bmad-review-edge-case-hunter

Provide the diff as the content input and the review scans only the changed hunks, listing boundaries reachable from changed lines that lack an explicit guard. Findings are returned as a JSON array with location, trigger condition, guard snippet, and consequence.

Edge case review is method-driven: it mechanically enumerates every branching path and reports only unhandled ones, without judging code quality. Adversarial review is attitude-driven and critiques design or style, which this review explicitly avoids.

Yes. When no diff is provided, the entire file or function becomes the analysis scope. The review walks all control flow and domain boundaries within that content and ignores the rest of the codebase unless explicitly referenced.

It returns only a valid JSON array where each object has exactly four fields: location, trigger_condition, guard_snippet, and potential_consequence. An empty array is returned when no unhandled paths are found.

The review halts immediately and returns a single JSON object indicating the input was empty or undecodable, with a guard snippet requesting valid content. No further analysis steps are executed.