chore: let this repo's own reviewers rate design findings by cost

#86 added the `design` rating rule to templates/shared.md and templates/agents/correctness.md, but not to this repo's own copies in .expo-agents/code-review/. Without it, High and Medium confidence are defined only by a failure path, so a `design` finding rates Low and the coordinator drops it. Found by the AI review of #87. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
2026-11-15 03:38:09 -10:00 · 2026-10-22 20:22:35 -07:00
2 changed files with 6 additions and 1 deletions
@@ -42,7 +42,8 @@ issues in the changed code.
 - Style or formatting concerns handled by a linter/formatter.
 - Issues in unchanged code the PR does not touch.
 - "Consider using library X instead" suggestions.
- Theoretical concerns with no concrete failure path.
+- Theoretical concerns with no concrete failure path (or, for a `design`
+  finding, no concrete cost).
 - Nitpicks about naming or idiom when the existing convention is being followed.
 - Anything a type-checker or linter would already catch.

@@ -122,6 +122,10 @@ For every real finding, assess two separate dimensions:
  - `Low` — a bounded edge case with little correctness or safety effect. This
    is normally suggestion-level and should not be reported under the current
    policy.
+- **A `design` finding** has a concrete cost instead of a failure path. Its
+  `Confidence` is how directly the code shows that cost, and its `Impact if
+  shipped` is how large the cost is. A design cost that is only `Low` is a
+  `suggestion`.

 Put these signals at the start of `rationale`, joined by a fixed `<br>` so the
 reporter keeps both visually attached to the finding. Follow them with the