agents: streamline code review report format to omit passing prose

.agents/rules/pr.md

@@ -52,5 +52,5 @@ Before drafting any pull request description, strictly adhere to the rules in
   * During code review, inspect the PR description and comments for open
     questions, `TODO` items, or "Things we could do / follow-up" notes.
     Evaluate each item against the diff and project rules, flag unresolved
-    items with `ACTION_REQUIRED` or `USER_DECISION_REQUIRED`, and verify the
+    items with `BLOCKER`, `QUESTION`, or `HUMAN-SIGN-OFF`, and verify the
     `"do not merge"` label is applied if open questions remain.

.agents/skills/review-code/SKILL.md

@@ -85,12 +85,39 @@ file from `.agents/skills/review-code/`:
   committed and uncommitted branch changes without newer `upstream/main`
   commits.
 - Launch all sub-agents concurrently using `invoke_subagent`.
-- Update `code-review-results.md` as sub-agent responses come in.
-- The artifact must include:
-  - Overall summary and verdict across audit categories.
-  - Detailed analysis and findings from each sub-agent.
-  - Actionable findings and fix suggestions with specific code snippets, diffs,
-    and clickable file links for any violations found.
+- Update `code-review-results.md` as sub-agent responses come in, omitting all
+  passing-check prose. Do not use bold for the introduction or lead-in of a
+  bulleted list or bullet item; use **bold** for any questions the user needs
+  to answer. Structure `code-review-results.md` as follows:
+
+  ````markdown
+  # Code Review: <Target / PR>
+
+  Verdict: `<PASS | NEEDS_FIXES | NEEDS_HUMAN_SIGN_OFF>` (<N> open, <H>
+  needing human sign-off, <M> resolved)
+
+  ## Open Issues
+
+  ### <ID>. [<SEVERITY>] <Short title> — [<file>:<line>](file:///...)
+  * Problem: <1-2 sentences stating what is wrong and why.>
+  * Proposed Fix:
+    ```<lang>
+    <replacement snippet or diff>
+    ```
+  * Draft Comment: `<comment text in user's voice>`
+  * Author Response: <If the author replied to this comment thread, quote or
+    summarize their response here, bolding any question to answer.>
+  * Draft Reply: `<proposed reply in user's voice, if applicable>`
+
+  ## Resolved Issues
+
+  * ~~<ID>. [<SEVERITY>] <Short title> ([<file>:<line>](file:///...))~~ —
+    Resolved: <How it was fixed or resolved (e.g., fixed in commit N,
+    updated in working copy, or dismissed per reviewer).>
+
+  ## Passing Domains
+  <Comma-separated list of audited domains with 0 issues>
+  ````
 - Once all sub-agents finish, finalize `code-review-results.md` and provide a
   concise summary with the overall verdict and a clickable markdown link to
   `code-review-results.md` in the response.

.agents/skills/review-code/review-pr-standards-prompt.md

@@ -15,8 +15,8 @@ Your sole task is to audit PR titles and PR descriptions against
 5. Inspect the PR description and comments for open questions, `TODO` items,
    or "Things we could do / follow-ups" sections. Evaluate each item against
    the diff and project rules, flag items requiring resolution or user input
-   with `ACTION_REQUIRED` or `USER_DECISION_REQUIRED`, and verify the PR has
-   the `"do not merge"` label when open questions are present (add it or flag
-   as `ACTION_REQUIRED` if missing).
+   with `BLOCKER`, `QUESTION`, or `HUMAN-SIGN-OFF`, and verify the PR has the
+   `"do not merge"` label when open questions are present (add it or flag as
+   `BLOCKER` if missing).
 
 @.agents/skills/review-code/review-report-format.md

.agents/skills/review-code/review-report-format.md

@@ -1,6 +1,17 @@
-Provide a structured report containing:
-- Status: PASS, WARNING, ACTION_REQUIRED, USER_DECISION_REQUIRED, or
-  NOT_APPLICABLE
-- Detailed analysis and findings for each item checked
-- Actionable findings and fix suggestions with specific code snippets, diffs,
-  and clickable file links for any violations found
+Report ONLY problems/violations found. Omit passing checks entirely. If no
+issues or rule-exception justifications requiring sign-off are found, return a
+single line: `Status: PASS` (or `NOT_APPLICABLE`).
+
+Do not use bold for the introduction or lead-in of a bulleted list or bullet
+item. Use **bold** for any questions the user needs to answer.
+
+For each issue found, provide:
+
+- Title: `<Short issue title>`
+- Severity: `BLOCKER` | `SHOULD-FIX` | `NIT` | `QUESTION` | `HUMAN-SIGN-OFF`
+- Location: `[<file>:<line>](file:///...#L...)` (or `PR Description`)
+- Problem: 1-2 sentences stating what is wrong and why (or, for
+  `HUMAN-SIGN-OFF`, quoting the author's justification and evaluating whether
+  it holds up).
+- Proposed Fix: Concrete code snippet, diff, or replacement text.
+- Draft Comment: Ready-to-post comment in user's voice.