fix: soften review-strategy-matches-criteria-scope wording

The previous wording forbade any cross-file reasoning from `strategy:
individual`, which would disqualify legitimate cases like a Python code review
rule where the reviewer may need to consult other project files (imports,
references, related code, conventions) while evaluating a single changed file.

Reworded so the distinction is about whether the reviewer needs to look at the
OTHER CHANGED FILES in the same review set, not whether they need to look at
any other file at all. Individual is appropriate when focus is heavily on each
file and the reviewer is unlikely to need to see the other changed files;
matches_together is for criteria that reason about the set as a whole
(coverage, deduplication, consistency across the set).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: nhorton

src/deepwork/standard_schemas/job_yml/deepschema.yml

@@ -77,13 +77,17 @@ requirements:
     outside their scope.
 
   review-strategy-matches-criteria-scope: >
-    A review `strategy: individual` MUST only be used when every listed criterion can be
-    evaluated from a single file in isolation. Criteria that require cross-file comparison,
-    project-wide enumeration, set-level properties (coverage, minimality, deduplication),
-    or reasoning about the relationship between multiple output files MUST use
-    `strategy: matches_together` so the reviewer sees the full set at once. Using
-    `individual` with cross-cutting criteria forces each reviewer to redo the project-wide
-    scan N times and multiplies latency without improving review quality.
+    Choose the review `strategy` based on whether the criteria need to reason across the
+    other changed files in the same review set. Use `individual` when the focus is
+    heavily on each file itself and the reviewer is unlikely to need to look at the other
+    changed files in order to evaluate this one — the reviewer MAY still consult unchanged
+    project files for context (imports, references, related code, conventions), and that
+    does not disqualify `individual`. Use `matches_together` when the changed files are
+    likely to need to be looked at alongside each other during review — e.g., criteria
+    about coverage across the set, deduplication, consistency between the files, or any
+    property of the set as a whole. Picking `individual` for set-level criteria forces
+    each spawned reviewer to redo the full cross-file scan N times and multiplies latency
+    without improving review quality.
 
   review-no-redundant-context: >
     Review `instructions` MUST NOT repeat domain context already in `common_job_info` since