diff --git a/.agents/skills/gstack-ship/SKILL.md b/.agents/skills/gstack-ship/SKILL.md
index ed8147ce..08e7f063 100644
--- a/.agents/skills/gstack-ship/SKILL.md
+++ b/.agents/skills/gstack-ship/SKILL.md
@@ -611,10 +611,14 @@ Use AskUserQuestion:
 - Continue with the workflow — treat the pre-existing failure as non-blocking.
 
 **If "Blame + assign GitHub issue" (collaborative only):**
-- Find who last modified the failing area:
+- Find who likely broke it. Check BOTH the test file AND the production code it tests:
   ```bash
+  # Who last touched the failing test?
   git log --format="%an (%ae)" -1 -- <failing-test-file>
+  # Who last touched the production code the test covers? (often the actual breaker)
+  git log --format="%an (%ae)" -1 -- <source-file-under-test>
   ```
+  If these are different people, prefer the production code author — they likely introduced the regression.
 - Create a GitHub issue assigned to that person:
   ```bash
   gh issue create \
diff --git a/bin/gstack-repo-mode b/bin/gstack-repo-mode
index be44feba..0c9ce904 100755
--- a/bin/gstack-repo-mode
+++ b/bin/gstack-repo-mode
@@ -12,7 +12,8 @@
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-eval $("$SCRIPT_DIR/gstack-slug" 2>/dev/null) || { echo "REPO_MODE=unknown"; exit 0; }
+# Compute SLUG directly (avoid eval of gstack-slug — branch names can contain shell metacharacters)
+SLUG=$(git remote get-url origin 2>/dev/null | sed 's|.*[:/]\([^/]*/[^/]*\)\.git$|\1|;s|.*[:/]\([^/]*/[^/]*\)$|\1|' | tr '/' '-')
 [ -z "${SLUG:-}" ] && { echo "REPO_MODE=unknown"; exit 0; }
 
 # Validate: only allow known values (prevent shell injection via source <(...))
@@ -39,7 +40,9 @@ if [ -f "$CACHE_FILE" ]; then
 fi
 
 # Compute from git history (90-day window)
-SHORTLOG=$(git shortlog -sn --since="90 days ago" --no-merges HEAD 2>/dev/null | head -20)
+# Use default branch (not HEAD) to avoid feature-branch sampling bias
+DEFAULT_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/||' || echo "origin/main")
+SHORTLOG=$(git shortlog -sn --since="90 days ago" --no-merges "$DEFAULT_BRANCH" 2>/dev/null | head -20)
 if [ -z "$SHORTLOG" ]; then
   echo "REPO_MODE=unknown"
   exit 0
diff --git a/scripts/gen-skill-docs.ts b/scripts/gen-skill-docs.ts
index 820671a6..ce33035a 100644
--- a/scripts/gen-skill-docs.ts
+++ b/scripts/gen-skill-docs.ts
@@ -353,10 +353,14 @@ Use AskUserQuestion:
 - Continue with the workflow — treat the pre-existing failure as non-blocking.
 
 **If "Blame + assign GitHub issue" (collaborative only):**
-- Find who last modified the failing area:
+- Find who likely broke it. Check BOTH the test file AND the production code it tests:
   \`\`\`bash
+  # Who last touched the failing test?
   git log --format="%an (%ae)" -1 -- <failing-test-file>
+  # Who last touched the production code the test covers? (often the actual breaker)
+  git log --format="%an (%ae)" -1 -- <source-file-under-test>
   \`\`\`
+  If these are different people, prefer the production code author — they likely introduced the regression.
 - Create a GitHub issue assigned to that person:
   \`\`\`bash
   gh issue create \\
diff --git a/ship/SKILL.md b/ship/SKILL.md
index 692bcb75..24941c0a 100644
--- a/ship/SKILL.md
+++ b/ship/SKILL.md
@@ -621,10 +621,14 @@ Use AskUserQuestion:
 - Continue with the workflow — treat the pre-existing failure as non-blocking.
 
 **If "Blame + assign GitHub issue" (collaborative only):**
-- Find who last modified the failing area:
+- Find who likely broke it. Check BOTH the test file AND the production code it tests:
   ```bash
+  # Who last touched the failing test?
   git log --format="%an (%ae)" -1 -- <failing-test-file>
+  # Who last touched the production code the test covers? (often the actual breaker)
+  git log --format="%an (%ae)" -1 -- <source-file-under-test>
   ```
+  If these are different people, prefer the production code author — they likely introduced the regression.
 - Create a GitHub issue assigned to that person:
   ```bash
   gh issue create \