diff --git a/plugins/sentry-skills/skills/iterate-pr/SKILL.md b/plugins/sentry-skills/skills/iterate-pr/SKILL.md
index d94a943..6277d3a 100644
--- a/plugins/sentry-skills/skills/iterate-pr/SKILL.md
+++ b/plugins/sentry-skills/skills/iterate-pr/SKILL.md
@@ -18,10 +18,12 @@ Continuously iterate on the current branch until all CI checks pass and review f
 Fetches CI check status and extracts failure snippets from logs.
 
 ```bash
-uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py [--pr NUMBER]
+uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py [--pr NUMBER] [--summary]
 ```
 
-Returns JSON:
+Use `--summary` for a compact human-readable view (ideal for quick status checks and polling). Omit for full JSON when you need to process individual check details.
+
+Returns JSON (without `--summary`):
 ```json
 {
   "pr": {"number": 123, "branch": "feat/foo"},
@@ -38,10 +40,12 @@ Returns JSON:
 Fetches and categorizes PR review feedback using the [LOGAF scale](https://develop.sentry.dev/engineering-practices/code-review/#logaf-scale).
 
 ```bash
-uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py [--pr NUMBER]
+uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py [--pr NUMBER] [--summary]
 ```
 
-Returns JSON with feedback categorized as:
+Use `--summary` for a compact human-readable view. Omit for full JSON when you need to process individual feedback items.
+
+Returns JSON (without `--summary`) with feedback categorized as:
 - `high` - Must address before merge (`h:`, blocker, changes requested)
 - `medium` - Should address (`m:`, standard feedback)
 - `low` - Optional (`l:`, nit, style, suggestion)
@@ -150,15 +154,15 @@ git push
 
 Poll CI status and review feedback in a loop instead of blocking:
 
-1. Run `uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py` to get current CI status
+1. Run `uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py --summary` to get current CI status
 2. If all checks passed → proceed to exit conditions
-3. If any checks failed (none pending) → return to step 5
+3. If any checks failed (none pending) → run without `--summary` for full failure details, then return to step 5
 4. If checks are still pending:
-   a. Run `uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py` for new review feedback
-   b. Address any new high/medium feedback immediately (same as step 3)
+   a. Run `uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py --summary` for new review feedback
+   b. Address any new high/medium feedback immediately (run without `--summary` to get full details)
    c. If changes were needed, commit and push (this restarts CI), then continue polling
    d. Sleep 30 seconds, then repeat from sub-step 1
-5. After all checks pass, do a final feedback check: `sleep 10`, then run `uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py`. Address any new high/medium feedback — if changes are needed, return to step 6.
+5. After all checks pass, do a final feedback check: `sleep 10`, then run `uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_feedback.py --summary`. Address any new high/medium feedback — if changes are needed, return to step 6.
 
 ### 8. Repeat
 
diff --git a/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_checks.py b/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_checks.py
index 03d1edf..bd7b27c 100755
--- a/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_checks.py
+++ b/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_checks.py
@@ -168,9 +168,40 @@ def get_run_logs(run_id: int) -> str | None:
         return None
 
 
+def format_summary(output: dict[str, Any]) -> str:
+    """Format a compact summary of check status."""
+    s = output["summary"]
+    pr = output["pr"]
+    lines = [f"PR #{pr['number']} ({pr['branch']}) — {s['passed']}/{s['total']} passed"]
+
+    if s["failed"]:
+        lines.append(f"  {s['failed']} failed, {s['pending']} pending")
+    elif s["pending"]:
+        lines.append(f"  {s['pending']} pending")
+    else:
+        lines.append("  All checks passed")
+
+    non_pass = [c for c in output["checks"] if c["status"] != "pass"]
+    for c in non_pass:
+        status = c["status"].upper()
+        line = f"  [{status}] {c['name']}"
+        if c.get("run_id"):
+            line += f" (run {c['run_id']})"
+        lines.append(line)
+        if c.get("log_snippet"):
+            snippet_lines = c["log_snippet"].split("\n")[:5]
+            for sl in snippet_lines:
+                lines.append(f"    {sl}")
+            if len(c["log_snippet"].split("\n")) > 5:
+                lines.append(f"    ... ({len(c['log_snippet'].split(chr(10)))} lines total)")
+
+    return "\n".join(lines)
+
+
 def main():
     parser = argparse.ArgumentParser(description="Fetch PR CI checks with failure snippets")
     parser.add_argument("--pr", type=int, help="PR number (defaults to current branch PR)")
+    parser.add_argument("--summary", action="store_true", help="Output compact summary instead of full JSON")
     args = parser.parse_args()
 
     # Get PR info
@@ -235,7 +266,10 @@ def main():
         "checks": processed_checks,
     }
 
-    print(json.dumps(output, indent=2))
+    if args.summary:
+        print(format_summary(output))
+    else:
+        print(json.dumps(output, indent=2))
 
 
 if __name__ == "__main__":
diff --git a/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_feedback.py b/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_feedback.py
index 80517d3..84fcfac 100755
--- a/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_feedback.py
+++ b/plugins/sentry-skills/skills/iterate-pr/scripts/fetch_pr_feedback.py
@@ -307,9 +307,42 @@ def extract_feedback_item(
     return item
 
 
+def format_summary(output: dict[str, Any]) -> str:
+    """Format a compact summary of PR feedback."""
+    s = output["summary"]
+    pr = output["pr"]
+    lines = [f"PR #{pr['number']} — {s['needs_attention']} need attention ({s['high']} high, {s['medium']} medium, {s['low']} low)"]
+
+    if pr.get("review_decision"):
+        lines.append(f"  Review: {pr['review_decision']}")
+
+    if output.get("action_required"):
+        lines.append(f"  Action: {output['action_required']}")
+
+    feedback = output["feedback"]
+    for priority in ("high", "medium", "low"):
+        for item in feedback[priority]:
+            location = ""
+            if item.get("path"):
+                location = f" in {item['path']}"
+                if item.get("line"):
+                    location += f":{item['line']}"
+            bot_tag = " [review-bot]" if item.get("review_bot") else ""
+            lines.append(f"  [{priority.upper()}] @{item['author']}{bot_tag}{location}")
+            lines.append(f"    {item['body'][:120]}")
+
+    if s["resolved"]:
+        lines.append(f"  ({s['resolved']} resolved threads skipped)")
+    if s["bot_comments"]:
+        lines.append(f"  ({s['bot_comments']} bot comments skipped)")
+
+    return "\n".join(lines)
+
+
 def main():
     parser = argparse.ArgumentParser(description="Fetch and categorize PR feedback")
     parser.add_argument("--pr", type=int, help="PR number (defaults to current branch PR)")
+    parser.add_argument("--summary", action="store_true", help="Output compact summary instead of full JSON")
     args = parser.parse_args()
 
     # Get repo info
@@ -468,7 +501,10 @@ def main():
     else:
         output["action_required"] = None
 
-    print(json.dumps(output, indent=2))
+    if args.summary:
+        print(format_summary(output))
+    else:
+        print(json.dumps(output, indent=2))
 
 
 if __name__ == "__main__":