diff --git a/.gitignore b/.gitignore
index 5a83ae0..52a5f4e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -76,5 +76,5 @@ docs-site/
 
 # Local agent logs / scratch
 .agent-logs/
+.codevetter/
 *.agent.log
-
diff --git a/src/lib/__tests__/rss-parser-performance.test.ts b/src/lib/__tests__/rss-parser-performance.test.ts
new file mode 100644
index 0000000..cbbc5b4
--- /dev/null
+++ b/src/lib/__tests__/rss-parser-performance.test.ts
@@ -0,0 +1,64 @@
+import { createHash } from 'node:crypto';
+import { performance } from 'node:perf_hooks';
+
+import { expect, test } from 'vitest';
+
+import { parseFeed } from '../rss-parser';
+
+const SIZES = [10, 100, 200];
+const ITERATIONS = 25;
+const EXPECTED_HASHES = new Map([
+  [10, 'e2c04d0f621e652d5cf5e180862d5ef0d3e420414fc6dd2766aa638cdd255d02'],
+  [100, 'bcc8798f918ca05af112d4a6c74f1defa2ae4073c4675bdcd65fb84dc91c2da9'],
+  [200, 'bb8a0c80775d61191a5ee3a23ea651a5b32b777250478821040a84cbce6148c0'],
+]);
+
+test('RSS parsing scales across supported feed sizes', { timeout: 30_000 }, () => {
+  const metrics: string[] = [];
+
+  for (const size of SIZES) {
+    const xml = buildFeed(size);
+    const expected = JSON.stringify(parseFeed(xml));
+    const expectedHash = createHash('sha256').update(expected).digest('hex');
+    expect(expectedHash).toBe(EXPECTED_HASHES.get(size));
+    let durationMs = 0;
+
+    for (let iteration = 0; iteration < ITERATIONS; iteration += 1) {
+      const startedAt = performance.now();
+      const parsed = parseFeed(xml);
+      durationMs += performance.now() - startedAt;
+      expect(JSON.stringify(parsed)).toBe(expected);
+      expect(createHash('sha256').update(JSON.stringify(parsed)).digest('hex')).toBe(expectedHash);
+    }
+
+    metrics.push(`size${size}=${(durationMs / ITERATIONS).toFixed(3)}ms/op`);
+  }
+
+  console.log(`[benchmark] ${metrics.join(' ')} (${ITERATIONS} iterations)`);
+  console.log(`[resource] maximum_supported_entries=${SIZES.at(-1)}`);
+});
+
+function buildFeed(size: number): string {
+  const items = Array.from({ length: size }, (_, index) => {
+    const day = String((index % 28) + 1).padStart(2, '0');
+    return `<item>
+      <guid>entry-${index}</guid>
+      <title>Research update ${index} &amp; notes</title>
+      <link>https://example.com/articles/${index}?source=reader</link>
+      <author>Author ${index % 20}</author>
+      <pubDate>Mon, ${day} Jul 2026 00:00:00 GMT</pubDate>
+      <description><![CDATA[
+        <article><h2>Finding ${index}</h2><p>This is a useful research summary with
+        <strong>evidence</strong>, context, and follow-up details for the Reader library.</p>
+        <p>Additional paragraph ${index} with <a href="https://example.com/source/${index}">source</a>.</p>
+        <script>ignored(${index})</script></article>
+      ]]></description>
+    </item>`;
+  }).join('');
+
+  return `<?xml version="1.0"?><rss version="2.0"><channel>
+    <title>Reader performance feed</title>
+    <link>https://example.com/</link>
+    ${items}
+  </channel></rss>`;
+}
diff --git a/src/lib/__tests__/rss-parser.test.ts b/src/lib/__tests__/rss-parser.test.ts
index b00842d..333862c 100644
--- a/src/lib/__tests__/rss-parser.test.ts
+++ b/src/lib/__tests__/rss-parser.test.ts
@@ -47,6 +47,19 @@ describe('parseFeed', () => {
     expect(feed.entries[0].content).not.toContain('<script');
   });
 
+  it('strips markup embedded in feed metadata', () => {
+    const rss = `<?xml version="1.0"?><rss version="2.0"><channel>
+      <title><![CDATA[Example <strong>RSS</strong>]]></title><link>https://example.com/</link>
+      <item><guid>post-1</guid><title><![CDATA[First <em>entry</em>]]></title>
+      <description>Summary</description></item>
+    </channel></rss>`;
+
+    expect(parseFeed(rss)).toMatchObject({
+      title: 'Example RSS',
+      entries: [{ title: 'First entry' }],
+    });
+  });
+
   it('normalizes Atom entries and alternate links', () => {
     const atom = `<?xml version="1.0"?><feed xmlns="http://www.w3.org/2005/Atom">
       <title>Example Atom</title><link rel="alternate" href="https://example.com/" />
diff --git a/src/lib/rss-parser.ts b/src/lib/rss-parser.ts
index 949196d..e72b931 100644
--- a/src/lib/rss-parser.ts
+++ b/src/lib/rss-parser.ts
@@ -41,6 +41,12 @@ function cleanText(value: string | null | undefined, maxLength = 2_000): string
   return (document.body.textContent ?? '').replace(/\s+/g, ' ').trim().slice(0, maxLength);
 }
 
+function normalizeText(value: string | null | undefined, maxLength = 2_000): string {
+  const text = value ?? '';
+  if (text.includes('<')) return cleanText(text, maxLength);
+  return text.replace(/\s+/g, ' ').trim().slice(0, maxLength);
+}
+
 function cleanHtml(value: string | null | undefined): string | undefined {
   const cleaned = sanitizeHtml(value ?? '', {
     allowedTags: sanitizeHtml.defaults.allowedTags,
@@ -56,7 +62,7 @@ function cleanHtml(value: string | null | undefined): string | undefined {
 function firstText(element: Element, names: string[]): string {
   for (const name of names) {
     const node = element.getElementsByTagName(name)[0];
-    const value = cleanText(node?.textContent);
+    const value = normalizeText(node?.textContent);
     if (value) return value;
   }
   return '';
@@ -132,7 +138,7 @@ export function parseOpml(xml: string): OpmlSubscription[] {
     if (!feedUrl || seen.has(feedUrl)) continue;
     seen.add(feedUrl);
     subscriptions.push({
-      title: cleanText(
+      title: normalizeText(
         outline.getAttribute('title') || outline.getAttribute('text') || new URL(feedUrl).hostname,
         500
       ),