diff --git a/lib/gstack-memory-helpers.ts b/lib/gstack-memory-helpers.ts
index 11a3f2239..66f2e3397 100644
--- a/lib/gstack-memory-helpers.ts
+++ b/lib/gstack-memory-helpers.ts
@@ -396,6 +396,7 @@ function extractGbrainBlock(frontmatter: string): GbrainManifest | null {
       const globM = body.match(/(?:^|\n)\s*glob\s*:\s*"?([^"\n]+?)"?\s*$/m);
       const sortM = body.match(/(?:^|\n)\s*sort\s*:\s*([^\n]+)/);
       const tailM = body.match(/(?:^|\n)\s*tail\s*:\s*(\d+)/);
+      const filterMap = parseFilterMap(body);
 
       if (idM) q.id = idM[1].trim();
       if (kindM) {
@@ -408,6 +409,7 @@ function extractGbrainBlock(frontmatter: string): GbrainManifest | null {
       if (globM) q.glob = globM[1].trim();
       if (sortM) q.sort = sortM[1].trim();
       if (tailM) q.tail = parseInt(tailM[1], 10);
+      if (filterMap) q.filter = filterMap;
 
       if (q.id && q.kind && q.render_as) {
         queries.push(q as GbrainManifestQuery);
@@ -418,6 +420,39 @@ function extractGbrainBlock(frontmatter: string): GbrainManifest | null {
   return { schema, context_queries: queries };
 }
 
+/**
+ * Parse a nested `filter:` block map out of a single context_queries item body.
+ *
+ * The block is a YAML map nested under the `filter:` key:
+ *
+ *   filter:
+ *     type: timeline
+ *     tags_contains: "repo:{repo_slug}"
+ *
+ * Each sub-key sits one indent level deeper than `filter:`. Surrounding quotes
+ * are stripped and template vars ({repo_slug}, now-7d, ...) are left intact for
+ * downstream substitution, matching how dispatchList stringifies each value
+ * into a `--filter k=v` argument. Returns undefined when there is no `filter:`
+ * block or it is empty.
+ */
+function parseFilterMap(body: string): Record<string, string> | undefined {
+  const lines = body.split("\n");
+  const filterIdx = lines.findIndex((l) => /^\s*filter\s*:\s*$/.test(l));
+  if (filterIdx === -1) return undefined;
+  const filterIndent = lines[filterIdx].match(/^\s*/)![0].length;
+
+  const filter: Record<string, string> = {};
+  for (let i = filterIdx + 1; i < lines.length; i++) {
+    const line = lines[i];
+    if (line.trim() === "") continue; // tolerate blank lines within the block
+    const indent = line.match(/^\s*/)![0].length;
+    if (indent <= filterIndent) break; // dedent to a sibling key ends the block
+    const kv = line.match(/^\s*([A-Za-z0-9_]+)\s*:\s*"?(.*?)"?\s*$/);
+    if (kv) filter[kv[1]] = kv[2].trim();
+  }
+  return Object.keys(filter).length > 0 ? filter : undefined;
+}
+
 // ── Public: withErrorContext ──────────────────────────────────────────────
 
 const ERROR_LOG_PATH = join(gstackHome(), ".gbrain-errors.jsonl");
diff --git a/test/gstack-memory-helpers.test.ts b/test/gstack-memory-helpers.test.ts
index 7b356a99c..04edd8fe8 100644
--- a/test/gstack-memory-helpers.test.ts
+++ b/test/gstack-memory-helpers.test.ts
@@ -244,6 +244,62 @@ body
     expect(m!.context_queries[0].id).toBe("complete");
     rmSync(dir, { recursive: true, force: true });
   });
+
+  it("parses a nested filter: block on a list query", () => {
+    const dir = mkdtempSync(join(tmpdir(), "gstack-test-"));
+    const file = join(dir, "filtered.md");
+    writeFileSync(
+      file,
+      `---
+name: investigate
+gbrain:
+  schema: 1
+  context_queries:
+    - id: prior-investigations
+      kind: list
+      filter:
+        type: timeline
+        tags_contains: "repo:{repo_slug}"
+        content_contains: "investigate"
+      sort: updated_at_desc
+      limit: 5
+      render_as: "## Prior investigations in this repo"
+    - id: recent-no-filter
+      kind: list
+      sort: created_at_desc
+      limit: 3
+      render_as: "## Recent (no filter)"
+---
+
+body
+`
+    );
+
+    const m = parseSkillManifest(file);
+    expect(m).not.toBeNull();
+    expect(m!.context_queries).toHaveLength(2);
+
+    // The filter: sub-block is parsed into a key/value map, with quotes
+    // stripped and template vars left intact for downstream substitution.
+    const filtered = m!.context_queries[0];
+    expect(filtered.id).toBe("prior-investigations");
+    expect(filtered.filter).toEqual({
+      type: "timeline",
+      tags_contains: "repo:{repo_slug}",
+      content_contains: "investigate",
+    });
+    // Sibling fields on the same item still parse alongside the filter.
+    expect(filtered.sort).toBe("updated_at_desc");
+    expect(filtered.limit).toBe(5);
+    expect(filtered.render_as).toBe("## Prior investigations in this repo");
+
+    // A list query with no filter: leaves filter undefined (no regression).
+    expect(m!.context_queries[1].id).toBe("recent-no-filter");
+    expect(m!.context_queries[1].filter).toBeUndefined();
+    expect(m!.context_queries[1].sort).toBe("created_at_desc");
+
+    rmSync(dir, { recursive: true, force: true });
+  });
 });
 
 // ── withErrorContext ───────────────────────────────────────────────────────