diff --git a/assets/CONTEXT.md b/assets/CONTEXT.md
index 8c1f4e9d..1db4a2ff 100644
--- a/assets/CONTEXT.md
+++ b/assets/CONTEXT.md
@@ -158,7 +158,7 @@ Where it says nothing, only a record on a PR whose author has write access count
 
 Checkpoint the design across review rounds.
 A review round is one `quest review` round, numbered within the branch's review session.
-Every third round, stop before fixing more findings and reconsider the approach.
+When a round whose number is a multiple of three reports findings, stop before fixing them and reconsider the approach; a clean round needs no checkpoint.
 Findings that keep coming usually mean the approach is wrong, not the last fix: brainstorm other designs that would avoid the whole class of findings, favoring simpler ones, and compare them with the current one.
 Report the alternatives and what remains, recommending to continue, rethink the approach, merge as is, or drop the PR, and let the user decide; a background agent leaves this under `## Waiting` rather than deciding it.
 Record each design change, including a rethink the user picks, in a PR comment that starts with `Design change:`, and start the next review with `quest review --new`, which restarts the count.
diff --git a/test/runner.test.ts b/test/runner.test.ts
index aeab4ffd..5229a836 100644
--- a/test/runner.test.ts
+++ b/test/runner.test.ts
@@ -1064,7 +1064,7 @@ describe("prompts", () => {
 		expect(merge).toContain("Where the workflow says to run `quest wait`, call `wait`");
 		expect(merge).toContain("# The merge workflow");
 		// The skill's design checkpoint still reaches the maintainer.
-		expect(merge).toContain("Every third round");
+		expect(merge).toContain("a multiple of three reports findings");
 	});
 
 	test("carry earlier summaries and the latest answer", () => {