diff --git a/README.md b/README.md
index 25ce5b5..9a2b898 100644
--- a/README.md
+++ b/README.md
@@ -77,7 +77,9 @@ Latency target came from the SLO review; keep the existing client API.
   cancelled). That one line pattern is the only thing the extension itself reads, for the widget.
 - The `discriminator` is the success test, written while planning: the positive observation that the
   goal succeeded and that none of the `subtle failure mode`s could fake. `evidence` is the proof,
-  filled at sign-off: each item pairs a durable artifact with a short read of it.
+  filled at sign-off: each item pairs a durable artifact with a short read of it. Prefer committed
+  artifacts (files, tests, diffs); `.pi/` is usually gitignored, so evidence there is judge-time
+  proof only and won't survive in history.
 - Small format deviations are fine; the file is read by the human and the judge, not a parser.
 - The agent prunes finished goals itself when the file gets long (evidence survives in git history
   and `## Log`).
diff --git a/src/prompts.ts b/src/prompts.ts
index 22d0cde..bf93a1c 100644
--- a/src/prompts.ts
+++ b/src/prompts.ts
@@ -66,6 +66,8 @@ Conventions:
 - Make the discriminator a concrete, checkable observation about a real artifact (a file, a test
   result, a committed diff, a metric), never about the plan file's own checkbox.
 - evidence stays empty at planning; you fill it at sign-off and a fresh read-only judge checks it.
+  Cite durable artifacts a future reader can open: committed files, test names, git diffs. .pi/ is
+  usually gitignored, so files there prove things only at judge time, not in history.
 
 When the goals are drafted, present them and stop for review. Do not begin execution.`;