diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
new file mode 100644
index 0000000000..9ccb1f7117
--- /dev/null
+++ b/.github/pull_request_template.md
@@ -0,0 +1,10 @@
+<!-- Required for issue/PR auto-link. Use Fixes / Closes / Resolves so the
+     linked issue closes on merge and release-time reverse lookup works.
+     Delete this whole block if the PR genuinely doesn't close any issue. -->
+Fixes #
+
+## Summary
+-
+
+## Validation
+-
diff --git a/AGENTS.md b/AGENTS.md
index 9230fdbb77..382a049141 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -97,6 +97,7 @@ The following is a working playbook for routine bug follow-ups, distilled from r
 - **Hold the spec's scope.** Defects discovered outside the bug's described boundary belong in a follow-up — their own red spec, their own PR — not in this fix. List them in the PR body's "Adjacent issues" section with the rationale and move on.
 - **Let the fix read as an invariant.** Prefer a named helper whose docblock describes what must hold over a bolt-on `if` guard with apologetic history-comments. The call site should read as intent.
 - **Diff against the baseline.** When neighboring suites have pre-existing failures, stash or check out upstream before claiming "no new failures."
+- **Link the issue from the PR body.** Use `Fixes #N` / `Closes #N` / `Resolves #N` so the issue auto-closes on merge and the release-time reverse lookup (`gh issue view N --json closedByPullRequestsReferences` → `git tag --contains <merge sha>`) actually has a chain to follow. The repo's PR template prompts for this; deleting the prompt is fine when the PR genuinely closes nothing.
 - **Stage human verification for visible bugs.** When the symptom needs an eye to confirm — UI, platform-native behavior, animations, race conditions a unit test can't see — green specs alone aren't acceptance. Stand up a buggy-vs-fix comparison the reviewer can drive themselves (typical shape: two namespaced runtimes, one on `main`, one on the fix branch), and seed any required data only through production HTTP APIs; source-level test backdoors invalidate the verification because they prove a fake flow rather than the real one.
 
 For a worked example of one full loop (red e2e spec → fix → green), see `e2e/tests/dialog/stop-reconciles-message.test.ts` (issue #135).