diff --git a/template-multi-extension/test/expected/base.out b/template-multi-extension/test/expected/base.out
index 7169d4a..06dd87a 100644
--- a/template-multi-extension/test/expected/base.out
+++ b/template-multi-extension/test/expected/base.out
@@ -1,2 +1,3 @@
+\set ECHO none
 
 multi_ext_ok
diff --git a/template-multi-extension/test/sql/base.sql b/template-multi-extension/test/sql/base.sql
index f32747d..744d8ec 100644
--- a/template-multi-extension/test/sql/base.sql
+++ b/template-multi-extension/test/sql/base.sql
@@ -1,3 +1,6 @@
+\set ECHO none
+-- DO NOT REMOVE: pg_regress runs psql with echo-all, so without this the SQL
+-- input is echoed into the output and never matches expected/base.out.
 \a
 \t
 SELECT pg_sleep(.1);
diff --git a/test/lib/foundation.bats b/test/lib/foundation.bats
index 8ea3124..1143411 100644
--- a/test/lib/foundation.bats
+++ b/test/lib/foundation.bats
@@ -29,7 +29,7 @@
 #
 # All other tests depend on this foundation:
 # - Sequential tests (01-meta, 02-dist, 03-setup-final) build on this base
-# - Independent tests (doc, make-results) copy this base to their own environment
+# - Independent tests (doc, make-test) copy this base to their own environment
 #
 # The foundation is created once in .envs/foundation/ and then copied to other
 # test environments for speed. Run `make foundation` to rebuild from scratch.
diff --git a/test/sequential/00-validate-tests.bats b/test/sequential/00-validate-tests.bats
index 8c86249..c0d8d9a 100755
--- a/test/sequential/00-validate-tests.bats
+++ b/test/sequential/00-validate-tests.bats
@@ -191,7 +191,7 @@ teardown_file() {
   done
 }
 
-@test "only make-results tests call make results" {
+@test "only make-test tests call make results" {
   # make results overwrites expected output files, so it should only be used
   # in tests specifically designed to test that functionality.
   local test_root="$BATS_TEST_DIRNAME/.."
@@ -205,8 +205,8 @@ teardown_file() {
   fi
   assert_success  # Any status other than 0 or 1 is a real grep error
 
-  # Filter out the tests that are allowed to call make results
-  run grep -v -e 'make-results\.bats$' -e 'test-verify-results\.bats$' <<< "$output"
+  # Filter out the test that is allowed to call make results
+  run grep -v -e 'make-test\.bats$' <<< "$output"
 
   # grep returns 1 when all lines are filtered out -- that's the success case
   if [ "$status" -eq 1 ]; then
@@ -217,7 +217,7 @@ teardown_file() {
   # If we get here, there are violations (grep returned 0, meaning matches remain)
   echo "FAIL: The following tests call 'make results' but should not:" >&2
   echo "$output" >&2
-  echo "Only make-results.bats and test-verify-results.bats may call 'make results'" >&2
+  echo "Only make-test.bats may call 'make results'" >&2
   return 1
 }
 
diff --git a/test/standard/make-results.bats b/test/standard/make-results.bats
deleted file mode 100755
index 41f1e01..0000000
--- a/test/standard/make-results.bats
+++ /dev/null
@@ -1,99 +0,0 @@
-#!/usr/bin/env bats
-
-# Test: make results functionality
-#
-# Tests that make results correctly updates expected output files:
-# - Modifies expected output to create a mismatch
-# - Verifies make test detects the mismatch
-# - Runs make results to update expected output
-# - Verifies make test now passes
-#
-# Not tested here:
-# - make results when already up-to-date (idempotent case). Safe to re-run,
-#   but the extra make test invocation adds non-trivial time for little value.
-
-load ../lib/helpers
-
-setup_file() {
-  setup_topdir
-
-  # Independent test - gets its own isolated environment with foundation TEST_REPO
-  load_test_env "make-results"
-  ensure_foundation "$TEST_DIR"
-
-  # Every test in this file requires PostgreSQL. Skip expensive setup if unavailable.
-  if ! check_postgres_available; then
-    return 0
-  fi
-
-  cd "$TEST_REPO"
-
-  # State modification: Ensure expected output exists.
-  # The template should already have it, but guard against it being missing or empty.
-  if [ ! -f "test/expected/pgxntool-test.out" ] || [ ! -s "test/expected/pgxntool-test.out" ]; then
-    make results
-  fi
-
-  # State modification: Ensure expected output is committed to git.
-  # Later tests create a mismatch and check git status to verify it,
-  # which only works if the baseline is committed.
-  local status_output
-  status_output=$(git status --porcelain test/expected/pgxntool-test.out)
-  if [ -n "$status_output" ]; then
-    git add test/expected/pgxntool-test.out
-    git commit -m "Add baseline expected output"
-  fi
-}
-
-setup() {
-  skip_if_no_postgres
-  load_test_env "make-results"
-  cd "$TEST_REPO"
-}
-
-@test "can modify expected output to create mismatch" {
-  # Add a blank line to create a difference
-  echo >> test/expected/pgxntool-test.out
-
-  # Verify file was modified (should show as modified since it's committed)
-  run git status --porcelain test/expected/pgxntool-test.out
-  [ -n "$output" ]
-  echo "$output" | grep -qE "^.M"
-}
-
-@test "make test shows diff with modified expected output" {
-  # Run make test (should show diffs due to mismatch)
-  # Note: make test doesn't exit non-zero due to .IGNORE: installcheck
-  run make test
-
-  # Check that diff output was produced (either in output or test/output directory exists)
-  # test/output is created when tests fail
-  [ -d "test/output" ] || echo "$output" | grep -q "diff"
-}
-
-@test "make results is blocked by verify-results when tests fail" {
-  # The previous test ran make test which failed (mismatch), creating regression.diffs.
-  # With the fixed ordering (results: test verify-results), make results re-runs
-  # make test first (still fails → regression.diffs), then verify-results blocks.
-  # This test verifies that verify-results correctly intercepts failing results.
-  run make results
-  assert_failure
-  assert_contains "$output" "Cannot run 'make results'"
-}
-
-@test "make results updates expected output" {
-  # Run make results with verify-results disabled to actually fix the mismatch.
-  # regression.diffs still exists from the previous test's make test run.
-  # Disabling verify-results lets make results run make test and copy the fresh
-  # results to expected/, fixing the mismatch.
-  run make PGXNTOOL_ENABLE_VERIFY_RESULTS=no results
-  assert_success
-}
-
-@test "make test succeeds after make results" {
-  # Now make test should pass
-  run make test
-  assert_success
-}
-
-# vi: expandtab sw=2 ts=2
diff --git a/test/standard/make-test.bats b/test/standard/make-test.bats
index be161a6..135986f 100755
--- a/test/standard/make-test.bats
+++ b/test/standard/make-test.bats
@@ -1,22 +1,50 @@
 #!/usr/bin/env bats
 
-# Test: make test framework
+# Test: make test / make results / verify-results
 #
-# Tests that the test framework works correctly:
-# - Creates test/output directory when needed
-# - Uses test/output for expected outputs
-# - Doesn't recreate output when directories removed
+# These three targets are one tightly-coupled pipeline -- `make results` and
+# `make verify-results` only exist to safely update the expected output that
+# `make test` checks against -- so they share a single file and a single
+# foundation-copied environment rather than three. Covers:
+# - `make test` succeeds against the template's known-good state
+# - EXTRA_CLEAN targets the real $(TESTOUT)/results/ directory (issue #7)
+# - unique per-directory database naming (REGRESS_DBNAME)
+# - check-stale-expected catches orphaned test/expected/*.out files (issue #14)
+# - verify-results blocks `make results` when tests are failing, detects
+#   pgtap failures, and can be disabled
 
 load ../lib/helpers
 
 setup_file() {
-  # Set TOPDIR
   setup_topdir
 
-
   # Independent test - gets its own isolated environment with foundation TEST_REPO
   load_test_env "make-test"
   ensure_foundation "$TEST_DIR"
+
+  # The verify-results/results tests below need a committed baseline expected
+  # output file so they can create a detectable mismatch against it. Skip
+  # this if PostgreSQL is unavailable -- `make results` needs a live server,
+  # and those tests skip themselves via skip_if_no_postgres anyway.
+  if check_postgres_available; then
+    cd "$TEST_REPO"
+
+    # State modification: Ensure expected output exists.
+    # The template should already have it, but guard against it being missing or empty.
+    if [ ! -f "test/expected/pgxntool-test.out" ] || [ ! -s "test/expected/pgxntool-test.out" ]; then
+      make results
+    fi
+
+    # State modification: Ensure expected output is committed to git.
+    # The verify-results/results tests below create a mismatch and check git
+    # status to verify it, which only works if the baseline is committed.
+    local status_output
+    status_output=$(git status --porcelain test/expected/pgxntool-test.out)
+    if [ -n "$status_output" ]; then
+      git add test/expected/pgxntool-test.out
+      git commit -m "Add baseline expected output"
+    fi
+  fi
 }
 
 setup() {
@@ -24,54 +52,11 @@ setup() {
   cd "$TEST_REPO"
 }
 
-@test "test/output directory does not exist initially" {
-  # Skip if already exists from previous run
-  if [ -d "test/output" ]; then
-    skip "test/output already exists"
-  fi
-
-  assert_dir_not_exists "test/output"
-}
-
-@test "make test creates test/output directory" {
-  # Skip if already exists
-  if [ -d "test/output" ]; then
-    skip "test/output already exists"
-  fi
-
-  # pg_regress does NOT create input/ or output/ directories - they are optional
-  # INPUT directories. We need to create it ourselves for this test.
-  mkdir -p test/output
-
-  # Verify directory was created
-  assert_dir_exists "test/output"
-}
-
-@test "test/output is a directory" {
-  assert_dir_exists "test/output"
-}
-
 @test "make test succeeds" {
   run make test
   assert_success
 }
 
-@test "can remove test directories" {
-  # Remove input and output
-  rm -rf test/input test/output
-
-  assert_dir_not_exists "test/output"
-}
-
-@test "make test doesn't recreate output when directories removed" {
-  # After removing directories, output should not be recreated
-  # We only care that the directory doesn't get recreated, not that tests pass
-  run make test
-
-  # test/output should NOT exist (correct behavior)
-  assert_dir_not_exists "test/output"
-}
-
 @test "repository is still functional" {
   # Basic sanity check
   assert_file_exists "Makefile"
@@ -117,10 +102,19 @@ setup() {
 @test "unique db name: create test SQL file and expected output" {
   skip_if_no_postgres
 
-  # Create a simple SQL test that queries the current database name
-  # Use \t and \a so output is just the bare value (no headers/formatting)
+  # Create a simple SQL test that queries the current database name.
+  # \set ECHO none is required: pg_regress always runs test files through
+  # `psql -a` (echo mode -- see psql_start_test() in pg_regress_main.c), so
+  # without it every input line, including \a/\t themselves, gets echoed
+  # verbatim into the output before it runs. This is the same convention
+  # template/test/sql/base.sql already documents and relies on -- hand-writing
+  # just the bare value here (without \set ECHO none) previously produced an
+  # expected file that could never match pg_regress's real output; that
+  # mismatch went unnoticed because make test's own diff output was never
+  # inspected here.
   mkdir -p test/sql
   cat > test/sql/dbname.sql <<'EOF'
+\set ECHO none
 \a
 \t
 SELECT current_database();
@@ -132,9 +126,10 @@ EOF
   expected_dbname=$(make print-REGRESS_DBNAME 2>&1 | sed -n 's/.*set to "\(.*\)"/\1/p')
   [ -n "$expected_dbname" ] || error "Could not extract REGRESS_DBNAME from make"
 
-  # Manually create the expected output file
+  # Expected output is just the echoed `\set ECHO none` line itself (read
+  # while ECHO was still "all") followed by the query's own bare result.
   mkdir -p test/expected
-  printf '%s\n' "$expected_dbname" > test/expected/dbname.out
+  printf '\\set ECHO none\n%s\n' "$expected_dbname" > test/expected/dbname.out
 }
 
 @test "unique db name: make test passes" {
@@ -284,4 +279,156 @@ EOF
   assert_success
 }
 
+# ============================================================================
+# verify-results / make results (issue #14)
+# ============================================================================
+#
+# pgxntool makes verify-results depend on test (verify-results: test), so
+# `make results` re-runs the tests and checks the FRESH regression.diffs,
+# even under make -j.
+
+@test "verify-results succeeds with clean template state" {
+  skip_if_no_postgres
+
+  run make verify-results
+  assert_success
+}
+
+@test "verify-results depends on test execution" {
+  # pgxntool makes verify-results depend on test (verify-results: test) so
+  # that `make results` re-runs the tests and checks the FRESH
+  # regression.diffs, even under make -j. Confirm the dependency is wired: a
+  # dry-run of verify-results must include the installcheck recipe pulled in
+  # via the test target.
+  run make -n verify-results 2>&1
+  assert_success
+  assert_contains "$output" "installcheck"
+}
+
+@test "can modify expected output to create mismatch" {
+  skip_if_no_postgres
+
+  # Add a blank line to create a difference. This mismatch stays in place
+  # through the rest of this section -- "make results updates expected
+  # output" below is what finally fixes it.
+  echo >> test/expected/pgxntool-test.out
+
+  # Verify file was modified (should show as modified since it's committed)
+  run git status --porcelain test/expected/pgxntool-test.out
+  [ -n "$output" ]
+  echo "$output" | grep -qE "^.M"
+}
+
+@test "make test shows diff with modified expected output" {
+  skip_if_no_postgres
+
+  # Run make test (should show diffs due to mismatch).
+  # Note: make test doesn't exit non-zero due to .IGNORE: installcheck.
+  run make test
+
+  echo "$output" | grep -q "diff"
+}
+
+@test "make results is blocked by verify-results when tests fail" {
+  skip_if_no_postgres
+
+  # The previous test's mismatch is still in place. verify-results depends
+  # on test, so its rerun of the suite fails again and blocks make results.
+  run make results
+  assert_failure
+  assert_contains "$output" "Cannot run 'make results'"
+}
+
+@test "verify-results blocks when invoked directly, not just via results" {
+  skip_if_no_postgres
+
+  # Same mismatch as above, but this test invokes `make verify-results`
+  # directly instead of going through `results` -- a distinct entry point
+  # worth covering on its own, since `results` only reaches verify-results
+  # as a prerequisite.
+  run make verify-results
+  assert_failure
+  assert_contains "$output" "Tests are failing"
+  assert_contains "$output" "Cannot run 'make results'"
+}
+
+@test "verify-results can be disabled" {
+  # With verify-results disabled, results depends only on test, so its
+  # dry-run never mentions the verify-results block message. We check
+  # for the actual block message rather than the bare string
+  # "verify-results", since that could spuriously match make's own
+  # "Entering directory" banners depending on the environment's path.
+  run make -n results PGXNTOOL_ENABLE_VERIFY_RESULTS=no 2>&1
+  assert_success
+  assert_not_contains "$output" "Cannot run 'make results'"
+}
+
+@test "make results updates expected output" {
+  skip_if_no_postgres
+
+  # Run make results with verify-results disabled to actually fix the mismatch.
+  # Disabling verify-results lets make results run the suite and copy the
+  # fresh results to expected/, fixing the mismatch.
+  run make PGXNTOOL_ENABLE_VERIFY_RESULTS=no results
+  assert_success
+}
+
+@test "make test succeeds after make results" {
+  skip_if_no_postgres
+
+  # Now make test should pass
+  run make test
+  assert_success
+}
+
+@test "verify-results detects pgtap failures in result files" {
+  skip_if_no_postgres
+
+  mkdir -p test/results
+  cat > test/results/pgtap_fail.out <<'EOF'
+1..2
+ok 1 - passing test
+not ok 2 - failing test
+EOF
+
+  run make verify-results
+  assert_failure
+  assert_contains "$output" "pgtap failure detected"
+
+  rm -f test/results/pgtap_fail.out
+}
+
+@test "verify-results ignores pgtap TODO failures" {
+  skip_if_no_postgres
+
+  mkdir -p test/results
+  cat > test/results/pgtap_todo.out <<'EOF'
+1..1
+not ok 1 - known issue # TODO fix later
+EOF
+
+  run make verify-results
+  assert_success
+
+  rm -f test/results/pgtap_todo.out
+}
+
+@test "verify-results detects pgtap plan mismatch" {
+  skip_if_no_postgres
+
+  mkdir -p test/results
+  cat > test/results/pgtap_plan.out <<'EOF'
+1..3
+ok 1 - test one
+ok 2 - test two
+# Looks like you planned 3 tests but ran 2
+EOF
+
+  run make verify-results
+  assert_failure
+  assert_contains "$output" "pgtap plan mismatch"
+
+  rm -f test/results/pgtap_plan.out
+}
+
 # vi: expandtab sw=2 ts=2
diff --git a/test/standard/test-verify-results.bats b/test/standard/test-verify-results.bats
deleted file mode 100644
index 3279e28..0000000
--- a/test/standard/test-verify-results.bats
+++ /dev/null
@@ -1,118 +0,0 @@
-#!/usr/bin/env bats
-
-# Test: verify-results feature
-#
-# Validates that verify-results correctly blocks make results when tests are
-# failing, detects pgtap failures, and can be disabled.
-#
-# NOTE: pgxntool makes verify-results depend on test (verify-results: test), so
-# `make verify-results` re-runs the suite and therefore requires PostgreSQL. The
-# pgtap-detection cases below plant files in test/results/ (which survive the
-# fresh test run) rather than a regression.diffs (which the fresh run overwrites).
-
-load ../lib/helpers
-
-setup_file() {
-  setup_topdir
-
-  load_test_env "verify-results"
-  ensure_foundation "$TEST_DIR"
-}
-
-setup() {
-  load_test_env "verify-results"
-  cd "$TEST_REPO"
-}
-
-@test "verify-results succeeds with clean template state" {
-  run make verify-results
-  assert_success
-}
-
-@test "verify-results depends on test execution" {
-  # pgxntool makes verify-results depend on test (verify-results: test) so that
-  # `make results` re-runs the tests and checks the FRESH regression.diffs, even
-  # under make -j. Confirm the dependency is wired: a dry-run of verify-results
-  # must include the installcheck recipe pulled in via the test target.
-  run make -n verify-results 2>&1
-  assert_success
-  assert_contains "$output" "installcheck"
-}
-
-@test "verify-results blocks when a test actually fails" {
-  # verify-results depends on test, so `make verify-results` re-runs the suite.
-  # A planted regression.diffs would just be overwritten by that fresh run, so
-  # force a REAL failure by corrupting an expected file, then confirm
-  # verify-results refuses to let make results proceed.
-  echo >> test/expected/base.out
-
-  run make verify-results
-  assert_failure
-  assert_contains "$output" "Tests are failing"
-  assert_contains "$output" "Cannot run 'make results'"
-
-  # Restore clean state for the tests that follow.
-  run git checkout -- test/expected/base.out
-  assert_success
-  rm -f test/regression.diffs
-}
-
-@test "verify-results can be disabled" {
-  # With verify-results disabled, results depends only on test, so its dry-run
-  # never mentions the verify-results block message.
-  run make -n results PGXNTOOL_ENABLE_VERIFY_RESULTS=no 2>&1
-  assert_success
-  # Check that verify-results recipe commands are not in the dry-run output.
-  # Note: we cannot check for the string "verify-results" directly because the
-  # test environment directory path contains "verify-results" and appears in
-  # make's "Entering directory" messages.
-  assert_not_contains "$output" "Cannot run 'make results'"
-
-  rm -f test/regression.diffs
-}
-
-@test "verify-results detects pgtap failures in result files" {
-  mkdir -p test/results
-  cat > test/results/pgtap_fail.out <<'EOF'
-1..2
-ok 1 - passing test
-not ok 2 - failing test
-EOF
-
-  run make verify-results
-  assert_failure
-  assert_contains "$output" "pgtap failure detected"
-
-  rm -f test/results/pgtap_fail.out
-}
-
-@test "verify-results ignores pgtap TODO failures" {
-  mkdir -p test/results
-  cat > test/results/pgtap_todo.out <<'EOF'
-1..1
-not ok 1 - known issue # TODO fix later
-EOF
-
-  run make verify-results
-  assert_success
-
-  rm -f test/results/pgtap_todo.out
-}
-
-@test "verify-results detects pgtap plan mismatch" {
-  mkdir -p test/results
-  cat > test/results/pgtap_plan.out <<'EOF'
-1..3
-ok 1 - test one
-ok 2 - test two
-# Looks like you planned 3 tests but ran 2
-EOF
-
-  run make verify-results
-  assert_failure
-  assert_contains "$output" "pgtap plan mismatch"
-
-  rm -f test/results/pgtap_plan.out
-}
-
-# vi: expandtab sw=2 ts=2