diff --git a/.agents/skills/teleo-gcp-parity-ops/SKILL.md b/.agents/skills/teleo-gcp-parity-ops/SKILL.md
index 2a0b41f..eef09a4 100644
--- a/.agents/skills/teleo-gcp-parity-ops/SKILL.md
+++ b/.agents/skills/teleo-gcp-parity-ops/SKILL.md
@@ -158,14 +158,14 @@ before the receipt-bound cleanup:
 
 ```bash
 sudo python3 ops/attest_gcp_reasoning_compute.py \
-  --reasoning-receipt "$PRIVATE_RUN_DIR/blind-reasoning-receipt.json" \
+  --reasoning-receipt "${PRIVATE_RUN_DIR}/blind-reasoning-receipt.json" \
   --restore-run-id "$RESTORE_RUN_ID" \
   --target-db "$TARGET_DB" \
   --project teleo-501523 \
   --expected-compute-instance teleo-prod-1 \
   --expected-compute-zone europe-west6-a \
   --expected-private-network projects/teleo-501523/global/networks/teleo-staging-net \
-  --output "$PRIVATE_RUN_DIR/reasoning-compute-attestation.json"
+  --output "${PRIVATE_RUN_DIR}/reasoning-compute-attestation.json"
 ```
 
 The replay must use the Hermes virtualenv, not system Python: