diff --git a/docs/tuning/2026-08-11-monitor-cpu.md b/docs/tuning/2026-08-11-monitor-cpu.md
index 2909b1f..5c6df07 100644
--- a/docs/tuning/2026-08-11-monitor-cpu.md
+++ b/docs/tuning/2026-08-11-monitor-cpu.md
@@ -10,7 +10,7 @@ to what the callback does can touch.
 
 Raw sampler output is in `2026-08-11-monitor-cpu/`; every figure below is a
 `mean` from one of those JSON files and can be re-derived with
-`mote_bringup/tools/node_cpu.py --summary <csv>`.
+`pixi run node-cpu --summary <csv>`.
 
 ## How it was measured
 
diff --git a/docs/tuning/2026-08-11-monitor-cpu/runs.txt b/docs/tuning/2026-08-11-monitor-cpu/runs.txt
index 059b72b..a80b551 100644
--- a/docs/tuning/2026-08-11-monitor-cpu/runs.txt
+++ b/docs/tuning/2026-08-11-monitor-cpu/runs.txt
@@ -6,7 +6,7 @@ node per sample plus load1; <tag>.json is its summary (mean/median/p95/max).
 
 Re-summarize any of them without a robot:
 
-    python -m mote_bringup.tools.node_cpu --summary <tag>.csv
+    pixi run node-cpu --summary <tag>.csv
 
   before-idle.csv        60 s. Stack as found: the drive servos were not
                          answering, so /joint_states was 1.6 Hz and /tf 33 Hz.
diff --git a/mote_bringup/tools/node_cpu.py b/mote_bringup/tools/node_cpu.py
index 8f15f2d..cbd4ab7 100755
--- a/mote_bringup/tools/node_cpu.py
+++ b/mote_bringup/tools/node_cpu.py
@@ -6,7 +6,7 @@
 compute. Answering that needs a figure per node, before and after a change, on
 the same workload:
 
-    python -m mote_bringup.tools.node_cpu --duration 60 --tag idle \
+    pixi run node-cpu --duration 60 --tag idle \
         --out docs/tuning/2026-08-11-monitor-cpu/before
 
 CPU comes from ``/proc/<pid>/stat`` as a delta of utime+stime over the interval,
@@ -31,7 +31,7 @@
 
     ros2 run mote_bringup health_monitor --ros-args -r __node:=health_monitor_b \
         -r diagnostics_agg:=diagnostics_agg_b -r health:=health_b
-    python -m mote_bringup.tools.node_cpu --nodes health_monitor,health_monitor_b
+    pixi run node-cpu --nodes health_monitor,health_monitor_b
 
 Load average is recorded beside each sample: a percentage of a core means little
 without knowing how contended the machine was when it was measured.