Establishes CPU/GPU baselines before resource-intensive operations like builds, training, or tests. Guides scoping, instrumentation, throttling, and logging for regression detection.
From conservenpx claudepluginhub athola/claude-night-market --plugin conserveThis skill uses the workspace's default tool permissions.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Guides idea refinement into designs: explores context, asks questions one-by-one, proposes approaches, presents sections for approval, writes/review specs before coding.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
token-conservation).cpu-gpu-performance:baselinecpu-gpu-performance:scopecpu-gpu-performance:instrumentcpu-gpu-performance:throttlecpu-gpu-performance:logCapture current utilization:
uptimeps -eo pcpu,cmd | headnvidia-smi --query-gpu=utilization.gpu,memory.used --format=csvNote which hosts/GPUs are already busy.
Record any CI/cluster budgets (time quotas, GPU hours) before launching work.
Set a per-task CPU minute / GPU minute budget that respects those limits.
pytest -kcargo test <module>perfintel vtunecargo flamegraphnvidia-smi dmonnsysnvprofnice, ionice, or Kubernetes/Slurm quotas to prevent starvation of shared nodes.Conclude by documenting the commands that were run and their resource cost (duration, CPU%, GPU%), confirming whether they remained within the per-task budget. If a full suite or long training run was necessary, justify why selective or staged approaches were not feasible. Capture any follow-up tasks, such as adding a new test marker or profiling documentation, to simplify future sessions.
pytest tests/test_orders.py -k test_refund instead of pytest -m slow"nvidia-smi dmon output to prove GPU idle time before scaling"Command not found Ensure all dependencies are installed and in PATH
Permission errors Check file permissions and run with appropriate privileges
Unexpected behavior
Enable verbose logging with --verbose flag