Borrowing it
Nothing to install: this file belongs to maoxx241/vllm-ascend-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/npu-fleet-monitor/SKILL.mdgit clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/npu-fleet-monitor)<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/npu-fleet-monitor"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/npu-fleet-monitor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/npu-fleet-monitor"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/npu-fleet-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.00639 |
| Opus 5 | $0.00036 | $0.00319 |
| Sonnet 5 | $0.00014 | $0.00128 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
npu-fleet-monitor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vaws-top entry
Keep the application and its complete Agent instructions on the standalone vaws-top branch. This main-branch Skill is only the bootstrap entry.
Run the helper on the host execution plane. Deploy or reconcile:
python3 .agents/skills/npu-fleet-monitor/scripts/manage_monitor.py ensure
Locate, inspect, restart, or stop:
python3 .agents/skills/npu-fleet-monitor/scripts/manage_monitor.py status
python3 .agents/skills/npu-fleet-monitor/scripts/manage_monitor.py restart
python3 .agents/skills/npu-fleet-monitor/scripts/manage_monitor.py stop
The final JSON includes worktree and agent_skill. Use the returned worktree as <vaws-top> below.
Basic CLI
python3 <vaws-top>/scripts/vaws-top.py servers
python3 <vaws-top>/scripts/vaws-top.py capacity --min-idle 4 --max-age 180
python3 <vaws-top>/scripts/vaws-top.py status HOST
python3 <vaws-top>/scripts/vaws-top.py status HOST --cache
python3 <vaws-top>/scripts/vaws-top.py mounts HOST
python3 <vaws-top>/scripts/vaws-top.py --json npu HOST --process-details
status HOST is live by default; add --cache when stored data is sufficient. servers, capacity, mounts, and npu use cached observations by default; commands that support it accept --live. Add --json for structured output. A live query asks the centralized service to probe once; do not follow a successful result with ad hoc SSH. Capacity is observed availability, not a reservation.
Basic MCP
Run the stdio server directly or register it in the Agent's MCP configuration:
[mcp_servers.vaws_top]
command = "python3"
args = ["<vaws-top>/scripts/vaws-top-mcp.py"]
env = { VAWS_TOP_URL = "http://127.0.0.1:8789" }
The basic tools are list_npu_servers, find_npu_capacity, server_status, npu_status, and list_mounts. Host-query tools default to cached data in MCP; pass mode="live" for a fresh centralized probe.
Before advanced fleet selection, process attribution, mount discovery, or operational changes, read the returned agent_skill completely and follow it.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 55 lines · 71 tokens per session scan A b3abb444b248
npu-fleet-monitor is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 639 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.