Borrowing it
Nothing to install: this file belongs to ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-. 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/ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-/main/.agents/skills/gpu-server-management/SKILL.mdgit clone --depth 1 https://github.com/ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-Wrote 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/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/gpu-server-management)<a href="https://agentmods.dev/skills/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/gpu-server-management"><img src="https://agentmods.dev/badge/skills/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/gpu-server-management/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/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/gpu-server-management"><img src="https://agentmods.dev/badge/skills/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/gpu-server-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00226 | $0.05809 |
| Opus 5 | $0.00113 | $0.02905 |
| Sonnet 5 | $0.00045 | $0.01162 |
| Haiku 4.5 | $0.00023 | $0.00581 |
Grade A, and why
gpu-server-management scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 直连测速: curl -s -w "%{speed_download}" -o /dev/null --max-time 8 "<URL>" How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPU Server Management & Next-Gen Proxy Orchestration
A shared registry and high-performance multi-proxy orchestration engine that lets you drive many remote GPU machines as one pool. The database is collective memory: what one agent configures, discovers, or encounters (including pitfalls, troubleshooting workarounds, and server notes), every later agent reads back — so setup work is never repeated and machines cooperate seamlessly.
What this unlocks — the reason to reach for these tools:
| Goal | Tool | In one line |
|---|---|---|
| 遇错优先查询·RAG 问题库 | query_troubleshooting { query } |
【遇到报错第一顺位调用】 秒级语义检索全集群所有踩坑经验 (pitfalls)、节点备忘 (notes) 与备份索引，返回已验证的解决方案与执行命令。 |
| Dual Timers: Lease & Task | get_servers / claim_server |
Tracks 2 distinct timers: 1. Server physical lifespan remaining (server_expires_at) vs. 2. Task countdown lease (duration_minutes). |
| Server Pitfalls & Caveats (踩坑与避坑记忆) | record_pitfall / get_servers |
Records environment traps, PyTorch/CUDA conflicts, OOM mitigations, and network quirks per server, auto-returned on every get_servers call. |
| Clash & V2Ray Subscriptions | import_proxy_subscription |
Auto-fetches and parses Clash YAML / Base64 subscriptions, batch-populating proxy nodes with region tags (HK/JP/US/SG). |
| Domain-Aware Routing & Racing | plan_network_relay |
Domain profiling (HuggingFace / GitHub / S3) + Direct vs Multi-Proxy concurrent Range benchmark (哪个快选哪个). |
| Multi-Proxy Chunk Aggregator | plan_network_relay |
For >500MB large weights/datasets, splits into 64MB chunks across multiple proxies in parallel with auto-failover and resume. |
| Intelligent Dual-Mode Backup | plan_server_backup |
Physical remaining > 1h: only backup experiment outputs (exclude datasets to keep affinity); Physical remaining <= 1h: full asset evacuation. |
| RAG Vector Search for Backups | query_backup_index |
Semantic natural-language / keyword RAG search across all historical checkpoints and backups (IP lifecycle-bound). |
| Dataset Affinity (数据就近计算) | plan_task_allocation { preferred_datasets } |
Route jobs directly to nodes with pre-cached datasets (+100k score boost), avoiding huge network downloads. |
| Manage Datasets | register_dataset / remove_dataset |
Record dataset paths & sizes so subsequent agents reuse local data paths without re-downloading. |
| Borrow disk | plan_disk_share |
Mount a disk-rich machine onto one that ran out of space (turn a peer into a cloud disk). |
| Unified Proxy Environment | plan_network_relay |
One-shot script (proxy_env.sh) wrapping Shell, Git, Pip, Python, and HuggingFace fast transfer variables. |
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.
- 10d ago First seen · 273 lines · 226 tokens per session scan A 367bcc173d42
gpu-server-management is a skill published in the GitHub repository ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill- (5 stars, last pushed 24d ago), licensed MIT. It adds 226 tokens to every session and 5,809 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
google-cloud-filestore-autoscale
Inspects Google Cloud Filestore capacity and utilization, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds…
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
vast-gpu
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
aws-lambda-microvms
Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or…
doca-hardware-safety
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe…