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/CLAUDE.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/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md)<a href="https://agentmods.dev/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md"><img src="https://agentmods.dev/badge/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md/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/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md"><img src="https://agentmods.dev/badge/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md.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 | $0.01868 | $0.01868 |
| Opus 5 | $0.00934 | $0.00934 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
GPU-Server-Management-MCP-Skill- CLAUDE.md 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 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.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - GPU Server Management MCP & Cluster Protocol
Target Platform: Cloudflare Workers + Cloudflare D1 Database + Streamable HTTP MCP (JSON-RPC 2.0)
Skill Name:gpu-server-management
Server Name:gpu-mcp-server-cf
🚀 Quick Development & Deployment Commands
# 进入 Worker 项目目录
cd gpu-mcp-server-cf
# 本地调试
npm run dev
# 编译类型检查
npx tsc --noEmit
# 部署到 Cloudflare Workers
npm run deploy # 或 npx wrangler deploy
# 应用 D1 数据库迁移 (远程生产库)
npx wrangler d1 migrations apply DB --remote
# 运行单元测试
npm test
🏛 系统架构与目录规范
gpu-mcp-server-cf/: Cloudflare Workers 后端核心源码src/index.ts: Hono 应用入口与路由分发 (/mcp,/api/*,/)src/mcp/: 18 个 MCP 工具的 schema 与执行处理器src/db/: D1 数据库 schema、SQL 迁移脚本与查询封装src/api/: REST API（服务器、代理池、NVIDIA NIM、排错知识库、状态探针）src/frontend/html.ts: 响应式 Web 控制台单文件前端（HTML/CSS/JS）
.agents/skills/gpu-server-management/: Agent 技能指令集与最佳实践
🛠 18 个核心 MCP 工具一览
| 分类 | 工具名称 | 作用 |
|---|---|---|
| 连接与生命周期 | get_servers |
获取可用节点列表、Base64 密钥、实时负载、预存数据集、倒计时、跳板机标识及避坑经验 (pitfalls) |
claim_server |
声明占用服务器，锁定任务并设定倒计时租期 (duration_minutes) |
|
release_server |
任务完成或异常退出后主动释放算力 | |
| 调度与智能备份 | plan_server_backup |
双模智能分流备份（充足期仅备产出 vs. 临期全量撤离），自动同步 MCP RAG 向量库 |
query_backup_index |
自然语言/指标关键词 RAG 检索历史备份记录（绑定 IP 生命周期） | |
plan_task_allocation |
多任务多维装箱调度（数据集亲和性 Dataset Affinity 享 +100,000 分置顶） |
|
register_dataset |
登记服务器已缓存的数据集路径与大小，写入集群集体记忆 | |
remove_dataset |
移除已删除或卸载的数据集元数据记录 | |
plan_disk_share |
磁盘不足时计算并生成 sshfs/nfs 跨机挂载指令 |
|
plan_network_relay |
生成直连 vs. 代理并发毫秒测速竞速脚本与 >500MB 分片聚合拉取命令 | |
refresh_load |
下发实时物理负载探测命令 (nvidia-smi, free, df) |
|
| 注册与集体记忆 | upsert_server |
注册/更新服务器（以 host 唯一去重），写回运维避坑笔记 (notes_entry) 与跳板机开关 |
update_server |
修改服务器字段（包含 is_jump_host、上下架状态等） |
|
remove_server |
永久移除服务器（级联清理该 IP 下关联的所有备份索引） | |
| 诊断与代理池 | verify_server_connectivity |
测试直连 SSH 与代理可达性 |
import_proxy_subscription |
一键导入 Clash/V2Ray 订阅链接，自动解析批量录入代理池 | |
list_proxies |
列出当前配置的所有 SOCKS5 / HTTP 代理节点 | |
add_proxy |
添加单个代理节点 | |
remove_proxy |
移除失效代理节点 |
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 · 120 lines · 1,868 tokens per session scan A e5a826191b01
GPU-Server-Management-MCP-Skill- CLAUDE.md is an instructions file published in the GitHub repository ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill- (5 stars, last pushed 24d ago), licensed MIT. It adds 1,868 tokens to every session, about $0.0093 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.