Communitygithub.com

itó-compute

查询实时 GPU 库存、提交已认证的 Itô 固定费率 RFQ、检查 RFQ 或采购状态、吊销设备凭证,并通过单独安装的规范 CLI 运行显式门控的节点认证。当用户要求查找 H100/H200 容量、请求固定计算费率、检查 Itô 计算状态、验证 GPU 节点、吊销 Itô 访问权限、或租用/购买 GPU 计算并需要了解支持边界时使用。

itó-compute 是什么?

Itô Compute 技能是一个基于规范 CLI 的接口,用于与 Itô 计算市场交互。它支持查询实时 GPU 库存(H100/H200)、提交固定费率 RFQ、检查 RFQ 和采购订单状态、以及吊销设备凭证。该技能不实现并行客户端、本地模拟、预留、工作负载运行器或推理服务器;也不执行任何浏览器自动化。用户必须通过 `ecc ito login` 完成设备授权流程,该流程支持基于 macOS Keychain 的设备令牌持久化。关键约束包括:提交 RFQ 前必须获得明确的买方授权,且 `count == nodes * gpus-per-node`,不允许自动推导拓扑。该技能还可通过 `ecc ito evals` 配合单独安装的 `sixty-two-cli` 进行实时的 GPU 节点认证。它主要适用于 Cursor、Claude Code、Codex 等 AI 代理平台,通过 CLI 或 MCP 服务器提供有限的操作集(auth、find、status、accept)。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/ito-compute

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Itô Compute

使用规范的 Itô 计算 CLI 或 MCP 服务器。ECC 不实现并行客户端、本地模拟、预留、工作负载运行器或推理服务器。ECC 本身不执行任何浏览器自动化。

安装本地规范包

ito-compute-cli 目前未发布。请从其规范仓库构建,而不是使用 npx、npm exec 或未经验证的包:

git clone https://github.com/Ito-Markets/ito-cloud-runtime.git
cd ito-cloud-runtime/cli/ito-compute-cli
npm ci
npm run check

将 ECC_ITO_CLI_EXECUTABLE 设置为构建后的显式绝对入口:

/absolute/path/to/ito-cloud-runtime/cli/ito-compute-cli/dist/bin/ito.js

ECC 永远不会通过 PATH 发现此承载凭据的客户端。ecc ito login 执行设备授权,并且永远不会继承 ITO_API_KEY。仅用于验证的 auth、以及 find 和 status 会在配置时直接转发 ITO_API_KEY;不需要 ITO_AUTH_MODE=legacy。切勿将密钥或令牌放入参数、跟踪文件、MCP 结果、日志或聊天中。

CLI 工作流程

  1. 在首次操作之前运行 ecc ito login。ECC 将此委托给规范 CLI 的设备授权,该授权默认会打开 Itô 验证页面,并在 macOS Keychain 中持久化设备令牌。使用 ecc ito login --no-browser 可抑制页面跳转。ECC 本身不执行浏览器自动化。如果发起代理无法完成已登录的浏览器步骤,请将确切的命令交给用户;审批完成后,返回原始任务并继续使用 ecc ito auth。设备令牌默认使用 macOS Keychain。文件令牌回退是显式的,其目录和令牌文件必须保持仅所有者可访问(0700 和 0600)。

  2. 运行 ecc ito auth 以验证现有凭据;它从不启动登录,并且拒绝 --no-browser。

  3. 在 ecc ito find 之前,获得明确的买方授权以提交 RFQ。

    • 需要 gpu、count、整数 days、max-rate、nodes、gpus-per-node、storage-tb、start-window、form-factor、contract-type、fabric、region 以及 split-fill 决策。
    • 需要 count == nodes * gpus-per-node;切勿推导拓扑。
    • 仅当买方明确接受任意 fabric 或 region 时使用 any。
    • 省略的 --allow-split 表示 false。
  4. 运行实时 RFQ 命令:

    ecc ito find \
      --gpu h200 \
      --count 8 \
      --nodes 1 \
      --gpus-per-node 8 \
      --days 30 \
      --storage-tb 1 \
      --start-window 2099-08-15 \
      --max-rate 3.00 \
      --form-factor bare_metal \
      --contract-type reservation \
      --fabric infiniband \
      --region us-east-1
    
  5. 运行 ecc ito status 以检查 RFQ 和采购订单。在出现模棱两可的传输失败后,在重复 find 之前先检查状态。

  6. 当报价准备好且买方明确批准时,接受它:

    ecc ito accept rfq_<ticket-id>
    

    这会将工单路由给人工审核的 desk。它不会移动资金或预留容量。未经明确买方授权,请勿接受。

  7. 当用户明确要求吊销此设备时,运行 ecc ito logout。当远程吊销失败时,规范 CLI 会保留本地凭据以便操作员重试;切勿手动删除令牌作为替代。

库存价格仅供参考。RFQ 并非预留容量。仅当规范结果包含非空的 firm quote 时,才将费率视为固定。

实时节点认证

ecc ito evals 将规范 CLI 的窄实时适配器暴露给单独安装的 sixtytwo-cli==0.3.33。它不通过 ECC 暴露本地 fixture 执行。 在调用它之前需要满足以下所有条件:

  • 操作员授权联系指定节点;
  • ITO_ENABLE_SIXTYTWO_LIVE=1;
  • --live-sixtytwo;
  • 一个显式的节点列表;以及
  • 一个包含 sixtytwo.yaml 的现有绝对配置目录。
ecc ito evals \
  --cluster clu_prod_example \
  --live-sixtytwo \
  --nodes gpu-01,gpu-02 \
  --config-dir /absolute/path/to/qualification-config

规范适配器只能对显式节点运行固定版本检查和 sixtytwo test --full。它不能租赁、启动、恢复、修复、重置、购买或订购资源。ECC 不会将 ITO_API_KEY 或模型/云凭据转发到节点认证。

MCP 工作流程

构建规范包,然后使用绝对路径配置 stdio 服务器:

{
  "mcpServers": {
    "ito-compute": {
      "command": "node",
      "args": [
        "/absolute/path/to/ito-cloud-runtime/cli/ito-compute-cli/dist/bin/ito-mcp.js"
      ]
    }
  }
}

服务器仅暴露:

  • ito_auth
  • ito_find
  • ito_status
  • ito_accept

ito_auth 验证现有凭据;它不启动设备登录。使用 ito_auth,收集明确的买方授权和所有硬约束,调用 ito_find,然后在需要时轮询 ito_status。当报价准备好且买方明确批准时,使用工单 ID 调用 ito_accept。Desk 报价通常仅供参考且无约束力,直到 desk 确认;结果中包含 quote_class。

租赁或购买语义

find 提交 RFQ 并可能返回 firm quote,但它不会租赁、购买、预留、配置或移动资金。accept 将报价路由到 desk 进行人工审核;它不移动资金或预留容量。status 是只读的,尽管提供商端点可能协调现有采购订单。ECC 帮助中的被动仪表板链接是单独的用户操作 Web 路由;不要将其打开或操作用作缺失 CLI 功能的替代方案。

不支持的操作

支持的客户端表面无法锁定报价、预留容量、执行工作负载或提供推理服务。accept 是一个 desk 交接,而不是购买。MCP 服务器不暴露认证功能;请使用上面显式的 CLI 命令。不要发明额外的工具或购买路径。当本地 CLI 缺失或实时操作失败时,不要使用浏览器或 fixture 替代。报告缺失的功能并停止。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

相关技能