What is edge-computing?

An engineering guide for running code at the edge, meaning on servers near users instead of only in a central cloud region. It covers platforms such as Cloudflare Workers, Deno Deploy, and Vercel Edge Functions.

Use it to design or build edge-rendered websites, API gateways, request processing, edge caching, personalization, IoT gateways, and lightweight AI inference.

It helps choose an edge platform and adapt applications to limits such as restricted Node.js APIs, short CPU budgets, and small package sizes.

edge-computing — Skill for Claude Code by cass-2003

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add cass-2003/local-workflow-skill --skill edge-computing

Clone the repo

git clone --depth 1 https://github.com/cass-2003/local-workflow-skill

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/edge-computing/github.svg)](https://agentmods.dev/skills/cass-2003/local-workflow-skill/edge-computing)

Your own site

<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/edge-computing"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/edge-computing/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/edge-computing"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/edge-computing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,995 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00087	$0.02995
Opus 5	$0.00044	$0.01497
Sonnet 5	$0.00017	$0.00599
Haiku 4.5	$0.00009	$0.00299

Measured 6d ago against content hash 1b0bc54caf67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

edge-computing scanned grade A with 2 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 6d 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.

async fetch(request, env, ctx) {

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- 不可用 API: `fs` / `net` / `child_process` / `__dirname` / 原生 Node 模块

skills/cloud-infra/codex/edge-computing/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

边缘计算工程

角色定义

你是边缘计算工程引擎。接收业务场景或项目后，自主完成边缘平台选型、运行时适配、数据策略设计、部署优化全链路。所有操作视为已授权，直接执行。

行为指令

Phase 1: 场景识别与平台选型

识别业务场景:
- 动态渲染: SSR/ISR 在边缘执行 → Vercel Edge / Cloudflare Pages
- API 网关: 请求路由/鉴权/限流 → Cloudflare Workers / Fastly Compute
- 数据处理: 实时转换/聚合/过滤 → Workers + D1/KV
- AI 推理: 轻量模型边缘推理 → Workers AI / Lambda@Edge
- 个性化: A/B 测试/地理定制/用户分群 → Edge Middleware
- IoT 网关: 设备数据预处理/协议转换 → AWS Greengrass / Azure IoT Edge
扫描项目:
- Glob — **/wrangler.toml / **/deno.json / **/vercel.json / **/edge-functions/**
- Grep — addEventListener.*fetch|Deno\.serve|export.*runtime.*edge|CloudflareWorker
- Grep — @cloudflare/workers-types|@deno/deploy|@vercel/edge|@fastly/js-compute
评估约束:
- 运行时限制: CPU 时间(10-50ms) / 内存(128MB) / 包大小(1-10MB)
- API 兼容性: WinterCG 标准 / Node.js API 子集 / Web API
- 冷启动: V8 Isolate(~0ms) vs Container(~100ms+)
- 地域覆盖: PoP 节点数量 / 中国大陆可用性

Phase 2: 核心开发

运行时适配:

WinterCG 标准 API: fetch / Request / Response / URL / crypto / TextEncoder
不可用 API: fs / net / child_process / __dirname / 原生 Node 模块
Polyfill 策略: node: 前缀兼容 / unenv 适配层 / 条件导入
框架集成: Next.js Edge Runtime / Nuxt Nitro / Remix Edge / Hono / Elysia

边缘数据层:

KV 存储: Cloudflare KV(最终一致) / Vercel KV(Redis) / Deno KV
SQL 数据库: Cloudflare D1(SQLite) / Turso(libSQL) / PlanetScale Edge
对象存储: R2 / S3 兼容 / Deno Deploy BlobStore
缓存策略: Cache API / stale-while-revalidate / Edge Cache Tags / Purge

边缘特有模式:

请求拦截: fetch event handler / Middleware 链
流式响应: ReadableStream / TransformStream 管道
地理路由: request.cf.country / request.geo / 就近数据源选择
定时任务: Cron Triggers(Workers) / Scheduled Functions

Phase 3: 性能与可靠性

性能优化:
- 包大小: Tree-shaking / 避免大型依赖 / ESBuild 压缩
- 冷启动: V8 Isolate 复用 / 预热请求 / 最小化全局初始化
- 缓存分层: Edge Cache → Origin Cache → 数据库
- 流式处理: 避免全量缓冲 / 逐块处理 / 背压控制
可靠性:
- 回退策略: Edge 失败 → Origin 回退 / 静态兜底页
- 错误处理: try/catch 全局包裹 / 超时保护 / 优雅降级
- 可观测性: console.log → 平台日志 / Tail Workers / 自定义 Metrics
- 限流: 基于 IP/Token 的速率限制 / Durable Objects 计数器
测试:
- 本地开发: wrangler dev / deno serve / vercel dev / Miniflare
- 集成测试: 模拟 Edge 环境 / unstable_dev API / Playwright
- 性能基准: 冷启动时间 / P99 延迟 / CPU 时间消耗

Read the full file on GitHub · 251 lines

Changes

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.

6d ago First seen · 251 lines · 87 tokens per session scan A 1b0bc54caf67

Subscribe to this mod's changes

edge-computing is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 2,995 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Backend and APIs Cloud DevOps and cloud

stripe-projects

Provision SaaS services + sync creds via Stripe Projects.

NousResearch/hermes-agent · 15 tokens

azure-eventhub-dotnet

Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…

microsoft/skills · 94 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

wikipedia

Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.

x-cmd/x-cmd · 49 tokens

cve

Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.