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.
npx skills add travisjneuman/.claude --skill edge-computinggit clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/edge-computing)<a href="https://agentmods.dev/skills/travisjneuman/.claude/edge-computing"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/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.
<a href="https://agentmods.dev/skills/travisjneuman/.claude/edge-computing"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/edge-computing.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 | $0.00063 | $0.00806 |
| Opus 5.5 | $0.00025 | $0.00322 |
| Sonnet 5.5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
edge-computing 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 1mo 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: Request, env: Env): Promise<Response> { How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edge Computing
Platforms
| Platform | Runtime | Cold Start | Limits |
|---|---|---|---|
| Cloudflare Workers | V8 isolates | ~0ms | 128MB, 30s CPU |
| Deno Deploy | V8 isolates | ~0ms | 512MB, 50ms CPU |
| Vercel Edge Functions | V8 isolates | ~0ms | 128MB, 25s |
| AWS Lambda@Edge | Node.js | ~100ms | 128MB, 5s (viewer) |
| Bun | JavaScriptCore | N/A (server) | No hard limits |
Cloudflare Workers
export default {
async fetch(request: Request, env: Env): Promise<Response> {
const url = new URL(request.url);
// KV storage
const cached = await env.KV.get(url.pathname);
if (cached) return new Response(cached, { headers: { 'Cache-Control': 'max-age=60' } });
// D1 database
const { results } = await env.DB.prepare('SELECT * FROM users WHERE id = ?')
.bind(url.searchParams.get('id'))
.all();
// Durable Objects for state
const id = env.COUNTER.idFromName('global');
const obj = env.COUNTER.get(id);
const count = await obj.fetch(request);
return new Response(JSON.stringify(results));
}
};
Edge Databases
| Database | Type | Best For |
|---|---|---|
| Cloudflare D1 | SQLite | Workers-native, SQL at edge |
| Turso | libSQL (SQLite) | Multi-region replicas, embedded |
| Cloudflare KV | Key-value | Simple caching, config |
| Durable Objects | Stateful | Real-time, coordination, counters |
| Upstash Redis | Redis | Rate limiting, sessions at edge |
Deno Deploy
Deno.serve(async (req: Request) => {
const kv = await Deno.openKv();
const url = new URL(req.url);
if (req.method === "POST") {
const body = await req.json();
await kv.set(["items", crypto.randomUUID()], body);
return new Response("Created", { status: 201 });
}
const entries = kv.list({ prefix: ["items"] });
const items = [];
for await (const entry of entries) items.push(entry.value);
return Response.json(items);
});
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.
- 1mo ago First seen · 88 lines · 63 tokens per session scan A c48ce240991f
edge-computing is a skill published in the GitHub repository travisjneuman/.claude (105 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 806 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
dev-auth
Modern web auth implementation (better-auth, NextAuth/Auth.js, Clerk, Supabase Auth; migrating off the deprecated Lucia). Trigger when the user wants to add login, signup, sessions, OAuth, magic links, 2FA, or when existing auth code is detected to audit or migrate.
modal
Build serverless AI pipelines with Modal for cloud-based compute and inference.
langgraph-execution-path-routing-conditional
Guidelines and instructions for LangGraph execution path routing conditional.
appdeploy
Deploy web apps with backend APIs, database, and file storage. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.