Add Node SDK

What it does

When your agent uses it

• The user wants to:
• Call the Temps platform API from Node.js (deployments
• Use Temps KV (key-value) storage
• Use Temps Blob storage for files

Example prompts

• “temps node sdk”
• “temps kv”
• “temps blob”
• “/add-node-sdk”

Requirements

• Node.js
• A credential in TEMPS_API_KEY
• A credential in TEMPS_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Never hardcode keys/tokens — read from environment variables.
2. 2Check error on TempsClient calls before using data (hey-api result shape).
3. 3Catch KVError / BlobError around storage calls.
4. 4Initialize ErrorTracking.init() once at startup, before code that can throw.
5. 5Confirm method names from the generated .d.ts — the platform client surface is generated from OpenAPI and evolves with the API.

What it can do on your machine

Read from SKILL.md and the folder at commit 80aff9a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • TEMPS_TOKEN
  • TEMPS_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Add Node SDK loads about 2.2k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 522 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~130

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gotempsh/temps at commit 80aff9a, republished under its Apache-2.0 licence (© gotempsh). 522 words, ~2,213 tokens.

name

add-node-sdk

description

Integrate the Temps Node.js SDKs for server-side platform access, KV storage, and Blob storage. Use when the user wants to: (1) Call the Temps platform API from Node.js (deployments, projects, analytics, session replay, etc.), (2) Use Temps KV (key-value) storage, (3) Use Temps Blob storage for files, (4) Server-side integration with a Temps project, (5) Backend access to Temps resources. Triggers: "temps node sdk", "temps kv", "temps blob", "backend integration", "node.js temps", "@temps-sdk/node-sdk".

npm install @temps-sdk/node-sdk   # platform API + error tracking
npm install @temps-sdk/kv         # optional: KV storage
npm install @temps-sdk/blob       # optional: blob storage

import { TempsClient } from '@temps-sdk/node-sdk';

const temps = new TempsClient({
  baseUrl: process.env.TEMPS_API_URL!,   // e.g. https://app.temps.sh
  apiKey: process.env.TEMPS_API_KEY,     // create under Settings → API Keys
});

// Resource namespaces (each maps to OpenAPI operations):
// temps.projects, temps.deployments, temps.analytics, temps.sessionReplay,
// temps.domains, temps.dns, temps.backups, temps.crons, temps.email,
// temps.externalServices, temps.files, temps.funnels, temps.git, temps.monitoring,
// temps.notifications, temps.performance, temps.platform, temps.proxyLogs,
// temps.repositories, temps.settings, temps.users, temps.apiKeys, temps.auditLogs, …

const projects = await temps.projects /* .list(...) etc. */;

import { ErrorTracking } from '@temps-sdk/node-sdk';

ErrorTracking.init({
  dsn: process.env.SENTRY_DSN!,            // Temps DSN, from Error Tracking → DSN & Setup
  environment: process.env.NODE_ENV,
  release: process.env.GIT_SHA,
  tracesSampleRate: 1.0,
});

try {
  doRiskyThing();
} catch (err) {
  ErrorTracking.captureException(err);
}

ErrorTracking.captureMessage('Something notable happened', 'warning');
ErrorTracking.setUser({ id: 'user_123', email: 'user@example.com' });
ErrorTracking.addBreadcrumb({ category: 'auth', message: 'logged in', level: 'info' });
const tx = ErrorTracking.startTransaction({ name: 'checkout', op: 'http.server' });
// … tx.startChild(...), tx.finish()

import { kv } from '@temps-sdk/kv';
// or: import { KV, createClient } from '@temps-sdk/kv';

// Default instance reads TEMPS_API_URL, TEMPS_TOKEN, TEMPS_PROJECT_ID from env.
await kv.set('user:123', { name: 'John' });
await kv.set('session:abc', { userId: '123' }, { ex: 3600 });  // expire in 3600s
const user = await kv.get<{ name: string }>('user:123');        // typed get; null if missing
await kv.incr('counter');
await kv.expire('user:123', 600);
const ttl = await kv.ttl('user:123');                            // seconds; -2 missing, -1 no-expiry
const removed = await kv.del('user:123', 'session:abc');         // count deleted
const matches = await kv.keys('user:*');                         // pattern match

import { KV } from '@temps-sdk/kv';

const store = new KV({
  apiUrl: process.env.TEMPS_API_URL,
  token: process.env.TEMPS_TOKEN,    // API key or deployment token
  projectId: 42,                     // number; required with API keys, inferred from deployment tokens
});

import { blob } from '@temps-sdk/blob';
// or: import { BlobClient, createClient } from '@temps-sdk/blob';

// Upload (returns BlobInfo: { url, pathname, contentType, size, ... })
const info = await blob.put('avatars/user-123.png', imageBuffer, {
  contentType: 'image/png',
  addRandomSuffix: false,   // default true — set false to keep the exact pathname
});

// Download (returns a fetch Response — stream or buffer it yourself)
const res = await blob.download(info.url);
const bytes = Buffer.from(await res.arrayBuffer());

// Metadata
const meta = await blob.head(info.url);

// List with pagination
const { blobs, cursor, hasMore } = await blob.list({ prefix: 'avatars/', limit: 100 });

// Copy and delete
await blob.copy(info.url, 'avatars/backup.png');
await blob.del(info.url);            // also accepts string[] of urls/pathnames

import { BlobClient } from '@temps-sdk/blob';

const store = new BlobClient({
  apiUrl: process.env.TEMPS_API_URL,
  token: process.env.TEMPS_TOKEN,
  projectId: 42,
});

© gotempsh, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/add-node-sdk of gotempsh/temps.

Open the folder on GitHubat commit 80aff9a