workflow-init

An initial setup guide for adding Vercel Workflow SDK to a JavaScript or TypeScript app before the package is installed. It identifies the app's framework and follows the official setup guide for it.

In plain words
What is it for?
Use it to start Workflow SDK in Next.js, Express, Hono, Fastify, NestJS, Nitro, Nuxt, Astro, SvelteKit, or Vite projects.
Why use it?
It removes the guesswork of choosing the right setup instructions when the workflow package is not yet in the project. It also checks whether the package is already installed before starting.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vercel/workflow/workflow-init
Any agent
npx skills add vercel/workflow --skill workflow-init
Clone the repo
git clone --depth 1 https://github.com/vercel/workflow

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.00869
Opus 5 $0.00039 $0.00434
Sonnet 5 $0.00016 $0.00174
Haiku 4.5 $0.00008 $0.00087

Measured yesterday against content hash c2c9c94090d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-init 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 yesterday.

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.

- Trigger the example endpoint with the provided `curl`.
skills/workflow-init/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

workflow-init

Initial setup of Vercel Workflow SDK before workflow is installed. Fetch the official getting-started guide for the user's framework.

Decision flow

0) Sanity check

Read package.json. If workflow is already a dependency, tell the user to use /workflow instead (it reads versioned docs from node_modules/workflow/docs/). Only continue if workflow is missing.

1) Determine the framework

Non-interactive: If the user named a framework in their prompt, use it directly.

Auto-detect: Inspect package.json deps and config files. Use the first match:

  1. Next.js - next dep or next.config.*
  2. Nuxt - nuxt dep or nuxt.config.*
  3. SvelteKit - @sveltejs/kit dep or svelte.config.*
  4. Astro - astro dep or astro.config.*
  5. NestJS - @nestjs/core dep or nest-cli.json
  6. Nitro - nitro dep or nitro.config.*
  7. Express - express dep
  8. Fastify - fastify dep
  9. Hono - hono dep
  10. Vite - vite dep (and not matched above)

If no match or multiple matches, ask the user to pick.

2) Fetch and follow the getting-started guide

Fetch exactly one of these URLs and follow the guide step-by-step:

Framework URL
Next.js https://workflow-sdk.dev/docs/getting-started/next
Express https://workflow-sdk.dev/docs/getting-started/express
Hono https://workflow-sdk.dev/docs/getting-started/hono
Fastify https://workflow-sdk.dev/docs/getting-started/fastify
NestJS https://workflow-sdk.dev/docs/getting-started/nestjs
Nitro https://workflow-sdk.dev/docs/getting-started/nitro
Nuxt https://workflow-sdk.dev/docs/getting-started/nuxt
Astro https://workflow-sdk.dev/docs/getting-started/astro
SvelteKit https://workflow-sdk.dev/docs/getting-started/sveltekit
Vite https://workflow-sdk.dev/docs/getting-started/vite

Each guide covers: install deps, configure framework, create first workflow, create route handler, run + verify.

Read the full file on GitHub · 75 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.

  1. yesterday First seen · 75 lines · 78 tokens per session scan A c2c9c94090d8

Subscribe to this mod's changes

workflow-init is a skill published in the GitHub repository vercel/workflow (2,363 stars, last pushed 3d ago), licensed Apache-2.0. It adds 78 tokens to every session and 869 once invoked, about $0.0004 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

drizzle

Use this skill when writing or modifying Drizzle ORM schemas, queries, or migrations in this repo — specifically the @internal/dashboard-agent-db package (the dashboard agent's conversation datastore). Covers pg-core schema definition, the postgres-js driver, drizzle-kit migrations, and this repo's conventions: a…

triggerdotdev/trigger.dev · 0 tokens

trigger-getting-started

Bootstrap Trigger.dev into an existing project from scratch: authenticate the CLI, install @trigger.dev/sdk and @trigger.dev/build, write trigger.config.ts with the project ref and task dirs, scaffold a /trigger directory with a first task, wire tsconfig and .gitignore, set TRIGGERSECRETKEY, and run the dev server.…

triggerdotdev/trigger.dev · 142 tokens

trigger-dev-tasks

Use this skill when writing, designing, or optimizing Trigger.dev background tasks and workflows. This includes creating reliable async tasks, implementing AI workflows, setting up scheduled jobs, structuring complex task hierarchies with subtasks, configuring build extensions for tools like ffmpeg or…

triggerdotdev/trigger.dev · 73 tokens

span-timeline-events

Use when adding, modifying, or debugging OTel span timeline events in the trace view. Covers event structure, ClickHouse storage constraints, rendering in SpanTimeline component, admin visibility, and the step-by-step process for adding new events.

triggerdotdev/trigger.dev · 52 tokens

trigger-authoring-chat-agent

Author and run a durable AI chat agent with chat.agent from @trigger.dev/sdk/ai: the per-turn run loop, why you MUST spread ...chat.toStreamTextOptions() first, returning a StreamTextResult vs calling chat.pipe(), the two server actions (chat.createStartSessionAction + auth.createPublicToken), and wiring useChat to…

triggerdotdev/trigger.dev · 129 tokens

trigger-chat-agent-advanced

Advanced and operational chat.agent capabilities for Trigger.dev, loaded on demand. Load this when working on the raw Sessions primitive (sessions / SessionHandle), a custom chat transport or the realtime wire protocol, durable sub-agents (AgentChat, chat.stream.writer), human-in-the-loop, steering, actions…

triggerdotdev/trigger.dev · 154 tokens