Workflow is a TypeScript SDK for building applications and AI agents whose work can continue reliably across steps and be observed while running. It is for developers creating durable workflows and orchestration logic for applications or agents. The catalogue add-ons provide workflows, rules, instructions, settings, commands, and agents for using the SDK.
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 vercel/workflow --skill migrating-to-workflow-sdkgit clone --depth 1 https://github.com/vercel/workflowWrote 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/vercel/workflow/migrating-to-workflow-sdk)<a href="https://agentmods.dev/skills/vercel/workflow/migrating-to-workflow-sdk"><img src="https://agentmods.dev/badge/skills/vercel/workflow/migrating-to-workflow-sdk/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/vercel/workflow/migrating-to-workflow-sdk"><img src="https://agentmods.dev/badge/skills/vercel/workflow/migrating-to-workflow-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00081 | $0.02062 |
| Opus 5.5 | $0.00032 | $0.00825 |
| Sonnet 5.5 | $0.00016 | $0.00412 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
migrating-to-workflow-sdk scanned grade A with 0 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 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrating to the Workflow SDK
Use this skill when converting an existing orchestration system to the Workflow SDK.
Intake
- Identify the source system:
- Temporal
- Inngest
- Trigger.dev
- AWS Step Functions
- Identify the target runtime:
- Managed hosting -> keep examples focused on
start(),getRun(), hooks/webhooks, and route handlers. - Self-hosted -> also read
references/runtime-targets.mdand explicitly say the workflow/step code can stay the same, but deployment still needs aWorldimplementation and startup bootstrap.
- Managed hosting -> keep examples focused on
- Extract the source constructs:
- entrypoint
- waits / timers
- external callbacks / approvals
- retries / failure handling
- child workflows / fan-out
- progress streaming
- external side effects
Default migration rules
- Put orchestration in
"use workflow"functions. - Put side effects, SDK calls, DB calls, HTTP calls, and stream I/O in
"use step"functions. - Use
sleep()only in workflow context. - For Signals,
step.waitForEvent(), and.waitForTaskToken, choose exactly one resume surface:resume/internal->createHook()+resumeHook()when the app resumes from server-side code with a deterministic business token.resume/url/default->createWebhook()when the external system needs a generated callback URL and the default202 Acceptedresponse is fine.resume/url/manual->createWebhook({ respondWith: 'manual' })only when the prompt explicitly requires a custom response body, status, or headers.- If a callback-URL prompt does not specify response semantics, default to
resume/url/defaultand make the assumption explicit in## Open Questions.
- Never pair
createWebhook()withresumeHook(), and never passtoken:tocreateWebhook(). - Wrap
start()andgetRun()inside"use step"functions for child runs. - Use
getStepMetadata().stepIdas the idempotency key for external writes. - Use
getWritable()in workflow context to obtain the stream, but interact with it (write, close) only inside"use step"functions. - Prefer rollback stacks for multi-step compensation.
- Choose app-boundary syntax in this order:
- If the prompt explicitly asks for framework-agnostic app-boundary code, use plain
Request/Responseeven when a framework like Hono is named. - Otherwise, if the target framework is named, shape app-boundary examples to that framework.
- Otherwise, keep examples framework-agnostic with
Request/Response. Do not default to Next.js-only route signatures unless Next.js is explicitly named.
- If the prompt explicitly asks for framework-agnostic app-boundary code, use plain
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/aws-task-token-parallel.md 1.3 KB
- evals/callback-url-default-response.md 835 B
- evals/inngest-timeout-streaming.md 1.1 KB
- evals/non-vercel-runtime-branch.md 1.1 KB
- evals/README.md 2.3 KB
- evals/temporal-signal-child-run.md 1.2 KB
- references/aws-step-functions.md 8.0 KB
- references/inngest.md 2.3 KB
- references/resume-routing.md 4.6 KB
- references/retries.md 4.4 KB
- references/runtime-targets.md 3.8 KB
- references/shared-patterns.md 9.9 KB
- references/temporal.md 2.8 KB
- references/trigger-dev.md 3.8 KB
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 · 178 lines · 81 tokens per session scan A c0cf6ea1e173
migrating-to-workflow-sdk is a skill published in the GitHub repository vercel/workflow (2,467 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 2,062 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…
trigger-realtime-and-frontend
Trigger.dev client/frontend surface: subscribe to runs in realtime (runs.subscribeToRun and the @trigger.dev/react-hooks hook useRealtimeRun), consume metadata and AI/text streams in React (useRealtimeStream), trigger tasks from the browser (useTaskTrigger, useRealtimeTaskTrigger), and mint scoped frontend credentials…
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.…
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 take streamText from the run argument rather than importing it from ai, returning a StreamTextResult vs calling chat.pipe(), the two server actions (chat.createStartSessionAction +…
trigger-cost-savings
Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when asked to reduce spend, optimize costs, audit usage, right-size machines, or review task efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP tools (listruns, getrundetails…
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…