A command that runs a complete example workflow with OpenTelemetry tracing. OpenTelemetry records how work moves through an application, and Jaeger displays those records in a browser.

Use it to launch the demo workbench, open the workflow web interface, trigger the user-signup workflow, and view its traces in Jaeger.

It provides a repeatable way to start the example services, trigger the workflow, and inspect its execution and timing.

How vercel/workflow configures Claude Code

About the project

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.

vercel/workflow · 2,493 stars · on GitHub · workflow-sdk.dev

Reuse

Borrowing it

Nothing to install: this file belongs to vercel/workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/vercel/workflow/main/.claude/commands/demo.md

Clone the repo

git clone --depth 1 https://github.com/vercel/workflow

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/commands/vercel/workflow/demo/github.svg)](https://agentmods.dev/commands/vercel/workflow/demo)

Your own site

<a href="https://agentmods.dev/commands/vercel/workflow/demo"><img src="https://agentmods.dev/badge/commands/vercel/workflow/demo/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/commands/vercel/workflow/demo"><img src="https://agentmods.dev/badge/commands/vercel/workflow/demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 453 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00007	$0.00453
Opus 5.5	$0.00003	$0.00181
Sonnet 5.5	$0.00001	$0.00091
Haiku 4.5	$0.00001	$0.00045

Measured 2mo ago against content hash e013ca50ac44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

demo 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 2mo 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.

allowed-tools: Bash(curl:*), Bash(npx workflow:*), Bash(pnpm dev), Bash(docker *), Bash(open *)

.claude/commands/demo.md · 53 lines

What it actually says

Run the demo workflow with OpenTelemetry tracing enabled.

Steps

Start Jaeger for OTEL trace visualization (if not already running):

docker run -d --name jaeger-otel \
  -p 16686:16686 \
  -p 4317:4317 \
  -p 4318:4318 \
  jaegertracing/jaeger:2.4.0 2>&1 || docker start jaeger-otel

Open the Jaeger UI in the browser:
```
open http://localhost:16686
```

Start the workbench (default: nextjs-turbopack) with OTEL tracing enabled:

cd workbench/nextjs-turbopack
OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4318" \
OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf" \
pnpm dev

Also start the workflow web UI in a separate terminal (from the same workbench directory):

cd workbench/nextjs-turbopack
npx workflow web

Trigger the 7_full.ts workflow:

curl -X POST "http://localhost:3000/api/trigger?workflowFile=workflows/7_full.ts&workflowFn=handleUserSignup"

View traces in Jaeger UI at http://localhost:16686 - select service example-nextjs-workflow

Tracing Details

The traces include:

Step execution spans with workflow.queue.overhead_ms, step.attempt, step.status
Workflow orchestration spans with workflow.run.status, workflow.events.count
Queue message spans with messaging attributes

$ARGUMENTS can specify a different workbench (e.g., "example" or "nextjs-webpack").

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.

2mo ago First seen · 53 lines · 7 tokens per session scan A e013ca50ac44

Subscribe to this mod's changes

demo is a command published in the GitHub repository vercel/workflow (2,493 stars, last pushed today), licensed Apache-2.0. It adds 7 tokens to every session and 453 once invoked, about $0.0000 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 2026-08-30.

Analytics and metrics Orchestration ai-agents durable-execution serverless vercel workflow-engine

demo next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
demovercel/workflow	Command	2.5k	today	Apache-2.0	A	7	Claude Code
projectUntrivial-ai/agent-orchestrator	Command	14k	5d ago	Apache-2.0	A	0	Claude Code
sendUntrivial-ai/agent-orchestrator	Command	14k	5d ago	Apache-2.0	A	0	Claude Code
reclaim-knowledgefrankxai/Starlight-Intelligence-System	Command	10	yesterday	MIT	A	58	Claude Code
buildtractorjuice/arc-kit	Command	2.3k	2d ago	none	A	19	Claude Code
org-role-designfrankxai/Starlight-Intelligence-System	Command	10	yesterday	MIT	A	58	Claude Code
orchestrate-brainfrankxai/Starlight-Intelligence-System	Command	10	yesterday	MIT	A	49	Claude Code

workflow: Command for Claude Code