How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

wf-review - Prompt - OpenSmartRoute

Promptv1.0.0

wf-review

Name: wf-review
Author: zingspark

Run method-neutral, evidence-first wf-review via the wf-review skill

by zingspark(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Prompt file imported from zingspark/create-harness-vibe-coding (.claude/commands/wf-review.md). Copyright stays with the author.

/wf-review

This is a workflow command, not a direct command. Do not execute it as a static help or script command.

Load CLAUDE.md, Harness/MEMORY.md (index only per Memory Preflight), then Harness/README.md.
Preserve cache-first order per Harness/specs/runtime/context-loading.md#Cache-First Context Contract.
Follow .claude/skills/wf-review/SKILL.md (mirror: .agents/skills/wf-review/SKILL.md) for risk-based independent review, targeted challenge, and evidence adjudication.
The skill owns the review strategy; do not duplicate its process here.

If this runtime cannot invoke the skill directly, read .claude/skills/wf-review/SKILL.md and follow it in place.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# /wf-review

This is a **workflow command**, not a direct command. Do not execute it as a
static help or script command.

1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.
2. Preserve cache-first order per `Harness/specs/runtime/context-loading.md#Cache-First Context Contract`.
3. Follow `.claude/skills/wf-review/SKILL.md` (mirror: `.agents/skills/wf-review/SKILL.md`) for risk-based independent review, targeted challenge, and evidence adjudication.
4. The skill owns the review strategy; do not duplicate its process here.

If this runtime cannot invoke the skill directly, read
`.claude/skills/wf-review/SKILL.md` and follow it in place.

Installed into a catalogue, chosen by a router

Install wf-review and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.

zingspark-create-harness-vibe-coding-wf-review-command.prompt.jsonjson

{
  "prompt": "# /wf-review\n\nThis is a **workflow command**, not a direct command. Do not execute it as a\nstatic help or script command.\n\n1. Load `CLAUDE.md`, `Harness/MEMORY.md` (index only per Memory Preflight), then `Harness/README.md`.\n2. Preserve cache-first order per `Harness/specs/runtime/context-loading.md#Cache-First Context Contract`.\n3. Follow `.claude/skills/wf-review/SKILL.md` (mirror: `.agents/skills/wf-review/SKILL.md`) for risk-based independent review, targeted challenge, and evidence adjudication.\n4. The skill owns the review strategy; do not duplicate its process here.\n\nIf this runtime cannot invoke the skill directly, read\n`.claude/skills/wf-review/SKILL.md` and follow it in place.",
  "variables": [],
  "notes": "Run method-neutral, evidence-first wf-review via the wf-review skill",
  "metadata": {
    "source": {
      "provider": "github-claude-commands",
      "repository": "https://github.com/zingspark/create-harness-vibe-coding",
      "path": ".claude/commands/wf-review.md",
      "ref": "fcd3edb97aa3fba2600da36cbbf90a2f58a1f688",
      "url": "https://github.com/zingspark/create-harness-vibe-coding/blob/fcd3edb97aa3fba2600da36cbbf90a2f58a1f688/.claude/commands/wf-review.md",
      "key": "zingspark/create-harness-vibe-coding/.claude/commands/wf-review.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/zingspark-create-harness-vibe-coding-wf-review-command/manifest?version=1.0.0

About

/wf-review

Use it

Install wf-review and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews