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

flag-impact - Prompt - OpenSmartRoute

Promptv1.0.0

flag-impact

Name: flag-impact
Author: sanchiconnect-org

Produce the full cross-repo plan to rename or remove a feature flag without leaving anything dangling

by sanchiconnect-org(0) 0 installs

Free

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

See reviews

About

Prompt file imported from sanchiconnect-org/sc-saas-ai-native (.claude/commands/flag-impact.md). Fill in {{arguments}} before use. Copyright stays with the author.

Produce the safe cross-repo change plan for: {{arguments}}

Delegate to the flag-impact-planner subagent. Pass the flag and operation (rename <old> <new> or remove <flag>). Ask for: the full inventory of sites across all four repos, the deploy-safe ordering (repos ship independently), the per-repo change list, the tenant_users migration note, and the dangling-risk analysis. Report verbatim, then one line: is this change safe to stage as described?

Use it

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

Produce the safe cross-repo change plan for: {{arguments}}

Delegate to the `flag-impact-planner` subagent. Pass the flag and operation (`rename <old> <new>` or `remove <flag>`). Ask for: the full inventory of sites across all four repos, the deploy-safe ordering (repos ship independently), the per-repo change list, the `tenant_users` migration note, and the dangling-risk analysis. Report verbatim, then one line: is this change safe to stage as described?

Manifest

Installed into a catalogue, chosen by a router

Install flag-impact 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.

sanchiconnect-org-sc-saas-ai-native-flag-impact-command.prompt.jsonjson

{
  "prompt": "Produce the safe cross-repo change plan for: {{arguments}}\n\nDelegate to the `flag-impact-planner` subagent. Pass the flag and operation (`rename <old> <new>` or `remove <flag>`). Ask for: the full inventory of sites across all four repos, the deploy-safe ordering (repos ship independently), the per-repo change list, the `tenant_users` migration note, and the dangling-risk analysis. Report verbatim, then one line: is this change safe to stage as described?",
  "variables": [
    "arguments"
  ],
  "notes": "Produce the full cross-repo plan to rename or remove a feature flag without leaving anything dangling Arguments: <flag-name> rename <new-name> | <flag-name> remove.",
  "metadata": {
    "source": {
      "provider": "github-claude-commands",
      "repository": "https://github.com/sanchiconnect-org/sc-saas-ai-native",
      "path": ".claude/commands/flag-impact.md",
      "ref": "e6c589eafb291b7f5509a7e7067d526e5edc9ed1",
      "url": "https://github.com/sanchiconnect-org/sc-saas-ai-native/blob/e6c589eafb291b7f5509a7e7067d526e5edc9ed1/.claude/commands/flag-impact.md",
      "key": "sanchiconnect-org/sc-saas-ai-native/.claude/commands/flag-impact.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/sanchiconnect-org-sc-saas-ai-native-flag-impact-command/manifest?version=1.0.0

About

Use it

Manifest

Install flag-impact 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

Reviews