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

gsd:fast - Prompt - OpenSmartRoute

Promptv1.0.0

gsd:fast

Name: gsd:fast
Author: strycker

Execute a trivial task inline — no subagents, no planning overhead

by strycker(0) 0 installs

Free

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

See reviews

About

Prompt file imported from strycker/barkeeper-bjorn-website (.claude/commands/gsd/fast.md). Copyright stays with the author.

This is NOT a replacement for /gsd-quick — use /gsd-quick for anything that needs research, multi-step planning, or verification. /gsd-fast is for tasks you could describe in one sentence and execute in under 2 minutes.

<execution_context> @/Users/glestryc/personal/github_repos/barkeeper-bjorn-website/.claude/get-shit-done/workflows/fast.md </execution_context>

Use it

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

<objective>
Execute a trivial task directly in the current context without spawning subagents
or generating PLAN.md files. For tasks too small to justify planning overhead:
typo fixes, config changes, small refactors, forgotten commits, simple additions.

This is NOT a replacement for /gsd-quick — use /gsd-quick for anything that
needs research, multi-step planning, or verification. /gsd-fast is for tasks
you could describe in one sentence and execute in under 2 minutes.
</objective>

<execution_context>
@/Users/glestryc/personal/github_repos/barkeeper-bjorn-website/.claude/get-shit-done/workflows/fast.md
</execution_context>

<process>
Execute the fast workflow from @/Users/glestryc/personal/github_repos/barkeeper-bjorn-website/.claude/get-shit-done/workflows/fast.md end-to-end.
</process>

Installed into a catalogue, chosen by a router

Install gsd:fast 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.

strycker-barkeeper-bjorn-website-fast-command.prompt.jsonjson

{
  "prompt": "<objective>\nExecute a trivial task directly in the current context without spawning subagents\nor generating PLAN.md files. For tasks too small to justify planning overhead:\ntypo fixes, config changes, small refactors, forgotten commits, simple additions.\n\nThis is NOT a replacement for /gsd-quick — use /gsd-quick for anything that\nneeds research, multi-step planning, or verification. /gsd-fast is for tasks\nyou could describe in one sentence and execute in under 2 minutes.\n</objective>\n\n<execution_context>\n@/Users/glestryc/personal/github_repos/barkeeper-bjorn-website/.claude/get-shit-done/workflows/fast.md\n</execution_context>\n\n<process>\nExecute the fast workflow from @/Users/glestryc/personal/github_repos/barkeeper-bjorn-website/.claude/get-shit-done/workflows/fast.md end-to-end.\n</process>",
  "variables": [],
  "notes": "Execute a trivial task inline — no subagents, no planning overhead Tools: Read, Write, Edit, Bash, Grep, Glob. Arguments: [task description].",
  "metadata": {
    "source": {
      "provider": "github-claude-commands",
      "repository": "https://github.com/strycker/barkeeper-bjorn-website",
      "path": ".claude/commands/gsd/fast.md",
      "ref": "7e5639c12dbe46b0fd61102023c71254044164ed",
      "url": "https://github.com/strycker/barkeeper-bjorn-website/blob/7e5639c12dbe46b0fd61102023c71254044164ed/.claude/commands/gsd/fast.md",
      "key": "strycker/barkeeper-bjorn-website/.claude/commands/gsd/fast.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/strycker-barkeeper-bjorn-website-fast-command/manifest?version=1.0.0

gsd:fast

About

Use it

Install gsd:fast 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