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.

fix - Prompt - OpenSmartRoute

Prompt file imported from faroukBakari/trader-pro (.github/prompts/fix.prompt.md). Fill in {{request}}, {{arguments}} before use. Copyright stays with the author.

Context

You are performing a quick, targeted fix. Effort tier: Quick.

Effort Calibration: Quick

This is a bounded correction — typo, small bug, rename, config tweak, or single-file fix. Builder should:

Skip heavy discovery and multi-step planning
Single implement invocation (1-3 files max)
Verify via type-check or quick test, not full suite
Minimal summary — no extensive completion report

Scope Signal

Target is clear and bounded
Acceptance criteria: "the fix works"
If this turns out bigger than expected → upgrade to standard effort

Key Rules

Ground changes in codebase evidence — read before editing
Read docs/DOCUMENTATION-GUIDE.md only if relevant to the fix domain
Use make targets — never raw npm, poetry, pip, or python commands
Follow existing code patterns and conventions

Skills

Apply these skills from .github/skills/: engineering-principles, fix-type-errors

{{request}} ## Context You are performing a **quick, targeted fix**. Effort tier: **Quick**. ### Effort Calibration: Quick This is a bounded correction — typo, small bug, rename, config tweak, or single-file fix. Builder should: - **Skip** heavy discovery and multi-step planning - **Single implement** invocation (1-3 files max) - **Verify** via type-check or quick test, not full suite - **Minimal summary** — no extensive completion report ### Scope Signal - Target is clear and bounded - Acceptance criteria: "the fix works" - If this turns out bigger than expected → upgrade to standard effort ### Key Rules - Ground changes in codebase evidence — read before editing - Read `docs/DOCUMENTATION-GUIDE.md` only if relevant to the fix domain - Use `make` targets — never raw `npm`, `poetry`, `pip`, or `python` commands - Follow existing code patterns and conventions ### Skills Apply these skills from `.github/skills/`: engineering-principles, fix-type-errors {{arguments}}

Install fix 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.

fix

About

Context

Effort Calibration: Quick

Scope Signal

Key Rules

Skills

Use it

Install fix 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