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.

Review - Prompt - OpenSmartRoute

Name: Review
Author: klintravis

Prompt file imported from klintravis/CopilotCustomizer (.github/prompts/Review.prompt.md). Fill in {{targetPath}}, {{focusArea}} before use. Copyright stays with the author.

Paired Instructions: RepoReview.instructions.md

Task Intent

Audit Copilot assets → generate analysis via templates/Analysis.template.md → save to output/.

Variable Block

Target Path [REQUIRED]: {{targetPath}} Focus Area [OPTIONAL]: {{focusArea}}

Output Requirements

Use templates/Analysis.template.md format:

Save to: output/<repo> - Repo Review - <date>.md
Include ready-to-run generator prompts for each asset type
Priority levels: High/Med/Low with concrete improvement examples

Workflow Phases

Phase 1: Discovery (Auto) — Inventory all assets in .github/ and root
Phase 2: Validation (Auto) — Schema compliance, cross-reference integrity, quality checks
Phase 3: Gap Analysis (Auto) — Compare against best practice checklist
Phase 4: Recommendation (Auto) — Generate prioritized improvement plan with ready-to-run prompts

Example Invocations

Full repository audit:

/Review targetPath: "/Users/dev/my-project"

Focus on agents only:

/Review targetPath: "/Users/dev/my-project", focusArea: "agents"

Security-focused review:

/Review targetPath: "/Users/dev/my-project", focusArea: "security"

Refinement Commands

Command	Action
`refine: enforce-output`	Validate output compliance
`refine: risks`	Expand risk analysis
`refine: concise`	Executive summary only

Generated using: RepoReview.instructions.md

VS Code Copilot Customization Framework v1.0

Install 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.

{ "prompt": "**Paired Instructions**: [RepoReview.instructions.md](../instructions/RepoReview.instructions.md)\n\n### Task Intent\nAudit Copilot assets → generate analysis via `templates/Analysis.template.md` → save to `output/`.\n\n### Variable Block\n---\n**Target Path** [REQUIRED]: {{targetPath}}\n**Focus Area** [OPTIONAL]: {{focusArea}}\n---\n\n### Output Requirements\nUse `templates/Analysis.template.md` format:\n- Save to: `output/<repo> - Repo Review - <date>.md`\n- Include ready-to-run generator prompts for each asset type\n- Priority levels: High/Med/Low with concrete improvement examples\n\n### Workflow Phases\n\n**Phase 1: Discovery** (Auto) — Inventory all assets in .github/ and root \n**Phase 2: Validation** (Auto) — Schema compliance, cross-reference integrity, quality checks \n**Phase 3: Gap Analysis** (Auto) — Compare against best practice checklist \n**Phase 4: Recommendation** (Auto) — Generate prioritized improvement plan with ready-to-run prompts\n\n### Example Invocations\n\n**Full repository audit**:\n```\n/Review targetPath: \"/Users/dev/my-project\"\n```\n\n**Focus on agents only**:\n```\n/Review targetPath: \"/Users/dev/my-project\", focusArea: \"agents\"\n```\n\n**Security-focused review**:\n```\n/Review targetPath: \"/Users/dev/my-project\", focusArea: \"security\"\n```\n\n### Refinement Commands\n| Command | Action |\n|---------|--------|\n| `refine: enforce-output` | Validate output compliance |\n| `refine: risks` | Expand risk analysis |\n| `refine: concise` | Executive summary only |\n\n**Generated using**: [RepoReview.instructions.md](../instructions/RepoReview.instructions.md)\n\n---\n\n*VS Code Copilot Customization Framework v1.0*", "variables": [ "targetPath", "focusArea" ], "notes": "Comprehensive Copilot customization asset audit with gap analysis and recommendations Tools: execute, read, edit, search, web, agent, todo. Arguments: Provide the path to the repository to review.", "metadata": { "source": { "provider": "github-prompts", "repository": "https://github.com/klintravis/CopilotCustomizer", "path": ".github/prompts/Review.prompt.md", "ref": "b2af066fbb4b2c8fa71b0596280eafc08b4b2268", "url": "https://github.com/klintravis/CopilotCustomizer/blob/b2af066fbb4b2c8fa71b0596280eafc08b4b2268/.github/prompts/Review.prompt.md", "key": "klintravis/CopilotCustomizer/.github/prompts/Review.prompt.md" } }, "model_hints": [ "Claude Sonnet 4.5 (copilot)" ] }

Review

About

Task Intent

Variable Block

Target Path [REQUIRED]: {{targetPath}} Focus Area [OPTIONAL]: {{focusArea}}

Output Requirements

Workflow Phases

Example Invocations

Refinement Commands

Install 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

Use it

Manifest

Reviews