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

create-github-issues-feature-from-implementation-plan - Prompt - OpenSmartRoute

Promptv1.0.0

create-github-issues-feature-from-implementation-plan

Name: create-github-issues-feature-from-implementation-plan
Author: KYLEPARK0514

Create GitHub Issues from implementation plan phases using feature_request.yml or chore_request.yml templates.

by KYLEPARK0514(0) 0 installs

Free

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

See reviews

About

Prompt file imported from KYLEPARK0514/Kaist-ai-agent-2026 (.github/prompts/create-github-issues-feature-from-implementation-plan.prompt.md). Fill in {{file}} before use. Copyright stays with the author.

Create GitHub Issue from Implementation Plan

Create GitHub Issues for the implementation plan at {{file}}.

Process

Analyze plan file to identify phases
Check existing issues using search_issues
Create new issue per phase using create_issue or update existing with update_issue
Use feature_request.yml or chore_request.yml templates (fallback to default)

Requirements

One issue per implementation phase
Clear, structured titles and descriptions
Include only changes required by the plan
Verify against existing issues before creation

Issue Content

Title: Phase name from implementation plan
Description: Phase details, requirements, and context
Labels: Appropriate for issue type (feature/chore)

Use it

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

# Create GitHub Issue from Implementation Plan

Create GitHub Issues for the implementation plan at `{{file}}`.

## Process

1. Analyze plan file to identify phases
2. Check existing issues using `search_issues`
3. Create new issue per phase using `create_issue` or update existing with `update_issue`
4. Use `feature_request.yml` or `chore_request.yml` templates (fallback to default)

## Requirements

- One issue per implementation phase
- Clear, structured titles and descriptions
- Include only changes required by the plan
- Verify against existing issues before creation

## Issue Content

- Title: Phase name from implementation plan
- Description: Phase details, requirements, and context
- Labels: Appropriate for issue type (feature/chore)

Installed into a catalogue, chosen by a router

Install create-github-issues-feature-from-implementation-plan 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.

kylepark0514-kaist-ai-agent-2026-create-github-issues-fe-774052.prompt.jsonjson

{
  "prompt": "# Create GitHub Issue from Implementation Plan\n\nCreate GitHub Issues for the implementation plan at `{{file}}`.\n\n## Process\n\n1. Analyze plan file to identify phases\n2. Check existing issues using `search_issues`\n3. Create new issue per phase using `create_issue` or update existing with `update_issue`\n4. Use `feature_request.yml` or `chore_request.yml` templates (fallback to default)\n\n## Requirements\n\n- One issue per implementation phase\n- Clear, structured titles and descriptions\n- Include only changes required by the plan\n- Verify against existing issues before creation\n\n## Issue Content\n\n- Title: Phase name from implementation plan\n- Description: Phase details, requirements, and context\n- Labels: Appropriate for issue type (feature/chore)",
  "variables": [
    "file"
  ],
  "notes": "Create GitHub Issues from implementation plan phases using feature_request.yml or chore_request.yml templates. Tools: search/codebase, search, github/*.",
  "metadata": {
    "source": {
      "provider": "github-prompts",
      "repository": "https://github.com/KYLEPARK0514/Kaist-ai-agent-2026",
      "path": ".github/prompts/create-github-issues-feature-from-implementation-plan.prompt.md",
      "ref": "e92986011ab64145610d89c0f473e880bfebb249",
      "url": "https://github.com/KYLEPARK0514/Kaist-ai-agent-2026/blob/e92986011ab64145610d89c0f473e880bfebb249/.github/prompts/create-github-issues-feature-from-implementation-plan.prompt.md",
      "key": "KYLEPARK0514/Kaist-ai-agent-2026/.github/prompts/create-github-issues-feature-from-implementation-plan.prompt.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/kylepark0514-kaist-ai-agent-2026-create-github-issues-fe-774052/manifest?version=1.0.0

About

Create GitHub Issue from Implementation Plan

Process

Requirements

Issue Content

Use it

Install create-github-issues-feature-from-implementation-plan 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