Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Every new feature or behaviour change includes tests, in the same PR: positive, negative
and edge cases.
Coverage target is 90% for lines, functions, branches and statements. Run
pnpm run test:coverage from the repo root to see the report.
Live services: tests that need a real model or API (Ollama, Anthropic, Azure, Firefly)
must skip cleanly when the service or key is unavailable. They're not part of the coverage
gate.
See testing-coverage.mdc for case shapes, test locations, thresholds and Vitest pitfalls.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install testing 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.
{
"ocm": "1",
"id": "executioncontrolprotocol-executioncontrolprotocol-testing-rule",
"kind": "skill",
"name": "testing",
"description": "Testing policy — every change ships with tests",
"publisher": "executioncontrolprotocol",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"math"
],
"tags": [
"skill-md",
"github-cursor-rules"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Testing policy — every change ships with tests"
],
"primary": false,
"metadata": {
"source": {
"provider": "github-cursor-rules",
"repository": "https://github.com/executioncontrolprotocol/executioncontrolprotocol",
"path": ".cursor/rules/testing.mdc",
"ref": "99d940f989e8b797a59068b95fd5ca3914878b7c",
"url": "https://github.com/executioncontrolprotocol/executioncontrolprotocol/blob/99d940f989e8b797a59068b95fd5ca3914878b7c/.cursor/rules/testing.mdc",
"key": "executioncontrolprotocol/executioncontrolprotocol/.cursor/rules/testing.mdc"
},
"applies_to": "**/*.test.ts,**/test/**/*.ts"
},
"instructions": "# Testing\n\n- **Every new feature or behaviour change includes tests**, in the same PR: positive, negative\n and edge cases.\n- **Coverage target is 90%** for lines, functions, branches and statements. Run\n `pnpm run test:coverage` from the repo root to see the report.\n- **Live services:** tests that need a real model or API (Ollama, Anthropic, Azure, Firefly)\n must skip cleanly when the service or key is unavailable. They're not part of the coverage\n gate.\n\nSee `testing-coverage.mdc` for case shapes, test locations, thresholds and Vitest pitfalls.",
"cost": {
"context_tokens": 138
}
}
Fetch it by URL: GET /api/v1/registry/executioncontrolprotocol-executioncontrolprotocol-testing-rule/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
