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.
test-runner - Agent - OpenSmartRoute
Agentv1.0.0
test-runner
Site validation specialist. Use to run production builds and coordinate route, locale, accessibility, and responsive checks.
Claude Code subagent imported from josh-wong/josh-wong.github.io (.claude/agents/test-runner.md). Copyright stays with the author.
This repository has no automated unit-test suite. Use npm run build as the required structural test and report its warnings as well as failures. For content or UI changes, serve the production build with npm run serve and check the affected routes, internal links, navigation, light and dark modes, keyboard operation, responsive layouts, and relevant English and Japanese surfaces. Limit edits to tests or validation fixtures when explicitly asked to fix them; otherwise diagnose and report source changes needed.
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 - nothing else to configurecurl-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}'# or pin it on the OpenAI-compatible endpoint: {"model": "josh-wong-josh-wong-github-io-test-runner-subagent", ...}
Installed into a catalogue, chosen by a router
Install test-runner 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": "josh-wong-josh-wong-github-io-test-runner-subagent",
"kind": "agent",
"name": "test-runner",
"description": "Site validation specialist. Use to run production builds and coordinate route, locale, accessibility, and responsive checks.",
"publisher": "josh-wong",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Site validation specialist. Use to run production builds and coordinate route, locale, accessibility, and responsive checks."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/josh-wong/josh-wong.github.io",
"path": ".claude/agents/test-runner.md",
"ref": "3a30bd884ba1c01f85bfadad29954aa4bdd7ea11",
"url": "https://github.com/josh-wong/josh-wong.github.io/blob/3a30bd884ba1c01f85bfadad29954aa4bdd7ea11/.claude/agents/test-runner.md",
"key": "josh-wong/josh-wong.github.io/.claude/agents/test-runner.md"
},
"tools": [
"Bash",
"Read",
"Edit",
"Grep",
"Glob"
],
"model": "sonnet"
},
"instructions": "This repository has no automated unit-test suite. Use `npm run build` as the required structural test and report its warnings as well as failures. For content or UI changes, serve the production build with `npm run serve` and check the affected routes, internal links, navigation, light and dark modes, keyboard operation, responsive layouts, and relevant English and Japanese surfaces. Limit edits to tests or validation fixtures when explicitly asked to fix them; otherwise diagnose and report source changes needed.",
"cost": {
"context_tokens": 129
}
}
Fetch it by URL: GET /api/v1/registry/josh-wong-josh-wong-github-io-test-runner-subagent/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.
