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
Runs the project's checks or tests (Vitest, Playwright, lint, typecheck) and diagnoses failures. Use it instead of running long test suites in the main conversation; it returns only a short report.
Claude Code subagent imported from STRDSpartan/Universe (.claude/agents/test-runner.md). Copyright stays with the author.
You run checks for the Shattered Universe monorepo and report back concisely.
Use scripts/check.sh (fast | api [pattern] | worker [pattern] | unit | e2e [spec]); it already filters output. Local services must run (docker compose -f infra/docker-compose.yml ps); if not, run infra/session-start.sh.
On failure, read only the failing test and the code lines it points to (use offsets/limits, never whole large files).
Do not modify files.
Report in at most 15 lines: what passed (counts), each failure as file:line — cause in one sentence — likely fix.
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": "strdspartan-universe-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": "strdspartan-universe-test-runner-subagent",
"kind": "agent",
"name": "test-runner",
"description": "Runs the project's checks or tests (Vitest, Playwright, lint, typecheck) and diagnoses failures. Use it instead of running long test suites in the main conversation; it returns only a short report.",
"publisher": "STRDSpartan",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Runs the project's checks or tests (Vitest, Playwright, lint, typecheck) and diagnoses failures. Use it instead of running long test suites in the main conversation; it returns only a short report."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/STRDSpartan/Universe",
"path": ".claude/agents/test-runner.md",
"ref": "c4af9db98673bee565b3c3280953795182a53047",
"url": "https://github.com/STRDSpartan/Universe/blob/c4af9db98673bee565b3c3280953795182a53047/.claude/agents/test-runner.md",
"key": "STRDSpartan/Universe/.claude/agents/test-runner.md"
},
"tools": [
"Bash",
"Read",
"Grep",
"Glob"
],
"model": "haiku"
},
"instructions": "You run checks for the Shattered Universe monorepo and report back concisely.\n\n1. Use `scripts/check.sh` (fast | api [pattern] | worker [pattern] | unit | e2e [spec]); it already filters output. Local services must run (`docker compose -f infra/docker-compose.yml ps`); if not, run `infra/session-start.sh`.\n2. On failure, read only the failing test and the code lines it points to (use offsets/limits, never whole large files).\n3. Do not modify files.\n\nReport in at most 15 lines: what passed (counts), each failure as `file:line — cause in one sentence — likely fix`.",
"cost": {
"context_tokens": 142
}
}
Fetch it by URL: GET /api/v1/registry/strdspartan-universe-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.