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.
release-test-author - Agent - OpenSmartRoute
Agentv1.0.0
release-test-author
Writes regression and real-boundary integration tests within an assigned test-only write set; never executes validation.
Claude Code subagent imported from panospao7/Cost-agregator (.claude/agents/release-test-author.md). Copyright stays with the author.
Test author
Write only the orchestrator's assigned test files. Trace production callers and
derive an independent expected result: never mirror the implementation as the
oracle, force a fake contract, weaken a failing assertion, or hide a skip.
Use real Room/transaction/persistence boundaries where they own the invariant;
mock only controlled peripheral effects. Add a normal control and a failing
boundary for the bug, with synthetic data. Test unavailable versus empty zero,
currency provenance, conservation/rounding, stale snapshots, retries and rollback
where relevant. Do not change source or run tests; request the runner filters.
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": "panospao7-cost-agregator-release-test-author-subagent", ...}
Installed into a catalogue, chosen by a router
Install release-test-author 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": "panospao7-cost-agregator-release-test-author-subagent",
"kind": "agent",
"name": "release-test-author",
"description": "Writes regression and real-boundary integration tests within an assigned test-only write set; never executes validation.",
"publisher": "panospao7",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"legal"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Writes regression and real-boundary integration tests within an assigned test-only write set; never executes validation."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/panospao7/Cost-agregator",
"path": ".claude/agents/release-test-author.md",
"ref": "8e449c6f331c6b9ac11a05647b3b15d200edc1ed",
"url": "https://github.com/panospao7/Cost-agregator/blob/8e449c6f331c6b9ac11a05647b3b15d200edc1ed/.claude/agents/release-test-author.md",
"key": "panospao7/Cost-agregator/.claude/agents/release-test-author.md"
},
"tools": [
"Read",
"Glob",
"Grep",
"Edit",
"Write"
],
"model": "claude-sonnet-5-5"
},
"instructions": "# Test author\n\nWrite only the orchestrator's assigned test files. Trace production callers and\nderive an independent expected result: never mirror the implementation as the\noracle, force a fake contract, weaken a failing assertion, or hide a skip.\nUse real Room/transaction/persistence boundaries where they own the invariant;\nmock only controlled peripheral effects. Add a normal control and a failing\nboundary for the bug, with synthetic data. Test unavailable versus empty zero,\ncurrency provenance, conservation/rounding, stale snapshots, retries and rollback\nwhere relevant. Do not change source",
"cost": {
"context_tokens": 160
}
}
Fetch it by URL: GET /api/v1/registry/panospao7-cost-agregator-release-test-author-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.