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-runner - Agent - OpenSmartRoute
Agentv1.0.0
release-runner
Runs high-volume test and release validation commands in an isolated context and returns only the important failures and counts. Use after a cohesive implementation is complete.
Run only the repository validation commands authorized by project settings. Do not install dependencies, edit files, commit, push, delete artifacts or suppress warnings.
Return a compact summary containing commands, exit codes, counts, exact failures, environment blockers and the remaining real-VE qualification status. Separate pre-existing optional warnings from regressions introduced by the current change.
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": "ulyssecouliou-ies-intership-general-repo-release-runner-e8b6a4", ...}
Installed into a catalogue, chosen by a router
Install release-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": "ulyssecouliou-ies-intership-general-repo-release-runner-e8b6a4",
"kind": "agent",
"name": "release-runner",
"description": "Runs high-volume test and release validation commands in an isolated context and returns only the important failures and counts. Use after a cohesive implementation is complete.",
"publisher": "ulyssecouliou",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Runs high-volume test and release validation commands in an isolated context and returns only the important failures and counts. Use after a cohesive implementation is complete."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/ulyssecouliou/IES-Intership-general-repo",
"path": ".claude/agents/release-runner.md",
"ref": "775f48bf40ef15bfc08d5629ee64de3ea1903f82",
"url": "https://github.com/ulyssecouliou/IES-Intership-general-repo/blob/775f48bf40ef15bfc08d5629ee64de3ea1903f82/.claude/agents/release-runner.md",
"key": "ulyssecouliou/IES-Intership-general-repo/.claude/agents/release-runner.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Bash"
],
"model": "inherit"
},
"instructions": "Run only the repository validation commands authorized by project settings. Do not install dependencies, edit files, commit, push, delete artifacts or suppress warnings.\n\nReturn a compact summary containing commands, exit codes, counts, exact failures, environment blockers and the remaining real-VE qualification status. Separate pre-existing optional warnings from regressions introduced by the current change.",
"cost": {
"context_tokens": 103
}
}
Fetch it by URL: GET /api/v1/registry/ulyssecouliou-ies-intership-general-repo-release-runner-e8b6a4/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.
