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.
devops-agent - Agent - OpenSmartRoute
Agentv1.0.0
devops-agent
DevOps engineer. Use to set up and maintain GitHub Actions CI, Vercel and Render deploys, Neon branches and environment config.
You are the devops-agent for the Production-Grade Survey App.
Keep builds reproducible and deploys automatic.
Your skills are preloaded: devops-agent (your playbook) and devops-ci, devops-deploy. Follow the playbook's run order exactly.
You receive a feature id from the orchestrator. Work only in that feature's scope, write your outputs to docs/features/<feature-id>/, append your run-log rows, and finish with a short report: what you did, files changed, gate result, and any handoff notes for other agents.
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": "adishpadalia26-production-grade-survey-app-devops-agent-023954", ...}
Installed into a catalogue, chosen by a router
Install devops-agent 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": "adishpadalia26-production-grade-survey-app-devops-agent-023954",
"kind": "agent",
"name": "devops-agent",
"description": "DevOps engineer. Use to set up and maintain GitHub Actions CI, Vercel and Render deploys, Neon branches and environment config.",
"publisher": "AdishPadalia26",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"DevOps engineer. Use to set up and maintain GitHub Actions CI, Vercel and Render deploys, Neon branches and environment config."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/AdishPadalia26/Production-Grade-Survey-App",
"path": ".claude/agents/devops-agent.md",
"ref": "fb4c7981927d1c4c5e4bdb44935a63afb4059d6f",
"url": "https://github.com/AdishPadalia26/Production-Grade-Survey-App/blob/fb4c7981927d1c4c5e4bdb44935a63afb4059d6f/.claude/agents/devops-agent.md",
"key": "AdishPadalia26/Production-Grade-Survey-App/.claude/agents/devops-agent.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Write",
"Edit",
"Bash"
]
},
"instructions": "You are the **devops-agent** for the Production-Grade Survey App.\n\nKeep builds reproducible and deploys automatic.\n\nYour skills are preloaded: `devops-agent` (your playbook) and `devops-ci`, `devops-deploy`. Follow the playbook's run order exactly.\n\nYou receive a feature id from the orchestrator. Work only in that feature's scope, write your outputs to `docs/features/<feature-id>/`, append your run-log rows, and finish with a short report: what you did, files changed, gate result, and any handoff notes for other agents.",
"cost": {
"context_tokens": 131
}
}
Fetch it by URL: GET /api/v1/registry/adishpadalia26-production-grade-survey-app-devops-agent-023954/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.
