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.
agentlas-graph - Prompt - OpenSmartRoute
Promptv1.0.0
agentlas-graph
Build an Agentlas automation by describing it, list saved ones, or request a run.
Prompt file imported from agentlas-ai/Agentlas-OS (.claude/commands/agentlas-graph.md). Copyright stays with the author.
/agentlas-graph
Identical to /hep-graph and /agentlas graph <request>. Locate the file named hep-graph.md in the exact same directory this file was loaded from, read it, and follow its instructions exactly — treating everything typed after /agentlas-graph as that command's request.
Do not improvise a separate workflow and do not summarize hep-graph.md from memory; that file is the sole authority for this command's behavior.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# /agentlas-graph
Identical to `/hep-graph` and `/agentlas graph <request>`. Locate the file named `hep-graph.md`in the exact same directory this file was loaded from, read it, and follow its instructions exactly — treating everything typed after `/agentlas-graph`as that command's request.
Do not improvise a separate workflow and do not summarize `hep-graph.md`from memory; that file is the sole authority for this command's behavior.
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
Installed into a catalogue, chosen by a router
Install agentlas-graph 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.
{
"prompt": "# /agentlas-graph\n\nIdentical to `/hep-graph` and `/agentlas graph <request>`. Locate the file named `hep-graph.md` in the exact same directory this file was loaded from, read it, and follow its instructions exactly — treating everything typed after `/agentlas-graph` as that command's request.\n\nDo not improvise a separate workflow and do not summarize `hep-graph.md` from memory; that file is the sole authority for this command's behavior.",
"variables": [],
"notes": "Build an Agentlas automation by describing it, list saved ones, or request a run. Tools: Bash, Read. Arguments: [new <what you want> | list | show <name> | run <name>].",
"metadata": {
"source": {
"provider": "github-claude-commands",
"repository": "https://github.com/agentlas-ai/Agentlas-OS",
"path": ".claude/commands/agentlas-graph.md",
"ref": "c0acd99be22114569e20bca94bed4540ba046eb4",
"url": "https://github.com/agentlas-ai/Agentlas-OS/blob/c0acd99be22114569e20bca94bed4540ba046eb4/.claude/commands/agentlas-graph.md",
"key": "agentlas-ai/Agentlas-OS/.claude/commands/agentlas-graph.md"
}
}
}
Fetch it by URL: GET /api/v1/registry/agentlas-ai-agentlas-os-agentlas-graph-command/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.