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.
analysis - Prompt - OpenSmartRoute
Promptv1.0.0
analysis
Analyst mode — Analysis of one or more stories (max 4 related)
Prompt file imported from albegali/agentic-skeleton (.codex/prompts/analysis.md). Fill in {{arguments}} before use. Copyright stays with the author.
Recommended model: gpt-5-codex (tier balanced, see models.toml). Switch to it before running this command.
Follow workflow/steps/analysis.md with {IDS} = {{arguments}}.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->
> Recommended model: **gpt-5-codex** (tier `balanced`, see models.toml). Switch to it before running this command.
Follow `workflow/steps/analysis.md`with {IDS} = {{arguments}}.
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
{
"prompt": "<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->\n> Recommended model: **gpt-5-codex** (tier `balanced`, see models.toml). Switch to it before running this command.\n\nFollow `workflow/steps/analysis.md` with {IDS} = {{arguments}}.",
"variables": [
"arguments"
],
"notes": "Analyst mode — Analysis of one or more stories (max 4 related) Arguments: <ID…>.",
"metadata": {
"source": {
"provider": "github-codex-prompts",
"repository": "https://github.com/albegali/agentic-skeleton",
"path": ".codex/prompts/analysis.md",
"ref": "d00c402bcac1b76d5adf5557359d1bbdee22a54d",
"url": "https://github.com/albegali/agentic-skeleton/blob/d00c402bcac1b76d5adf5557359d1bbdee22a54d/.codex/prompts/analysis.md",
"key": "albegali/agentic-skeleton/.codex/prompts/analysis.md"
}
}
}
Installed into a catalogue, chosen by a router
Install analysis 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.