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.
spec - Prompt - OpenSmartRoute
Promptv1.0.0
spec
Developer mode — update an existing Spec (e.g. after human review)
Prompt file imported from albegali/agentic-portal (.github/prompts/spec.prompt.md). Fill in {{args}} before use. Copyright stays with the author.
Arguments ( ): {{args}}
Developer mode. Arguments: the arguments above. Update only delivery/20-specs/SPEC-<ID>-*.md as requested, following delivery/templates/SPEC-template.md.
Do not touch the Brief, except for an Addendum if the intent changes. Chat: 3 lines with what changed.
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`. -->
Arguments (<ID> <requested changes>): {{args}}
Developer mode. Arguments: the arguments above. Update only `delivery/20-specs/SPEC-<ID>-*.md`as requested, following `delivery/templates/SPEC-template.md`.
Do not touch the Brief, exceptfor an Addendum if the intent changes. Chat: 3 lines with what changed.
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 spec 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": "<!-- Generated by tools/render_agents.py from workflow/workflow.toml and models.toml — do not edit; run `make agents`. -->\nArguments (<ID> <requested changes>): {{args}}\n\nDeveloper mode. Arguments: the arguments above. Update only `delivery/20-specs/SPEC-<ID>-*.md` as requested, following `delivery/templates/SPEC-template.md`.\nDo not touch the Brief, except for an Addendum if the intent changes. Chat: 3 lines with what changed.",
"variables": [
"args"
],
"notes": "Developer mode — update an existing Spec (e.g. after human review) Mode: agent.",
"metadata": {
"source": {
"provider": "github-prompts",
"repository": "https://github.com/albegali/agentic-portal",
"path": ".github/prompts/spec.prompt.md",
"ref": "7cb58d565ebbe7272f485eda67109ef281e73bdc",
"url": "https://github.com/albegali/agentic-portal/blob/7cb58d565ebbe7272f485eda67109ef281e73bdc/.github/prompts/spec.prompt.md",
"key": "albegali/agentic-portal/.github/prompts/spec.prompt.md"
}
},
"model_hints": [
"Claude Sonnet 5.5"
]
}
Fetch it by URL: GET /api/v1/registry/albegali-agentic-portal-spec-prompt/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.