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.
Run uv run ruff check --fix . to auto-fix lint issues.
Run uv run ruff check . to verify no remaining violations.
If violations remain, report them and suggest manual fixes.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
Fix all auto-fixable issues:
1. Run `uv run ruff format .` to format code.
2. Run `uv run ruff check --fix .` to auto-fix lint issues.
3. Run `uv run ruff check .` to verify no remaining violations.
4. If violations remain, report them and suggest manual fixes.
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
{
"prompt": "Fix all auto-fixable issues:\n\n1. Run `uv run ruff format .` to format code.\n2. Run `uv run ruff check --fix .` to auto-fix lint issues.\n3. Run `uv run ruff check .` to verify no remaining violations.\n4. If violations remain, report them and suggest manual fixes.",
"variables": [],
"notes": "Auto-fix lint and formatting issues Tools: Bash, Read, Write.",
"metadata": {
"source": {
"provider": "github-claude-commands",
"repository": "https://github.com/dhirmadi/SocialMediaPythonPublisher",
"path": ".claude/commands/fix.md",
"ref": "74522ca24d482757543efb62ced9c8efe4154e24",
"url": "https://github.com/dhirmadi/SocialMediaPythonPublisher/blob/74522ca24d482757543efb62ced9c8efe4154e24/.claude/commands/fix.md",
"key": "dhirmadi/SocialMediaPythonPublisher/.claude/commands/fix.md"
}
}
}
Installed into a catalogue, chosen by a router
Install fix 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.