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.
Prompt file imported from gokulnpc/tether-hackathon (.claude/commands/check-score.md). Copyright stays with the author.
/check-score
Fetch the current leaderboard from Supabase using leaderboard_snapshots for a specific arena_id.
Return:
participant
rank
score
snapshot time
If no snapshots exist, say the leaderboard has not been populated yet.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
/check-score
Fetch the current leaderboard from Supabase using `leaderboard_snapshots`for a specific `arena_id`.
Return:
- participant
- rank
- score
- snapshot time
If no snapshots exist, say the leaderboard has not been populated yet.
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
{
"prompt": "/check-score\n\nFetch the current leaderboard from Supabase using `leaderboard_snapshots` for a specific `arena_id`.\n\nReturn:\n- participant\n- rank\n- score\n- snapshot time\n\nIf no snapshots exist, say the leaderboard has not been populated yet.",
"variables": [],
"notes": "/check-score Tools: supabase/, frontend/src/app/api/.",
"metadata": {
"source": {
"provider": "github-claude-commands",
"repository": "https://github.com/gokulnpc/tether-hackathon",
"path": ".claude/commands/check-score.md",
"ref": "ed49fb524fdf6c00843a35377d481c5adcb43079",
"url": "https://github.com/gokulnpc/tether-hackathon/blob/ed49fb524fdf6c00843a35377d481c5adcb43079/.claude/commands/check-score.md",
"key": "gokulnpc/tether-hackathon/.claude/commands/check-score.md"
}
}
}
Installed into a catalogue, chosen by a router
Install check-score 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.