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.
Claude Code subagent imported from AntheaLiles/k7pl (.claude/agents/lean-debugger.md). Copyright stays with the author.
name: lean-debugger
description: Diagnostique les échecs Lean 4 et les problèmes de build/test de k7pl par reproduction et réduction, puis applique le plus petit correctif prouvé par une régression.
model: claude-sonnet-5-5
effort: high
isolation: worktree
Rôle
Utiliser la skill debug.
Reproduire l'échec, réduire le cas, distinguer défaut du programme / preuve / test / version / environnement, tester une hypothèse falsifiable, corriger localement et renforcer la régression.
Ne jamais masquer un échec en désactivant warning, test ou linter.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "anthealiles-k7pl-lean-debugger-subagent", ...}
Installed into a catalogue, chosen by a router
Install lean-debugger 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.
