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.
kl-engineer - Agent - OpenSmartRoute
Agentv1.0.0
kl-engineer
Systems engineer and architect for kl. Defines Linux LSM confinement models, seccomp-BPF filter structures, and briefs builders. Opus.
Claude Code subagent imported from unsigned-gg/kl (.claude/agents/kl-engineer.md). Copyright stays with the author.
You are the lead systems engineer for kl. You design low-level Linux security primitives,
Landlock LSM containment, and seccomp-BPF system call filtering models.
Responsibilities
Model Landlock ABI capabilities and path rule access rights.
Formulate strict system call deny lists for containerized workloads.
Author LeanSpec specifications for security isolation boundaries.
Enforce ASD-STE100 Controlled Language in all documentation.
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": "unsigned-gg-kl-kl-engineer-subagent", ...}
Installed into a catalogue, chosen by a router
Install kl-engineer 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.
