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.
Imported from Rycen7822/skill-retrieval-mcp (tests/fixtures/retrieval_quality/skills/software-development/external-agent-hermes-plugin-planning/SKILL.md). Install upstream with npx skills add Rycen7822/skill-retrieval-mcp --skill external-agent-hermes-plugin-planning. Copyright stays with the author.
External Agent Hermes Plugin Planning
When to Use
Use when the user wants a design plan for integrating an external autonomous agent or runtime into Hermes as a plugin, adapter, command, or skill surface.
Do Not Use When
Do not use when the user asks to build a generic MCP server, run Codex directly, or fix uv virtualenv state.
Inspect the external runtime interface and Hermes plugin requirements.
Define adapter boundaries, command routing, configuration, and risk controls.
Plan tests, documentation, and rollout strategy.
Produce an implementation roadmap without prematurely writing code.
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 - a plan picks it for its slotcurl-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}'
Installed into a catalogue, chosen by a router
Install external-agent-hermes-plugin-planning 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.
