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.
devlog-obsidian - Prompt - OpenSmartRoute
Promptv1.0.0
devlog-obsidian
DEPRECATED — use Codex skill .agents/skills/devlog-obsidian instead
Prompt file imported from musicofthings/devlog (.codex/prompts/devlog-obsidian.md). Copyright stays with the author.
Custom Codex prompts (/prompts:…) were removed in Codex CLI 0.117+.
Use the repo skill at .agents/skills/devlog-obsidian/SKILL.md (or ask Codex
to run the devlog-obsidian skill).
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
Custom Codex prompts (`/prompts:…`) were removed in Codex CLI 0.117+.
Use the repo skill at `.agents/skills/devlog-obsidian/SKILL.md` (or ask Codex
to run the `devlog-obsidian` skill).
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
{
"prompt": "Custom Codex prompts (`/prompts:…`) were removed in Codex CLI 0.117+.\nUse the repo skill at `.agents/skills/devlog-obsidian/SKILL.md` (or ask Codex\nto run the `devlog-obsidian` skill).",
"variables": [],
"notes": "DEPRECATED — use Codex skill .agents/skills/devlog-obsidian instead",
"metadata": {
"source": {
"provider": "github-codex-prompts",
"repository": "https://github.com/musicofthings/devlog",
"path": ".codex/prompts/devlog-obsidian.md",
"ref": "29771802a27a2b933e41764c9a999999c1808785",
"url": "https://github.com/musicofthings/devlog/blob/29771802a27a2b933e41764c9a999999c1808785/.codex/prompts/devlog-obsidian.md",
"key": "musicofthings/devlog/.codex/prompts/devlog-obsidian.md"
}
}
}
Installed into a catalogue, chosen by a router
Install devlog-obsidian 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.