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.
bmad-automation - Prompt - OpenSmartRoute
Promptv1.0.0
bmad-automation
Use the shipped Compass automation layer when the user asks for:
Prompt file imported from Compass-Brand/forge-rag (.codex/prompts/bmad-automation.md). Copyright stays with the author.
BMAD Automation Prompt
Use the shipped Compass automation layer when the user asks for:
auto-plan
auto-epic-start
auto-story
auto-epic-end
approval-gated BMAD orchestration
Start with:
_bmad/tools/automation/README.md
_bmad/tools/automation/commands/
.codex/skills/bmad-automation/SKILL.md
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# BMAD Automation Prompt
Use the shipped Compass automation layer when the user asks for:
- `auto-plan`
- `auto-epic-start`
- `auto-story`
- `auto-epic-end`
- approval-gated BMAD orchestration
Start with:
1. `_bmad/tools/automation/README.md`2. `_bmad/tools/automation/commands/`3. `.codex/skills/bmad-automation/SKILL.md`
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
Installed into a catalogue, chosen by a router
Install bmad-automation 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.