model-routerlisted

# model-router Scores a task, then hands it off to the matching subagent. Three tiers, one each — effort is fixed per tier, the model is whatever the project's profile resolves to. | Tier | `opus-centric` (default) | `frontier` | `lean` | | -------- | --------------------------------- | ------------------------------------- | -------------------------------------- | | Quick | `quick-executor` — sonnet/low | `quick-executor` — sonnet/low | `quick-executor` — sonnet/low | | Standard | `standard-worker` — opus/medium | `standard-worker-high` — opus/high | `standard-worker-high` — sonnet/high | | Deep | `deep-architect` — opus/high | `deep-architect` — fable/high | `deep-architect` — opus/high | | Verifier | `verifier` — sonnet/high | `verifier` — sonnet/high | `verifier-medium` — sonnet/medium | The **agent** varies by profile, not just the model: effort comes only from an agent file's frontmatter (the Agent tool has no effort parameter), so a profile pinning a tier at a different effort routes to a variant agent. Read both off `routing.agents[tier]` and `routing.models[tier]` — never assume the agent from the tier name. Two axes, scored separately, because they answer different questions: - **Capability** picks the tier, and therefore the model. Raise it when the model had the context, clearly tried, and still got it w