| name | model-router |
|---|
| description | Confirm-the-goal, "plan high, run low" routing for substantial tasks on any tier (scaled: premium delegates to Sonnet, Sonnet to Haiku, mechanical work to Haiku). Use at the start of multi-step analysis, report builds, data pulls, document generation, deck/doc assembly, automation runs, and when creating or editing a scheduled task. Step 0: before any action or delegation, restate the goal, deliverable, scope, assumptions, tiered plan and per-phase effort, and wait for a go (users can opt out). Then recommend effort per phase, delegate execution to cheaper tiers, and keep sessions short (~25-turn stop with a state handoff). Route silently: don't ask which model to use, except at the scheduled-task gate. Skip for pure conversation or trivial one-step asks. |
|---|
Model Router: confirm the goal, plan high, run low
Version 1.0 · Prices and benchmarks last verified 2026-10-13
Trigger: any substantial task, on any tier. Routing scales to the session's tier: a premium session (Fable or Opus) delegates to Sonnet by default, a Sonnet session delegates to Haiku, and mechanical work goes to Haiku from any tier. On Haiku, do not route; just work.
Requirements: full routing needs a harness that can spawn subagents with a per-call model choice (for example Claude Code, Cowork or the Claude Agent SDK). Without subagents, the understanding check, effort advice, session-length discipline and data-pull rules still apply; skip the delegation steps.
Standing acknowledgment: enabling this skill means the user opted in. Don't ask "should I switch models" or pause for permission to delegate. There are two stops: the understanding check (Step 0) and the scheduled-task gate. Everywhere else, route silently and report routing in one line at the end.
User overrides
The user's wording (preferences or request) wins over this skill.
| Default | Override phrase |
|---|
| Understanding check on substantial tasks | "skip the understanding check" / "just do it" |
| Session stop at ~25 assistant turns | "session stop at N turns" |
| Data pulls >~50 rows go to a subagent or file | "row limit N" |
| One-line routing summary at the end | "no routing line" |
Model registry (edit ONLY this table when models change)
Roles are permanent; model names are not. Prices verified 2026-10-13 against the Claude Platform pricing docs. Prices and benchmarks change with every release: check Anthropic's pricing and models pages before quoting them, and update this table first.
| Role | Current model | Agent model value | $/MTok in / out | Weight (output price, Haiku = 1x) | Reach for it when |
|---|
| Volume | Haiku 5.5 | haiku | $0.10 / $0.50 (prompts ≤100k); $0.50 / $2.50 above | 1x | Narrow, clear, repeated work: extraction, classification, tagging, summaries, compaction, database queries, fixed-template reads, simple browser/computer use |
| Everyday default | Sonnet 5.5 | sonnet | $2 / $10 | ~20x | Well-defined multi-step execution. Default for anything Haiku fails or is too risky for |
| Reasoning specialist | Opus 5.5 | opus | $4 / $20 | ~40x | Correctness-critical work, or the first run of an unproven recipe |
| Frontier judgment | Fable 5.1 | (never delegate to) | $10 / $50 | ~100x | Open-ended problems where the approach itself is unclear |