# Use the top model to plan and review, and cheaper models to write

My top model writes specs and reviews, while cheaper models do the typing.

By Ki Moon · 2026-07-20 · technique · current
Canonical: https://kihmoon.com/bench-notes/p/planner-never-types/

**Symptom:** A top-model session hits its context or usage limit after a few prompts spent reading raw tool output.

The most capable model is the one I run out of first. In an interactive session it also carries the most fixed overhead, because it re-reads the instructions, tool schemas and the whole conversation every turn.

So my top-tier session only plans, writes specs, dispatches, reviews and integrates. The bulk runs in disposable contexts on cheaper models:

- A pinned-Opus builder drafts against a written spec.
- A research agent does the sourcing.
- A Haiku checker runs pass/fail checks with read-only tools.

The spec keeps the cheaper model safe. It carries locked decisions, the files to read, the deliverables and a return contract. The builder flags any deviation instead of redesigning.

A vague spec moves the design work onto the cheaper model.

As the Claude Code subagent documentation lays out, sub-agents inherit the session's model unless the call, the agent's own definition or the CLAUDE_CODE_SUBAGENT_MODEL variable sets one. With none of them set, the saving disappears with no error.

On an early build of a scoring rubric done this way, the draft needed two small integration fixes, and more than 200k tokens of drafting, research and testing stayed off the top model.

## Check your setup (read-only)

Take the 3 longest of your last 10 top-model sessions by turn count. Count the tool calls that returned raw data in each transcript. Count the calls that returned a sub-agent's conclusion. If raw-data calls outnumber conclusions, the top model is doing the work instead of planning it.

**Passes if:** In each sampled session's transcript, calls that returned conclusions equal or outnumber calls that returned raw data.

**Access needed:** agent-transcripts

## If it fails (changes to make later, not part of the check)

1. Keep the top model on intent, specs, review and integration.
2. Write the spec before dispatching, including locked decisions, files to read, deliverables and a return contract.
3. Set a default sub-agent model in config with the CLAUDE_CODE_SUBAGENT_MODEL variable. Pass a model explicitly where it differs from the default. Do not let a sub-agent inherit the top model.
4. Send an investigation to a sub-agent when the raw output would cost more than the sub-agent's start-up cost. Have the sub-agent return conclusions, not raw output.
5. Keep work of 2 tool calls or fewer, single-file edits and judgment-dense integration in the main session.

**Applies if:** Your top-model session transcripts list a tool that spawns sub-agents, and some sessions reach their context or usage limit.

**Skip if:** Your top-model session transcripts show fewer than 10 tool calls each.

Tags: agents, cost
