# A sub-agent has a fixed token cost, so small work is cheaper inline

In my setup each sub-agent paid 70 to 85k tokens before it did any work.

By Ki Moon · 2026-08-17 · finding · current
Canonical: https://kihmoon.com/bench-notes/p/delegation-fixed-cost/

**Symptom:** A fan-out of one sub-agent per small task costs far more tokens than the tasks' tool calls explain.

Each sub-agent starts by loading its base instructions, tool schemas and orientation. I measured that at about 70 to 85k tokens per agent, whatever the task size.

I had been dispatching one agent per file to republish pages, about two tool calls of real work each.

Batching 5 to 9 files per agent took a round from about 600 to 900k tokens to about 160 to 255k. Reliability held, because the return contract kept one result line per file.

If the repeat is deterministic, like a regex-safe edit across files, it shouldn't be an agent at all.

Resuming a finished agent is cheaper still, because it keeps its warm context and costs no new spawn.

That breaks down when files on disk have changed since the agent read them.

A drafter I resumed through two rounds of template and voice edits held the old versions in context and blended them with the new. Its output looked compliant while missing the edits, so the final run went to a fresh agent.

That resume-or-respawn call depends on knowing which files an agent read, so that list needs a record outside the orchestrator's head.

## Check your setup (read-only)

Take the most recent session that spawned 5 or more sub-agents for the same kind of task. List each sub-agent's total tokens beside the tool calls it made on the task itself. Any sub-agent with tens of thousands of tokens on 2 or 3 task calls should have been batched or scripted.

**Passes if:** No sub-agent in the sampled session spent tens of thousands of tokens on 2 or 3 task calls.

**Access needed:** agent-transcripts

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

1. Batch mechanical repeats 5 to 10 per agent, with one result line per unit in the return contract.
2. Script any repeat that is deterministic instead of dispatching an agent.
3. Resume a finished agent when the inputs are new and the files it read are unchanged.
4. Respawn a fresh agent once its contract files changed. Name the changed files for re-reading in the resume message when only 1 or 2 changed.

**Applies if:** Your transcripts show sessions that spawn several sub-agents for small repeated tasks, or reuse one agent across rounds.

**Skip if:** In your transcripts, each sub-agent makes dozens of task calls on its own distinct task.

Tags: agents, cost
