fleet-worker

Run a cheap headless Claude Code worker on a cheaper model and let an Opus orchestrator (this session) fan workers out in parallel, then verify and land their work. The worker keeps Claude Code's entire tool harness (Read/Write/Edit/Bash/Glob/Grep/Task/MCP/hooks) — only the brain is swapped to a cheaper model via env — a cheaper Anthropic model (Sonnet/Haiku) or a non-Anthropic endpoint. GLM-5.2 on z.ai is the default worked example; the mechanism is provider- and model-agnostic (any Anthropic-compatible endpoint).

This is the spawning layer. fleet-ops is the landing layer. fleet-worker produces branches cheaply; fleet-ops lands them through a test gate with your review. See references/fleet-ops-handoff.md.

The architecture crux: per-agent model = process isolation