Token burn — same task
Workflow tool typically spawns 6–10 full-context agents with unconstrained outputs — several hundred thousand tokens before synthesis.
The effort dial scales fanout, agent caps, output caps, model tier, and circuit breaker settings together. Default: high.
Every run follows a canonical pipeline. Trivial tasks skip the pipeline entirely. The approved diagram is the run's contract.
Haiku scouts at ~1/3 Sonnet cost. 40–85% of total savings come almost entirely from this one choice.
No runtime, no daemon. A markdown playbook that makes the main Claude Code session the orchestrator.
Or clone manually:
Optional — enable Fable escalation: export ANTHROPIC_API_KEY=sk-ant-...
Hooked on Fable but not on its API bill? worktrickle buys its judgment by the decision (~$0.07), not by the session.
Without a key, worktrickle degrades gracefully and never proposes Fable.
Full docs and source: github.com/ez-gz/worktrickle