Claude cost-saving workflow: Opus plans, Sonnet edits, Haiku reads, Fable reviews
dr_cintas · x · 2026-10-08
drcintas shares a multi-model Claude workflow built on one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points — stop spending Opus tokens on work that doesn't need it.
The roles:
- Opus 5.5 (high effort): owns the plan and reviews final code
- Sonnet 5.5 (medium effort): the worker — edits files, runs tests
- Haiku 5.5 (low effort): split into an explorer (searches/reads the codebase) and a researcher (pulls docs); the first Haiku with an effort setting
- Fable 5.1: set via /advisor fable; Opus calls it at decision points with the full transcript
Typical Fable call moments: before committing to a plan, when the same error recurs, and before marking a task done.
Context: Anthropic just shipped Haiku 5.5, which the company says costs 75% less to run than Haiku 4.5 and pairs well as a subagent for high-volume, cost-sensitive tasks.
More from coding & agent
- 10 open-source GitHub repos to cut your AI agent's token bill — victor_explore · 2026-10-08
- Dev Argues Coding Is Solved by AI, the Hard Part Is Coming Up with Novel Ideas — Suspicious_Fun_6338 · 2026-10-08
- Paper models LLMs as oracles in a pushdown automaton, unifying Agents and Workflows — China666 · 2026-10-08
- Naveen Rao: Let Agents Probe Every PowerPoint Feature, Then Rewrite the App — NaveenGRao · 2026-10-08
- Coding agents can build funnels but can't grasp why humans buy, marketer argues — boringmarketer · 2026-10-08
- AWS open-sources Strands Box, an OS-level sandbox for AI agents — TheNickWalsh · 2026-10-08