A tiered approach to token budgeting when developing with agent swarms
doodlestein · x · 2026-09-16
doodlestein shares how to think about token usage and project velocity when building with agent swarms: there's no simple formula — it depends on your project, methodology, budget, and urgency.
His core practice is tiered token tracking: frontier-tier tokens (Fable, Astra) at the top, then Sol/Opus, then cheaper tiers like Gemini 3.8 Flash, Grok 4.6, and GLM 5.3 Flash. The optimization target is total wall-clock time to ship working projects relative to total spend, not per-call cost.
More from coding & agent
- Three agents citing one shared note is one lineage, not three verifications: on agent provenance design — RileyRalmuto · 2026-09-16
- User resolves flight issue in 15 minutes with Muse AI agent — armand_ruiz · 2026-09-16
- Gary Bernhardt: code review cuts agent diffs to 25%, "coding is solved" is hype — mgill25 · 2026-09-16
- Hooking a local LLM to GIMP via MCP: a working llama.cpp setup — BrianScottGregory · 2026-09-16
- Skillry Launches a Marketplace of Design-Focused Skills for Coding Agents — yihui_indie · 2026-09-16
- AI vet Moyix cringes at how OpenAI's Astra describes him to its subagents — moyix · 2026-09-16