10 practical tips to save tokens in Claude Code, from session hygiene to model tiering
atullchaurasia · x · 2026-11-05
A practitioner's 10-point list for cutting token usage in Claude Code: one chat per task with fresh sessions on context switches; use Sonnet for simple edits and reserve Opus for complex work; maintain a CLAUDE.md with project structure, stack, conventions and build commands; request handoff summaries before ending sessions; point Claude at specific files instead of full-repo scans; avoid unrelated questions mid-session; disable unused tools and skills; keep changelog and architecture docs updated; ask for a detailed plan before implementing; and monitor which workflows burn the most tokens. Key lesson: more context doesn't always mean better results.
More from coding & agent
- Vector search finds resemblance, not proof: where Microsoft Fabric Graph fits — WirelessLife · 2026-11-05
- Databricks recipe: multi-tenant Genie isolation via OAuth custom identity claims + ABAC — Wise_Ear_4064 · 2026-11-05
- How do you teach AI agents company-specific jargon? Four glossary approaches, none great — ladybawss · 2026-11-05
- Garry Tan spends $200K/yr on a 23-skill Claude Code setup — benchmarks show elaborate harnesses can lose to vanilla — echen · 2026-11-05
- Teams experiment: cheap models for subagents, top model only on the primary agent — cramforce · 2026-11-05
- Mistral's Vibe CLI releases version 3.1 — qtnx_ · 2026-11-05