I cut my Claude Code token usage significantly without losing output quality — what's your setup?

Hey everyone 👋

Like a lot of you, I use AI coding agents (Claude Code / Codex) daily, and token usage adds up fast — especially on large codebases where the agent burns context just orienting itself.

I contribute to OpenObserve (open-source observability platform, large Rust + Vue codebase), and here's what's actually moved the needle for me:

1. CLAUDE.md / AGENTS.md files — a short project map (architecture, conventions, key file paths) so the agent doesn't re-explore the repo every session. Biggest single win.

2. Scoped prompts over vague ones — "fix the null check in parseQuery() in src/utils/query.ts" costs a fraction of "the query parser is broken, fix it."

3. Fresh sessions per task — long conversations drag the entire history into every request. Clearing context between unrelated tasks cuts spend noticeably.

4. Plan first, execute second — asking for a plan in plain text, approving it, then executing beats letting the agent trial-and-error its way through with expensive tool calls.

5. Right-sizing the model — using cheaper/faster models for boilerplate and refactors, saving the big model for architecture and tricky debugging.

Questions for the community:

- What's the one technique that cut your token bill the most?

- Anyone found a good way to handle monorepos where even a "project map" file gets huge?

Curious what setups people have landed on — feels like everyone's solving this independently right now.