Artem Yakimenko

Your spaghetti code has an invoice now: what complexity does to coding agents

We've told engineers for decades that high complexity makes code harder for humans to reason about. It turns out it makes code measurably more expensive for agents too. Unlike human frustration, this shows up directly on your API bill.

I show and discuss my research based around a series of controlled benchmarks on the same codebase with different levels of cyclomatic complexity, which shows that Claude Code uses up to 50% more tokens on the identical, simple feature requests, in a repeatable and controlled environment (i.e. 2 functionally identical branches, same codebase, caching disabled, same change sizes, etc.)

I'll walk through the benchmark design (and its limitations), the numbers, and what they imply for teams adopting agentic coding at scale: refactoring now has a directly quantifiable ROI, complexity linting belongs in your agent-readiness checklist alongside CLAUDE.md files and MCP servers, and "tech debt" arguments you've been losing with vibes can now be won with direct financial impact.

I expect people to leave the talk with a replicable methodology for benchmarking your own codebase, tools to measure complexity across a polyglot estate, and a budget-shaped argument for the refactor they've been putting off.