Notifications
Clear all
Topic starter
19/08/2026 3:53 pm
TL;DR: Cleaner code reduced agent cost and churn in a study of 540 Claude Code runs, with 7.2% fewer input tokens, 8.5% fewer output tokens, and 34% fewer file revisits, while task completion stayed essentially unchanged, according to Sonar. The finding reframes code quality as an AI infrastructure cost control, not just a developer experience issue.
NHIMG editorial — based on content published by Sonar: cleaner code lowers AI agent costs without improving task success
By the numbers:
- Across 540 runs, the cleaner side of each matched repository pair used 7.2% fewer input tokens and 8.5% fewer output tokens than the messier side.
- The study measured 34% fewer file revisits after the agent had already edited a file on cleaner codebases.
- Sonar reported 3.6% fewer turns before the first code change on cleaner repositories.
Questions worth separating out
Q: How should teams reduce AI coding agent costs without slowing delivery?
A: Start with the code paths agents touch most often.
Q: Why does messy code increase the cost of AI-assisted development?
A: Messy code forces agents to read more, revisit earlier edits, and spend extra turns rebuilding context before they can safely change anything.
Q: What signals show that an AI coding workflow is operating inefficiently?
A: Look for high token usage, repeated file revisits, and a long delay before the first meaningful edit.
Practitioner guidance
- Measure agentic inference cost per task Track input tokens, output tokens, file revisits, and time to first edit for representative coding workflows so you can separate task success from runtime inefficiency.
- Prioritise refactoring in high-volume agent paths Focus on repositories and modules where AI agents repeatedly touch the same files, since those paths are most likely to amplify token burn and reviewer churn.
- Standardise code structure for machine readability Use smaller functions, clearer names, and predictable control flow in code that agents are likely to modify, because those traits reduce context recovery work.
What's in the full report
Sonar's full research covers the experimental setup and run-by-run measurements this post intentionally leaves for the source:
- Side-by-side repository design details showing how the clean and messy codebases were matched for architecture, dependencies, and test coverage
- The 27-task experiment design, including how each task was routed through the codebase and why that routing matters for interpreting results
- Per-task variance across the 540 runs, including where cleaner code helped most and where it slightly increased cost
- Methodology notes on how reasoning effort was approximated from the event stream and why that matters for interpreting token economics
👉 Read Sonar's analysis of how cleaner code affects AI agent cost and reasoning →
AI agent workloads and messy code: what changes for teams?
Explore further
19/08/2026 4:30 pm
Cleaner code is becoming a governance control for agentic engineering. Sonar’s findings show that structural quality affects how much an AI agent must read, revisit, and re-reason before it acts. That turns code maintainability into an operational control surface, not merely a developer experience concern. For programmes adopting AI-assisted development, the governance question is now whether code structure is legible enough for both humans and machines to review safely.
A question worth separating out:
Q: How do organisations decide whether code quality work is worth it for AI agents?
A: Compare refactoring effort with the amount of agent runtime it removes. If the same repositories are repeatedly driving extra reads, retries, and long edit cycles, structural cleanup can become a real operating-cost lever. The right decision framework is cost avoided per workflow, not code beauty in the abstract.
👉 Read our full editorial: Cleaner code lowers AI agent costs without improving task success
