Track your Claude Code ROI from the terminal
If you’re vibe coding with Claude Code, measure what ships to production.
Run this: npx claude-roi
See what made it to git vs what just burned tokens.
Cost per commit. Orphaned sessions. Line survival. And many more insights.
Most of us are optimizing prompts. Very few of us are optimizing ROI.
All local. Open source. GitHub: https://github.com/Akshat2634/Codelens-AI Open source — PRs, feature requests, and welcome.
Track your AI ROI Now!
3 comments
The "very few of us are optimizing ROI" point is sharp. The vibe coding discourse is dominated by "what can I build" conversations, but almost no one is asking "what actually shipped and created value?"
ROI with AI-assisted coding is tricky because gains are front-loaded (generation is fast) while costs are deferred (maintenance, debugging, security issues surface later). Measuring tokens vs. commits is a start, but the real signal is: does the generated code survive contact with production?
This connects to the first principle of the Agile Vibe Coding Manifesto (https://agilevibecoding.org): "Acceleration in development must translate into validated customer value. Speed without value is waste." ROI tracking is how you actually operationalize that.
The line survival metric matrixgard mentions (30-40% for non-trivial code) is fascinating and sobering. Would love to see this broken down by task type.
ROI with AI-assisted coding is tricky because gains are front-loaded (generation is fast) while costs are deferred (maintenance, debugging, security issues surface later). Measuring tokens vs. commits is a start, but the real signal is: does the generated code survive contact with production?
This connects to the first principle of the Agile Vibe Coding Manifesto (https://agilevibecoding.org): "Acceleration in development must translate into validated customer value. Speed without value is waste." ROI tracking is how you actually operationalize that.
The line survival metric matrixgard mentions (30-40% for non-trivial code) is fascinating and sobering. Would love to see this broken down by task type.
The survival rate metric is the one I find most telling — how much of what Claude wrote actually made it past code review unchanged. In practice it hovers around 30-40% for anything non-trivial, which reframes the whole cost calculation.
Have you noticed patterns in which types of tasks have the highest token burn but lowest line survival? Curious if it's test generation or refactoring that kills the ratio most.
Have you noticed patterns in which types of tasks have the highest token burn but lowest line survival? Curious if it's test generation or refactoring that kills the ratio most.