speckit-token-analyzer-baseline

Token analysis baselines for Spec Kit runs are captured by estimating input tokens, parsing CLI JSON metrics, and saving aggregated totals and quality scores into structured baseline files within your project's .specify directory.

Token analysis workflow measurement tracks token consumption and output quality scoring across multi-step Spec Kit commands like specify, plan, and tasks to evaluate and compare project cost and efficiency.

You measure and compare token costs by executing a named test scenario, aggregating CLI-reported token data into a run summary, and saving it as a reusable baseline for later comparison against other runs.

Yes, this token analyzer requires projects to use a .specify token analysis directory structure where it creates structured run folders and saves baseline files for repeatable comparisons.

Yes, you can score output quality for commands that produce artifacts; the skill summarizes these quality scores alongside aggregated token metrics in the final run summary.

The best way to establish repeatable token baselines for CLI metrics is to parse CLI JSON outputs, estimate token totals, apply quality scoring, and persist the completed run summary as a structured baseline file.