gspdev-benchmark

What problem does it solve?

GSP token consumption can silently grow, leading to rate‑limit risks and degraded performance. This Skill records token‑budget snapshots, compares them between releases or PRs, and highlights regressions, enabling data‑driven optimization.

Core Features & Use Cases

• Capture snapshots of the current token budget, optionally labeling them for later reference.
• Release baseline creation to serve as the official reference for a given version.
• Compare any two snapshots (defaulting to the latest release baseline) and surface changes in weight, red‑zone skills, and rate‑limit risk.
• Trend analysis across all stored snapshots to show overall trajectory and identify persistently high‑cost skills.
• Action suggestions based on analysis, guiding developers to address red‑zone items or unexpected exec_context growth.

Quick Start

Run the gspdev-benchmark skill with no arguments to capture a snapshot and automatically compare it to the latest release baseline.