perf-optimization-loop
Measures first, proves performance wins, and locks them behind a CI budget.
Measures first, proves performance wins, and locks them behind a CI budget.
perf-optimization-loop refuses to edit code before a measured baseline exists. It isolates one experiment at a time, re-runs the same benchmark to decide KEEP, REVERT, or INCONCLUSIVE, records both wins and negatives, and generates a CI performance budget to catch regressions.
Resource types
Use cases
Platforms
Diagnose and repair Claude Desktop third-party model configuration gaps
Turn an existing website into a deployable conversational agentfront.
Audience
Public GitHub facts last synced Jul 10, 2026.
Turn a repository's structure into an editable, interactive architecture map.
Install coding guidance distilled from s4.codes videos as a Claude skill.