Skip to main content
Back to all repositories

Benchmark-calibrated per-subagent reasoning effort for Claude Code. Classify the subtask, dispatch the cheapest tier a blind grader still accepts. Pilot-proven: -64.7% tokens vs effort inheritance at equal quality.

31stars2forks0watchers/subscribers0issues
Language
Python
License
MIT License
Size
1.4 MB
Created
Jul 6, 2026
Last Updated
Aug 7, 2026
Last Pushed
Jul 10, 2026

Available Plugins

Loading plugins...

Evaluate before installing

  1. Review the source repository, recent maintenance, and license on GitHub.
  2. Read the marketplace manifest and plugin source files before running commands.
  3. Start with the smallest required permission set and validate behavior in a safe environment.