contract-first

Route models by task complexity, track costs immutably, retry safely, and cache prompts to optimize LLM API spend.

Track Claude Code token usage, spending, and budgets from local metrics logs.

Convene four independent voices—Architect, Skeptic, Pragmatist, Critic—to surface structured disagreement on ambiguous decisions.

Agent skill from affaan-m/ecc.

C++ coding standards based on the C++ Core Guidelines for modern, safe, and idiomatic code.

Write, fix, and diagnose C++ tests with GoogleTest/GoogleMock and CMake/CTest.