Token Optimization Skill Leaderboard

A token optimization toolkit that uses a compressed, minimalist language style to reduce AI communication costs.

Formats AI output for ADHD users by leading with next actions, numbering multi-step tasks, and suppressing tangents.

A set of AI skills for software architects to conduct research, design codebase structures, and generate technical specifications via iterative review loops.

Reduces token usage across coding agent sessions through configurable rules for replies, artifacts, tests, code, context management, and delegation, with correctness guardrails.

Reads local Claude usage logs and applies a targeted subset of eleven rules to reduce token burn and avoid hitting plan limits.

Forces heavy token consumption for LLM backend stress testing, A/B testing, cost modeling, and autoscaling validation. Supports four computation loads from small to xlarge.

A token-cost routing skill that dispatches code implementation to a cheaper model while reserving the premium session for judgment, planning, specs, validation, and git operations.