domains / families / agent-tooling / tokenwise

tokenwise

separate

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.

When to use

Cutting Claude Code token spend without sacrificing output quality
Validating whether Haiku/Sonnet is "good enough" for a specific task class before trusting auto-routing
Auditing where Opus tokens are actually being burned
Logging per-session cost data for finance or chargeback

When not to use

Token counts approximate to ±2% vs Anthropic billing
A/B test mode costs extra tokens (one task × N tiers) — intentional one-time validation
Anthropic-only by design (use LiteLLM or OpenRouter for cross-vendor)
Subagent `model:` param has known silent-fail bugs on some Claude Code builds — skill probes for this at install and refuses to configure if routing is broken

Source

Repository	Path
sickn33/agentic-awesome-skills	`skills/tokenwise/SKILL.md`