Spending the fewest dollars per completed task on model APIs: the anatomy of a pricing page (input, cached input, output all priced separately), model tiering and the cascade from cheap to strong, prompt-cache discounts and what a cache hit actually costs, batch discounts and the latency they buy, context-window economics where input tokens dominate, the spend ledger and attribution, and the written cost record. It treats dollars-per-task as the cost metric; it never recommends a provider and never quotes a price as current. Use when asking "token cost", "cost per million tokens", "why is my API bill so high", "model cascade", "cheaper model first", "prompt caching discount", "batch API discount", "output tokens cost more", "cost per task", "spend ledger", "token budget dollars". Not for packing more into each request (ac-single-request-value), not for the SDK mechanics of cache and batch endpoints (ac-llm-api-integration), not for cloud infrastructure unit economics (ac-cost-aware-engineering).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-token-cost-optimization .claude/skills/clawhub install anoscranel-ac-token-cost-optimizationCapabilities below are detected automatically by an open-source scanner that reads the skill's text and scripts (see how this is computed). Not measured means the scanner couldn't make a confident call — it is NOT a green check, and you should treat it as a possible red flag until a human or a stronger scanner has measured it.
analysis_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
External services this skill needs in order to work. The skill's behavior depends on these services being up, honest, and unchanged. Today we only show services we recognize from a curated list of ~50 well-known hosts (exchanges, RPC providers, data APIs); a complete dependency list — including every package, library, and binary the skill installs or imports — is on the roadmap.
anthropic.comopenai.comNo one has audited this skill yet. That is different from “audited and clean” — it just means no professional reviewer (a security firm, the CryptoSkill team, or a verified independent researcher) has signed off on it. There are no audit reports to read. How reviewer levels work →
SKILL.md → SOURCE.md → TRUST.auto.yaml → Browse directory →
Auto-generated by cryptoskill/extract-capabilities/0.3.1 · hosted-service list version 2026-09-06 · how this is computed