Results for “token-cost”
6 skillstokenwise
Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.
42.4k
ai-infra
Operates AI infrastructure as a production dependency: manages GPU utilization, MCP servers, LLM gateways, inference pipelines, token costs, semantic caching, and model observability.
2
aws
Executes AWS CLI commands with parallel execution, CloudWatch statistics syntax, Cost Explorer aggregation, and output token limits.
7
More results
audit-infra-cost
Read-only audit of hosting, database, storage, egress, and serverless spend (Supabase, Vercel, S3/R2, edge). Use when "hosting bill is high", "cut infra costs", or a bill jumps. CI minutes → audit-cicd. Model tokens → plan-llm-cost-guardrails. Consumes test-load numbers.
8
project-development
Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.
16.9k · bundle
03-performance
Optimizes Dify workflows and plugins by restructuring graphs, reducing LLM token usage, tuning worker pools, and improving parallel processing.
34 · bundle