Loading...
Loading...
Found 39 Skills
Track and report Claude Code token usage, spending, and budgets from a local cost-tracking database. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.
LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.
Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)
Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace
Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost
Read accumulated cost-tracking spend + budget config, compute utilization, emit 50/75/90/100% alert ladder
PM용 관리자 대시보드에 LLM 사용 모니터링 페이지를 자동 생성. Tokuin CLI 기반 토큰/비용/레이턴시 추적 + 사용자 랭킹 시스템 + 비사용자 추적 + 데이터 기반 PM 인사이트 자동 생성 + Cmd+K 글로벌 검색 + 사용자별 드릴다운 링크 탐색 포함. OpenAI/Anthropic/Gemini/OpenRouter 지원.
내부 AI 툴 필수 구현 가이드(P0/P1) 기반으로 권한, 비용, 로그, 보안 컴플라이언스를 설계-검증-개선하는 자동화 스킬. RBAC 설계, Gateway 원칙, Firestore 정책, 행동 로그, 비용 투명성, 기준검증 시스템의 전체 라이프사이클을 지원한다.
Use Agent Pulse to inspect AI agent activity, token usage, tool calls, model usage, cost, budgets, forecasts, reports, local log sources, health checks, and MCP tools. Use when the user asks to check how much AI agents have been used, what sessions ran, what models cost, whether spending is high, generate Agent Pulse reports, diagnose Agent Pulse setup, or expose Agent Pulse data to other agents.
AI-first application patterns, LLM testing, prompt management
Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.