Cost Report
Skill AktivGenerate a cost report showing token usage and USD costs by agent and model
To provide users with clear insights into their AI agent spending, helping them understand costs per agent, model, and tier to manage budgets effectively.
Funktionen
- Generate token usage and USD cost reports
- Aggregate costs by agent, model, and tier
- Incorporate benchmark data for accurate cost breakdowns
- Check spending against configured budgets
- Provide a tier breakdown (Tier 1, 2, 3) of costs
Anwendungsfälle
- Understand how much each agent is costing
- Identify which models consume the most budget
- Track spending against defined budget thresholds
- Analyze Tier 1 cost eligibility and spending
Nicht-Ziele
- Real-time cost monitoring
- Predictive cost forecasting
- Automated budget optimization
- Billing users directly
Documentation
- info:Configuration & parameter referenceThe SKILL.md mentions an optional '--period' argument but does not explicitly document its format or default value, nor does it detail other potential parameters.
Portability
- warning:Structural AssumptionThe skill assumes the existence and specific location of 'docs/benchmarks/runs/latest.json' for Tier 1 cost data, which may break if the project structure changes or this file is absent.
Code Execution
- warning:ValidationThe skill accepts an optional '--period' argument but does not appear to validate its format or provide constraints, potentially leading to errors if an invalid value is supplied.
- warning:Error HandlingThe SKILL.md outlines steps but does not detail specific error handling for cases like the benchmark file not existing, invalid period formats, or tool failures, which could lead to opaque errors.
Errors
- warning:Actionable error messagesWhile the skill outlines its steps, it lacks explicit documentation on error handling for specific failure modes, such as missing benchmark files or invalid period arguments, potentially leading to unhelpful error messages.
Practical Utility
- warning:Edge casesThe SKILL.md describes the happy path but does not explicitly document failure modes or recovery steps for scenarios like a missing benchmark file or invalid period arguments.
Safety
- warning:Halt on unexpected stateThe SKILL.md does not explicitly state that the workflow will halt on unexpected pre-state conditions, such as a missing benchmark file, and document recovery steps.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-cost-tracker@rufloQualitätspunktzahl
Vertrauenssignale
Ähnliche Erweiterungen
Ops Revenue
100Revenue and costs tracker. AWS spend via aws ce, credits tracker, project revenue stages. Shows burn rate, runway estimate, credits expiring.
Usage Tracker
100Verfolgen und melden Sie die lokale Claude Code-Nutzung pro Anfrage: verbrauchte Tokens, geschätzte Kosten in €, Sitzungen, Projekte und Tool-Aufschlüsselung. Verwenden Sie, wenn der Benutzer nach Verbrauch, Guthaben, Nutzung, Kosten pro Anfrage fragt, einen Bericht sehen möchte, fragt, warum eine bestimmte Anfrage teuer war, vermutet, dass ein Prozess Tokens verbraucht, seine Claude Code-Nutzung optimieren möchte oder die Tool-Nutzung nach Anfrage prüfen möchte. Löst auch bei spanischen Sätzen aus: 'cuánto me está costando', 'cuántos tokens', 'consumo de hoy', 'qué petición fue cara', 'está consumiendo mucho', 'optimizar consumo', 'reporte de uso', 'ver uso', 'instalar tracker', 'hook no registra'. Befehle: /usage-tracker report [hoy|semana|mes|all] [proyecto], /usage-tracker top-requests [hoy|semana], /usage-tracker install, /usage-tracker status
Cost Budget Check
99Read accumulated cost-tracking spend + budget config, compute utilization, emit 50/75/90/100% alert ladder
Mcp Audit
99Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
Cost Summary
98Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate. JSON or markdown.
Cost Federation
98Consumer-side wiring for ADR-097 Phase 3 federation_spend events — per-peer rolling windows + suspension-threshold check