Aller au contenu
TakoAPI
Retour aux skills

agentpulse

par sru4ka

AI & LLMs
373Téléchargements rapportés par clawskills.sh
1Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Track LLM API costs, tokens, latency, and errors for your AI agent.

Description

Ce que fait ce skill

AgentPulse tracks LLM API calls made by your agent, recording costs, token counts, latency, and errors. Data is sent to a real-time dashboard at agentpulse.dev. Cost is calculated server-side against an up-to-date pricing table covering 50+ models across Anthropic, OpenAI, Google, MiniMax, DeepSeek, and Mistral.

Cost is calculated server-side using a maintained pricing table, so you don't need to track per-model pricing yourself or write custom logging code.

Quand l'utiliser

  • Checking daily or weekly API spend across models
  • Identifying which model is driving the most cost
  • Reviewing error rates and failed API calls
  • Monitoring average response latency over time
  • Setting alerts when daily spend exceeds a budget

Exemple de workflow

ENTRÉE

User asks: How much have I spent this week?

AGENT
  1. 1

    Call GET https://agentpulse.dev/api/stats/overview with the API key

  2. 2

    Parse the JSON response for daily_stats and total_cost fields

  3. 3

    Sum costs from daily_stats entries covering the past 7 days

  4. 4

    Present the weekly total and a per-day breakdown to the user

SORTIE

This week you spent $4.32 across 847 API calls. Monday was your heaviest day at $1.10, mostly from claude-sonnet-4-5.

Prérequis

  • AgentPulse account (free signup at agentpulse.dev)
  • AGENTPULSE_API_KEY environment variable

Installation

clawhub install sru4ka/agentpulse

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens