本文へスキップ
TakoAPI
スキル一覧に戻る

agentpulse

sru4ka 作

AI & LLMs
373ダウンロード数はclawskills.shが公開している値です
1閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

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

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

User asks: How much have I spent this week?

エージェント
  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

出力

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

要件

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

インストール

clawhub install sru4ka/agentpulse

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク