skills.rest
TeamWiseFlow
TeamWiseFlowOFFICIAL
Explore all skills by this author →
GitHub

HRBP Skill — Usage Monitor (用量监控)

Aggregate OpenClaw session transcripts into call counts, token breakdowns, and estimated costs.

8.4k|1.4k|Updated Apr 24, 2024
Search Tags:#anomaly detection#agent usage#cost monitoring#token analytics#time range reporting#OpenClaw sessions#HRBP operations
One-click install
npx skills add https://github.com/TeamWiseFlow/wiseflow --skill hrbp-skill-usage-monitor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: HRBP Skill — Usage Monitor (用量监控)
Source: https://github.com/TeamWiseFlow/wiseflow/tree/main/crews/hrbp/skills/hrbp-usage
Command: npx skills add https://github.com/TeamWiseFlow/wiseflow --skill hrbp-skill-usage-monitor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, bash, fs, path, readline, JSON.parse, and includes scripts (resource) components.

What problem does it solve?

This Skill helps you understand which HRBP-related AI agents consume the most tokens and money, so you can monitor usage trends and spot anomalies.

Core Features & Use Cases

  • Agent usage reporting: Aggregates call counts, input/output tokens, cache read/write tokens, and total tokens from OpenClaw session logs.
  • Cost estimation: Extracts per-entry cost from usage fields based on pricing configuration in openclaw.json, showing a grand total and per-agent subtotals.
  • Time-range controls: Supports cumulative, daily (e.g., last 7/14 days), weekly, and monthly views to quickly answer questions like “this week’s spend”.
  • Actionable insights: Highlights agents with unexpectedly high usage, zero-token sessions, missing usage metrics, and error responses, and suggests configuration review when costs are high.

Quick Start

Ask the system to show your agent usage report for the last 7 days including tokens and costs.

Frequently Asked Questions about HRBP Skill — Usage Monitor (用量监控)

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor agent token usage and cost across OpenClaw sessions?▼

To monitor agent token usage and cost, this Skill aggregates OpenClaw session transcripts into call counts, token breakdowns, and estimated costs by scanning session logs and extracting pricing from openclaw.json.

Can I generate a daily or weekly agent usage report for anomaly detection?▼

Yes, you can generate agent usage reports for anomaly detection across cumulative, daily, weekly, or monthly time windows to quickly identify high usage, zero-token sessions, or error responses.

What is the best way to track per-agent token costs from session logs?▼

The best way to track per-agent token costs is by normalizing usage fields from session transcripts and extracting per-entry costs, providing a grand total and per-agent subtotals for operational review.

Does this usage monitor require any specific environment setup to read session files?▼

Yes, it requires a Node.js environment with access to the local file system to scan and parse ~/.openclaw/agents/*/sessions/*.jsonl files and optionally read openclaw.json for agent display names.

Why are some agent sessions showing missing usage metrics or zero tokens?▼

Missing usage metrics or zero-token sessions occur when session logs lack normalized usage fields; this Skill highlights these anomalies and suggests a configuration review when costs are unexpectedly high.

Related Skills

Explore More Data & Analytics Skills→
JiayueMeng128JiayueMeng128

session-logs

Search and analyze past conversation logs in JSONL format using jq and rg.

Community
Intermediate
DTMC-marketplaceDTMC-marketplace

token-budgeting

Estimate and optimize AI/ML costs by analyzing token usage and caching strategies.

Official
Advanced
dakshrawat298-gifdakshrawat298-gif

session-logs

Analyze session JSONL logs with jq and rg to extract costs, token usage, and tool interactions.

Community
Intermediate
ReefBytesReefBytes
1

dashboard

Visualize agent efficiency metrics from parallel run logs as markdown dashboards.

Community
Advanced