inspector

Evaluate and track AI Agent performance with tiered feedback and token budgets.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/hhx465453939/Claude_skill_pool --skill inspector
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: inspector
Source: https://github.com/hhx465453939/Claude_skill_pool/tree/main/skills.gemini/inspector
Command: npx skills add https://github.com/hhx465453939/Claude_skill_pool --skill inspector

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive system for evaluating, tracking, and guiding the performance of all AI Agents within a project, ensuring quality, efficiency, and continuous improvement.

Core Features & Use Cases

  • Multi-Agent Evaluation: Standardized scoring for all agents (programming, analysis, design, etc.).
  • Performance Tracking: Monitors quality, token efficiency, and prediction accuracy over time.
  • Feedback & Guidance: Provides tiered feedback from encouragement to critical warnings, with actionable recovery plans.
  • Resource Management: Dynamically adjusts token budgets and task priorities based on agent performance.
  • Use Case: Automatically assess an agent's code delivery, flag issues if it requires rework, and adjust its token budget for future tasks.

Quick Start

Evaluate the latest task completed by the Frontend Agent, noting its A-grade, 8/8 CHECKFIX pass, and 6.8k/8k token usage.

Frequently Asked Questions about inspector

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

FAQPage Schema
How do I evaluate and track AI agent performance across multiple tasks?

You can evaluate and track AI agent performance by implementing a global supervision system that provides standardized scoring, monitors token efficiency, and logs quality grades across programming, analysis, and design tasks.

What is the best way to manage token budgets for AI agents dynamically?

The best way to manage token budgets dynamically is to use a resource management system that adjusts task priorities and token allocations based on real-time agent performance tracking and historical efficiency data.

How does tiered feedback improve AI agent task delivery?

Tiered feedback improves AI agent delivery by providing actionable recovery plans and escalating guidance from encouragement to critical warnings, directly addressing specific quality issues flagged during the evaluation phase.

Can I integrate agent quality control with Gemini CLI workflows?

Yes, you can integrate agent quality control with Gemini CLI to trigger interactive queries and supervision workflows at various stages, including PLAN, DO, CHECK, and OPT, ensuring continuous performance tracking.

When do I need a global supervision system for AI agents?

You need a global supervision system when managing multiple AI agents that require standardized quality grading, token budget allocation, and consistent feedback to ensure efficiency and continuous improvement across diverse project tasks.