monitor-ai-quality

monitor-ai-quality is a skill for Claude Code from amplitude/mcp-marketplace. It costs 84 tokens per session (2,041 once invoked), scanned A, original, MIT.

A monitoring guide for AI agents that use Amplitude Agent Analytics, Amplitude's data about agent sessions and behavior. It produces a health report covering quality, costs, speed, failures, and related measures.

In plain words
What is it for?
Use it to review agent health, investigate AI errors or performance, check language-model costs, and identify the sessions that need attention.
Why use it?
It helps find quality regressions, error spikes, unusual costs, and slower responses in one place. It requires Amplitude Agent Analytics to already be set up in the project.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the amplitude plugin — 37 skills shipped together

Good fit Use it to review agent health, investigate AI errors or performance, check language-model costs, and identify the sessions that need attention.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amplitude/mcp-marketplace/monitor-ai-quality
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add amplitude/mcp-marketplace --skill monitor-ai-quality
Clone the repo
git clone --depth 1 https://github.com/amplitude/mcp-marketplace

Made for: Claude Code.

Or install amplitude, the plugin that ships this one along with the rest of its 37 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for monitor-ai-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/monitor-ai-quality/github.svg)](https://agentmods.dev/skills/amplitude/mcp-marketplace/monitor-ai-quality)
Your own site
<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/monitor-ai-quality"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/monitor-ai-quality/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for monitor-ai-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/monitor-ai-quality"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/monitor-ai-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.02041
Opus 5 $0.00042 $0.01020
Sonnet 5 $0.00017 $0.00408
Haiku 4.5 $0.00008 $0.00204

Measured 12d ago against content hash 8d0a812612f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

monitor-ai-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/amplitude/skills/monitor-ai-quality/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Quality Monitor

You are a proactive AI operations advisor that delivers a concise, actionable health report on the user's AI agents. Your goal is to surface quality regressions, error spikes, cost anomalies, and performance degradations — then point to the specific sessions that need attention.

Instructions

Phase 1: Get Context and Schema

  1. Get context. Call Amplitude:get_amplitude_context to identify the user's projects and role.
  2. Get AI schema. Call Amplitude:get_amplitude_agent_analytics_info with view: "schema" to discover available agent names, tool names, topic models, and rubric definitions. This tells you what's in the data before you query it.
  3. Determine scope. If the user specifies an agent, time range, or focus area, narrow accordingly. Otherwise default to all agents over the last 7 days.

Phase 2: Gather the Full Picture

Run these in parallel — this is one batch of calls that gives you the complete health snapshot.

  1. Quality + cost + performance overview. Call Amplitude:get_amplitude_agent_analytics_info with view: "sessions", then aggregate quality, cost, latency, sentiment, failures, rubric scores, and error categories by agent from the returned sessions and evaluator results. This gives you the overall and per-agent health snapshot.

  2. Time series trends. Group the returned sessions locally by day and aggregate quality, volume, cost, success rate, sentiment, and latency. This gives you the trend lines to spot regressions and spikes.

  3. Recent failures. Call Amplitude:get_amplitude_agent_analytics_info with view: "sessions", filter to task failures, limit to 10, and order by newest session first. This gives you the most recent failed sessions for drill-down examples.

  4. Frustrated users. From the newest sessions, select up to 10 whose evaluator results show negative feedback or sentiment at or below 0.4. This surfaces sessions where users were unhappy.

Phase 3: Analyze and Triage

Read the full file on GitHub · 165 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 165 lines · 84 tokens per session scan A 8d0a812612f2

Subscribe to this mod's changes

monitor-ai-quality is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 2,041 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens