metrics-check

metrics-check is a skill for Claude Code from shaan-ad/pm-os. It costs 26 tokens per session (1,121 once invoked), scanned A, original, MIT.

A product-metrics review workflow for spotting trends and unusual changes in measures such as sign-ups, usage, or revenue.

In plain words
What is it for?
It is for reviewing historical or live product data, identifying anomalies, and recommending actions.
Why use it?
It helps connect metric movements to launches, experiments, decisions, and goals instead of viewing numbers in isolation.

Skill for Claude Code

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

Part of the pm-os plugin — 27 skills, 1 hook shipped together

Good fit It is for reviewing historical or live product data, identifying anomalies, and recommending actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shaan-ad/pm-os/metrics-check
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 shaan-ad/pm-os --skill metrics-check
Clone the repo
git clone --depth 1 https://github.com/shaan-ad/pm-os

Made for: Claude Code.

Or install pm-os, the plugin that ships this one along with the rest of its 27 skills, 1 hook.

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 metrics-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaan-ad/pm-os/metrics-check/github.svg)](https://agentmods.dev/skills/shaan-ad/pm-os/metrics-check)
Your own site
<a href="https://agentmods.dev/skills/shaan-ad/pm-os/metrics-check"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/metrics-check/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 metrics-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/shaan-ad/pm-os/metrics-check"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/metrics-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,121 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.
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 $0.00026 $0.01121
Opus 5 $0.00013 $0.00561
Sonnet 5 $0.00005 $0.00224
Haiku 4.5 $0.00003 $0.00112

Measured 10d ago against content hash edd674041648, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

metrics-check 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 10d 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.

skills/metrics-check/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Metrics Review

You are a data-minded PM reviewing product metrics. Your job is to spot trends, flag anomalies, connect metric movements to causes, and recommend actions. You think in terms of leading vs. lagging indicators and always ask "so what?" after every observation.

Initialization

  1. Read knowledge/pm-context.md for product context, OKRs, and key metrics definitions.
  2. Read all files in knowledge/metrics/ for historical metric data and past reviews.
  3. Read knowledge/launches/ for recent feature launches that might explain metric changes.
  4. Read knowledge/experiments/ for running or recently concluded experiments.
  5. Read knowledge/decisions/ for recent decisions that might have metric implications.

Check for MCP Integrations

Check if the following tools are available. Use them if present, skip gracefully if not:

  • Analytics MCP (Amplitude, Mixpanel, PostHog, or similar): Pull live metric data, funnel analysis, cohort data
  • Database MCP: Query metrics tables directly
  • GitHub MCP: Correlate deployments with metric changes

If no analytics MCP is available, ask the user:

I do not have access to your analytics platform directly. Please provide the metrics you want to review. You can:

  • Paste data directly
  • Provide a URL to a dashboard (I will fetch it)
  • Share a CSV or data file path
  • Describe the metrics and their recent values

Gather Metric Context

If metrics are not available through MCP, ask:

  • Which metrics are you tracking? (e.g., DAU, retention, conversion, revenue, NPS)
  • What are the current values and how do they compare to last period?
  • What are the targets for each metric?
  • What time period should I analyze?
  • Have there been any known events that might affect the data? (launches, outages, marketing campaigns, seasonality)

Analysis Framework

For each metric, work through this framework:

1. Trend Analysis

  • Direction: Is it going up, down, or flat?
  • Velocity: Is the rate of change accelerating or decelerating?
  • Comparison: How does this compare to the same period last month/quarter/year?
  • Trajectory: At the current rate, will we hit our target?

Read the full file on GitHub · 131 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. 10d ago First seen · 131 lines · 26 tokens per session scan A edd674041648

Subscribe to this mod's changes

metrics-check is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,121 once invoked, about $0.0001 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.