pm-metric-framework

pm-metric-framework is a skill for Claude Code from marfoerst/the-pragmatic-pm. It costs 102 tokens per session (3,081 once invoked), scanned A, original, MIT.

A product measurement planning skill that builds a hierarchy of metrics, from one main value measure down to team inputs, health checks, and safeguards. It also includes guidance on tracking the data and can use frameworks such as AARRR, which covers stages from acquiring users to retaining and monetising them.

In plain words
What is it for?
Use it to create a KPI hierarchy, measurement plan, product review metrics, or tracking requirements for a feature or team.
Why use it?
It helps teams connect day-to-day activity to product outcomes instead of collecting disconnected KPIs. It also highlights early warning signals and checks that prevent one goal from harming another.

Skill for Claude Code

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

Part of the pm-toolkit plugin — 54 skills, 5 agents, 4 hooks shipped together

Good fit Use it to create a KPI hierarchy, measurement plan, product review metrics, or tracking requirements for a feature or team.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marfoerst/the-pragmatic-pm/pm-metric-framework
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 marfoerst/the-pragmatic-pm --skill pm-metric-framework
Clone the repo
git clone --depth 1 https://github.com/marfoerst/the-pragmatic-pm

Made for: Claude Code.

Or install pm-toolkit, the plugin that ships this one along with the rest of its 54 skills, 5 agents, 4 hooks.

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 pm-metric-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-metric-framework/github.svg)](https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-metric-framework)
Your own site
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-metric-framework"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-metric-framework/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 pm-metric-framework

Your own site · 80×15
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-metric-framework"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-metric-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,081 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 $0.00102 $0.03081
Opus 5 $0.00051 $0.01541
Sonnet 5 $0.00020 $0.00616
Haiku 4.5 $0.00010 $0.00308

Measured 11d ago against content hash 3b2fdb67f4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pm-metric-framework 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 11d 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/pm-metric-framework/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metric Framework Builder

You are a product analytics strategist helping a product leadership team. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context. Adapt all outputs to match that context. The user is a Head of Product or PM who needs a structured, actionable metric hierarchy that teams can operate against.

Intent Detection

Activate this skill when the user:

  • Wants to build a metric framework for a product, feature, or team
  • Needs to define KPIs with leading and lagging indicators
  • Asks about AARRR/pirate metrics or similar frameworks
  • Wants to create a measurement or instrumentation plan
  • Needs health metrics or counter metrics for existing goals
  • Is preparing metrics for a product review or OKR cycle
  • Asks "how do we know if this is working"

Core Principle: Every Metric Has Two Sides

This is non-negotiable in every metric framework you produce.

Every metric must be paired:

  • Leading indicator: Predicts future movement. Actionable today. Input-oriented.
  • Lagging indicator: Confirms past impact. Outcome-oriented. Validates the leading indicator.

If a PM cannot name the leading indicator for their goal, they are flying blind. If they cannot name the lagging indicator, they cannot prove impact.

Process

Phase 1 — Problem Clarity (Ask First)

Mandatory questions (ask all 3):

  1. What are you measuring and why now? Is this a new product launch, an existing product health check, a team OKR exercise, or a specific initiative? Context determines scope.
  2. Do you have a North Star metric defined? If yes, what is it? If no, we should define one first (suggest the pm-north-star skill). The entire framework flows from the North Star.
  3. What is the current state of measurement? Do you have analytics instrumented? What tools are in place? (Mixpanel, Amplitude, custom, nothing?) This determines how pragmatic we need to be about what is measurable today vs. aspirational.

Read the full file on GitHub · 274 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. 11d ago First seen · 274 lines · 102 tokens per session scan A 3b2fdb67f4aa

Subscribe to this mod's changes

pm-metric-framework is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 3,081 once invoked, about $0.0005 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 2026-08-31.