Product Metrics Ladder Coach

Product Metrics Ladder Coach is a skill for Claude Code from BrennanJCollins/UnabatedPM-coaching. It costs 59 tokens per session (4,320 once invoked), scanned B, original, MIT.

A coaching skill that helps product managers connect a proposed feature to product measures, customer value, and business results. A product metric is a measurable signal such as usage or retention.

In plain words
What is it for?
Use it to discuss product priorities interactively or evaluate PRDs, OKRs, and metric documents against the five-step Product Metrics Ladder.
Why use it?
It catches plans that describe what to build without explaining why it matters, and helps assess whether the chain from feature to business outcome is complete.

Skill for Claude Code

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

Part of the unabatedpm-business-building plugin — 8 skills, 1 command shipped together

Good fit Use it to discuss product priorities interactively or evaluate PRDs, OKRs, and metric documents against the five-step Product Metrics Ladder.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder
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 BrennanJCollins/UnabatedPM-coaching --skill product-metrics-ladder
Clone the repo
git clone --depth 1 https://github.com/BrennanJCollins/UnabatedPM-coaching

Made for: Claude Code.

Or install unabatedpm-business-building, the plugin that ships this one along with the rest of its 8 skills, 1 command.

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 Product Metrics Ladder Coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder/github.svg)](https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder)
Your own site
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder/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 Product Metrics Ladder Coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/product-metrics-ladder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,320 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00059 $0.04320
Opus 5 $0.00030 $0.02160
Sonnet 5 $0.00012 $0.00864
Haiku 4.5 $0.00006 $0.00432

Measured 12d ago against content hash 749a51d7f2c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

Product Metrics Ladder Coach scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Ask questions, don't lecture** - Help them discover the gaps through Socratic method
unabatedpm-business-building/skills/product-metrics-ladder/SKILL.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating Modes

This skill operates in two modes:

Conversation mode (default): Coach the PM through the Metrics Ladder interactively. Triggered by direct invocation or natural conversation.

Evaluate mode: Read a document silently, score how well it connects features to business outcomes, and return structured findings. No conversation, no questions — just assessment. Triggered by the /audit orchestrator.

Evaluate Mode Instructions

When invoked in evaluate mode, you receive a PRD, OKR doc, metrics dashboard, or any document that should connect product work to outcomes. Do NOT coach. Do NOT ask questions. Read and score.

Score each dimension 1-5:

  • 1 = Not present or fundamentally broken (feature list with no metrics)
  • 2 = Attempted but significant gaps (metrics exist but don't ladder up)
  • 3 = Competent but missing key elements (partial ladder, missing business outcome connection)
  • 4 = Strong with minor improvements possible (full ladder with minor gaps)
  • 5 = Exemplary — every feature traces to a business outcome with measurable steps

Dimensions to evaluate:

  1. Problem discovery & prioritization — Does the document explain WHY these features/metrics matter? Is there a clear problem → metric → outcome chain? Or is it a feature list without a "so what?"

  2. Solution validation & optimization — Does the document define how success will be measured? Are there baselines, targets, and validation criteria? Does it treat launch as a hypothesis or a finish line?

Apply the Product Metrics Ladder test:

  • Feature level: What are we building? (Must be present)
  • Product Metric: What changes when we ship it? (Must be present and measurable)
  • Product Objective: What goal does that metric serve? (Must connect to something larger)
  • Customer Value: How does the customer's life improve? (Must be articulated)
  • Business Outcome: What business metric moves? (Must connect to revenue, retention, or cost)

For each feature or initiative in the document, check: Does it climb all 5 rungs? Where does the ladder break?

Read the full file on GitHub · 413 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 · 413 lines · 59 tokens per session scan B 749a51d7f2c7

Subscribe to this mod's changes

Product Metrics Ladder Coach is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 21d ago), licensed MIT. It adds 59 tokens to every session and 4,320 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.