Four Pillars PM Check

Four Pillars PM Check is a skill for Claude Code from BrennanJCollins/UnabatedPM-coaching. It costs 60 tokens per session (3,323 once invoked), scanned A, original, MIT.

An interactive review of product management across Strategy, Delivery, Customer Experience, and Growth, with scores and coaching.

In plain words
What is it for?
Use it to review a product plan, score its four areas, find blind spots, and get advice suited to the product's stage.
Why use it?
It reveals missing product thinking and overreliance on familiar strengths. It can also assess a document without a conversation.

Skill for Claude Code

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

Part of the unabatedpm-strategic-thinking plugin — 6 skills, 1 command shipped together

Good fit Use it to review a product plan, score its four areas, find blind spots, and get advice suited to the product's stage.

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

Made for: Claude Code.

Or install unabatedpm-strategic-thinking, the plugin that ships this one along with the rest of its 6 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 Four Pillars PM Check

README.md
[![agentmods](https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/four-pillars-check/github.svg)](https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/four-pillars-check)
Your own site
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/four-pillars-check"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/four-pillars-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 Four Pillars PM Check

Your own site · 80×15
<a href="https://agentmods.dev/skills/brennanjcollins/unabatedpm-coaching/four-pillars-check"><img src="https://agentmods.dev/badge/skills/brennanjcollins/unabatedpm-coaching/four-pillars-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,323 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 $0.00060 $0.03323
Opus 5 $0.00030 $0.01662
Sonnet 5 $0.00012 $0.00665
Haiku 4.5 $0.00006 $0.00332

Measured 11d ago against content hash e6ed188b823f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Four Pillars PM 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 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.

unabatedpm-strategic-thinking/skills/four-pillars-check/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.

Operating Modes

This skill operates in two modes:

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

Evaluate mode: Read a document silently, score it against this skill's rubric, 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 document and return a structured assessment. Do NOT coach. Do NOT ask questions. Read and score.

Score each dimension 1-5:

  • 1 = Not present or fundamentally broken
  • 2 = Attempted but significant gaps
  • 3 = Competent but missing key elements
  • 4 = Strong with minor improvements possible
  • 5 = Exemplary — would pass senior PM review

Dimensions to evaluate (all four pillars at high level):

  1. Strategy — Does the document clearly articulate WHICH customer/problem is being solved with evidence, or is it vague/missing?

  2. Delivery — Is the plan outcome-focused (measure by problem solved) or feature-focused (measure by ships)?

  3. Customer Experience — Is the document journey-aware with qualitative insights, or feature-aware/missing CX perspective?

  4. Growth — Does it show platform-thinking and business impact, or just feature-thinking?

Apply Four Pillars bias detection to score:

  • Identify the dominant pillar (highest coverage — likely matches PM's background)
  • Identify the blind spot (lowest coverage — likely neglected area)
  • Flag whether this is phase-appropriate (e.g., discovery phase should be Strategy-heavy, not Delivery-heavy)

Return format:

SKILL: Four Pillars Check
CATEGORIES SCORED:
- Strategy: [X]/5
  Evidence: "[exact quote showing clear customer/problem or vague assertion]"
  Gap: [missing specificity or evidence]
  Upgrade: [single highest-leverage change]
- Delivery: [X]/5
  Evidence: "[quote showing outcome-focus or feature-focus]"
  Gap: [what's missing]
  Upgrade: [single highest-leverage change]
- Customer Experience: [X]/5
  Evidence: "[quote showing journey/empathy or functional-only thinking]"
  Gap: [what's missing]
  Upgrade: [single highest-leverage change]
- Growth: [X]/5
  Evidence: "[quote showing platform/business impact or feature-thinking]"
  Gap: [what's missing]
  Upgrade: [single highest-leverage change]

BIAS & BLIND SPOT:
- Dominant pillar: [Strategy/Delivery/CX/Growth] — likely PM background
- Neglected pillar: [the weakest one]
- Phase assessment: [Is this appropriate for the current stage, or over-indexed on wrong pillar?]

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 · 60 tokens per session scan A e6ed188b823f

Subscribe to this mod's changes

Four Pillars PM Check is a skill published in the GitHub repository BrennanJCollins/UnabatedPM-coaching (4 stars, last pushed 21d ago), licensed MIT. It adds 60 tokens to every session and 3,323 once invoked, about $0.0003 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.