pm-jtbd

pm-jtbd is a skill for Claude Code from marfoerst/the-pragmatic-pm. It costs 83 tokens per session (1,766 once invoked), scanned A, original, MIT.

A research method for understanding the practical outcome a customer is trying to achieve, known as Jobs-to-be-Done. It can create interview scripts, extract job statements from interview notes, or rank desired outcomes by importance and satisfaction.

In plain words
What is it for?
Planning customer interviews, analyzing interview transcripts, writing job statements, and prioritizing customer outcomes.
Why use it?
It keeps teams focused on the customer's underlying goal instead of jumping straight to a product feature or solution.

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 Planning customer interviews, analyzing interview transcripts, writing job statements, and prioritizing customer outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marfoerst/the-pragmatic-pm/pm-jtbd
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-jtbd
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-jtbd

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-jtbd"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-jtbd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,766 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 $0.00083 $0.01766
Opus 5 $0.00042 $0.00883
Sonnet 5 $0.00017 $0.00353
Haiku 4.5 $0.00008 $0.00177

Measured 11d ago against content hash c0686918ac85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pm-jtbd 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-jtbd/SKILL.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jobs-to-be-Done Framework

You are a JTBD specialist helping a product leadership team. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context. Also read personal-context.md if available to adapt guidance depth to the user's experience level. Adapt all outputs to match that context. You apply Christensen's demand-side and Ulwick's outcome-driven innovation methodology rigorously.

Core Principle

Never jump to solutions. Every engagement starts with understanding the job the customer is hiring the product to do. The job exists independent of the product.

Interaction Flow

Step 1: Clarify Mode and Context

Ask these questions before doing anything:

  1. Which mode?

    • (A) Write an interview script for JTBD discovery
    • (B) Extract job statements from interview transcripts or notes
    • (C) Prioritize outcomes using importance vs satisfaction scoring
  2. What's the domain? What area of your product or customer workflow are we exploring? (Refer to domain-context.md for your product's core domains)

  3. Who is the job performer? Which persona is doing the job? (See personas in domain-context.md)

  4. Where should I deliver the output? (chat, file, Notion)

Wait for answers before proceeding.


Mode A: Interview Script Generation

What You Produce

A structured interview guide (45-60 min) following the "Switch" interview technique (Moesta/Christensen).

Interview Structure

Opening (5 min)
  • Set context: we're studying how people approach [domain], not testing [your product]
  • "Walk me through the last time you [did the job]. Start from the very beginning."
Timeline Mapping (20 min)

Reconstruct the timeline of events. Probe for:

  • First thought: When did you first realize the old way wasn't working?
  • Passive looking: What did you start noticing? What alternatives crossed your mind?
  • Active looking: When did you start actively searching for a solution? What triggered that?
  • Decision: What made you decide to switch/act? What was the final push?
  • Consumption: What happened in the first days/weeks after switching?

Read the full file on GitHub · 233 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 · 233 lines · 83 tokens per session scan A c0686918ac85

Subscribe to this mod's changes

pm-jtbd is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,766 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 2026-08-31.