the-pragmatic-pm: Instructions file for Claude Code

CLAUDE.md

the-pragmatic-pm CLAUDE.md is an instructions file for Claude Code from marfoerst/the-pragmatic-pm. It costs 500 tokens per session, scanned A, original, MIT.

Project instructions for The Pragmatic PM Toolkit, a collection of written workflows and skills for product-management work. They describe its files, conventions, and how its workflows operate.

In plain words
What is it for?
Maintaining PM skills, workflows, agents, hooks, and project context files.
Why use it?
They give an agent the project context needed to edit or extend the toolkit consistently.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is marfoerst/the-pragmatic-pm's own configuration. It tells Claude Code how to work on the-pragmatic-pm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything the-pragmatic-pm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to marfoerst/the-pragmatic-pm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/marfoerst/the-pragmatic-pm/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/marfoerst/the-pragmatic-pm

Made for: Claude Code.

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 the-pragmatic-pm CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/marfoerst/the-pragmatic-pm/claude-md"><img src="https://agentmods.dev/badge/instructions/marfoerst/the-pragmatic-pm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 500 This file is loaded in full into every session.
When invoked 500 The same file — it is already loaded in full.
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 $0.00500 $0.00500
Opus 5 $0.00250 $0.00250
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 10d ago against content hash 944dfe4758e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

the-pragmatic-pm CLAUDE.md 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.

CLAUDE.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Project Instructions

This is a Claude Code plugin called The Pragmatic PM Toolkit. It contains PM skills, agents, and workflows — all as markdown files. There is no application code.

Project Structure

.claude-plugin/     — Plugin manifest (plugin.json + marketplace.json)
agents/             — 5 orchestrator agents (markdown)
skills/             — 48 skills + 6 workflows (each in its own directory as SKILL.md)
hooks/              — 4 automation hooks (JS scripts + hooks.json)
domain-context.md   — Company/product/persona context (customized per user)
personal-context.md — User's role, seniority, preferences (personal, may be gitignored)
CHANGELOG.md        — Release notes for all versions

Key Conventions

  • Every skill reads domain-context.md and personal-context.md in its opening paragraph
  • Frontmatter uses YAML with name and description fields (description includes trigger phrases)
  • Skills follow a phase-based interaction: ask questions first, then generate, then iterate
  • Workflows chain multiple skills with checkpoint-driven artifact handoffs and support mid-entry
  • Agents route user intent to the right skill, asking clarifying questions first
  • No hardcoded examples — all domain-specific content comes from domain-context.md

When Editing Skills

  • Preserve the YAML frontmatter exactly
  • Keep the domain-context.md and personal-context.md references in the opening paragraph
  • Maintain the ask-then-generate pattern — never skip to output without questions
  • Include both leading AND lagging indicators in any metrics section
  • Add Anti-Patterns sections to catch common mistakes
  • Test mentally: would this produce useful output for a junior PM AND a senior PM?

When Adding Skills

  • Directory: skills/pm-{name}/SKILL.md
  • Register in skills/pm-hub/SKILL.md under the right category
  • Register in README.md in the matching table
  • Follow the existing quality standard (see pm-ai-pricing or pm-battlecard as reference)

Read the full file on GitHub · 47 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 · 47 lines · 500 tokens per session scan A 944dfe4758e9

Subscribe to this mod's changes

the-pragmatic-pm CLAUDE.md is an instructions file published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 500 tokens to every session, about $0.0025 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.