pm-skills CLAUDE.md

A set of instructions for AI agents working in the phuryn/pm-skills repository. It explains the project structure, its nine product-management plugins, and the rules for maintaining them.

In plain words
What is it for?
Guiding agents that inspect or modify the pm-skills project, including its plugins, skills, commands, tests, documentation, and release files.
Why use it?
It gives agents one documented source of truth for understanding and changing that repository, reducing confusion about its files and design rules.

Instructions file

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.

agentmods
npx agentmods add instructions/phuryn/pm-skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/phuryn/pm-skills
Per session 1,830 This file is loaded in full into every session.
When invoked 1,830 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01830 $0.01830
Opus 5 $0.00915 $0.00915
Sonnet 5 $0.00366 $0.00366
Haiku 4.5 $0.00183 $0.00183

Measured yesterday against content hash 9e1fff4c61fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-skills 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 yesterday.

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 · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI agents (Claude Code, Cowork, and others) working in this repository. This file is the single source of truth for how the project is structured and maintained.

Project Overview

PM Skills (phuryn/pm-skills) — a marketplace of 9 independent plugins (68 skills, 42 commands) that bring structured product-management workflows to AI coding assistants. Built for Claude Code and Claude Cowork; the skills are also compatible with other agents (Gemini CLI, Cursor, Codex CLI).

Owner: Paweł Huryn — [email protected]https://www.productcompass.pm

Repo Structure

pm-skills/                           <- repo root
├── .claude-plugin/marketplace.json  <- root marketplace manifest (lists all 9 plugins)
├── .docs/images/                    <- images used by README (webp, gif)
├── .gitattributes
├── .gitignore
├── .github/workflows/               <- CI: tests.yml (every PR/push), tag-on-merge.yml (auto-release)
├── CHANGELOG.md                     <- release source of truth (new ## vX.Y.Z heading on main = release)
├── CLAUDE.md                        <- this file (agent guidance, single source of truth)
├── AGENTS.md                        <- pointer to CLAUDE.md (for non-Claude agents)
├── CONTRIBUTING.md                  <- contributor guidelines
├── README.md                        <- public documentation (GitHub)
├── LICENSE                          <- MIT
├── validate_plugins.py              <- plugin validator
├── tests/                           <- unit + docs-consistency tests (unittest)
└── pm-{name}/                       <- 9 plugin directories
    ├── .claude-plugin/plugin.json   <- per-plugin manifest
    ├── skills/{skill}/SKILL.md      <- one folder per skill
    ├── commands/{command}.md        <- one file per command
    └── README.md                    <- per-plugin documentation

The 9 plugins

Plugin Focus
pm-product-discovery Ideation, experiments, assumption testing, prioritization, interview synthesis
pm-product-strategy Vision, strategy/lean/business-model canvas, SWOT, PESTLE, Ansoff, Porter, monetization
pm-execution PRDs, OKRs, roadmaps, sprints, pre-mortems, stakeholder maps, user stories, red-teaming
pm-market-research Personas, segmentation, sentiment analysis, competitive analysis, market sizing
pm-data-analytics SQL query generation, cohort/retention analysis
pm-go-to-market GTM strategy, growth loops, motions, beachhead segments, ICPs
pm-marketing-growth Marketing ideas, value-prop statements, North Star metrics, naming, positioning
pm-toolkit Resume review, NDA drafting, privacy policy, grammar/flow checking
pm-ai-shipping AI Shipping Kit: document a vibe-coded app, map test coverage, audit security/performance against intended behavior, compile a shipping packet

Read the full file on GitHub · 118 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. yesterday First seen · 118 lines · 1,830 tokens per session scan A 9e1fff4c61fc

Subscribe to this mod's changes

pm-skills CLAUDE.md is an instructions file published in the GitHub repository phuryn/pm-skills (25,802 stars, last pushed 2mo ago), licensed MIT. It adds 1,830 tokens to every session, about $0.0092 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 2026-08-30.

Related

Other instructions, from other repositories