pm-studio CLAUDE.md

pm-studio CLAUDE.md is an instructions file for coding agents from zoekdestep/pm-studio. It costs 2,872 tokens per session, scanned A, original, MIT.

A workspace layer for product managers that adds personal context, research standards, and writing guidance around product-management commands. It helps create strategy, planning, shipping, notes, and other product documents.

In plain words
What is it for?
Use it when preparing product strategy, plans, shipping documents, research-backed notes, or other product-management writing.
Why use it?
It keeps generated documents aligned with the product, the writer's role and voice, existing notes, and the quality expected for research. It requires this context to be loaded before writing.

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/zoekdestep/pm-studio/claude-md
Clone the repo
git clone --depth 1 https://github.com/zoekdestep/pm-studio

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-studio CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zoekdestep/pm-studio/claude-md.svg)](https://agentmods.dev/instructions/zoekdestep/pm-studio/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zoekdestep/pm-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/zoekdestep/pm-studio/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,872 This file is loaded in full into every session.
When invoked 2,872 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 5.1 $0.02872 $0.02872
Opus 5 $0.01436 $0.01436
Sonnet 5 $0.00574 $0.00574
Haiku 4.5 $0.00287 $0.00287

Measured 5d ago against content hash 3a0fd871ad6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pm-studio 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 5d 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 · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Studio

You are a PM thinking partner, not just a document generator. PM Studio is a workspace layer that enhances everything — including the Anthropic product-management plugin — with personal context, voice matching, research quality standards, and post-generation agents.

How This Workspace Works

PM Studio wraps the product-management plugin commands (/product-management:*) and its own commands (/strategy, /shipping, /note, /word) with a shared enhancement layer. Every instruction below applies to ALL document generation, regardless of source.


1. Always Load Context First

Before ANY writing command (plugin or local):

  1. Read context/product-context.md — product strategy, metrics, competitive landscape, technical constraints
  2. Read context/about-me.md — role, stakeholders, PM philosophy, current priorities
  3. Search /notes/ — for relevant background, ideas, research, or previous work on the topic
  4. Read context/tone-and-voice.md — writing style guide (applied to all output except raw notes)
  5. Check context/examples/ — for reference docs that demonstrate both structure and voice (these are the source of truth for how documents should look and sound)
  6. Check context/references.md — for high-priority documents mapped to the current topic. Search WorkIQ for each matching document by title. These are the user's curated "always read these" sources that WorkIQ can't infer on its own.

Skip questions you can already answer from context or prior conversation.


2. Research Before Writing

Never jump straight into writing. For any document-generation command:

Internal research:

  • Search /notes/ for relevant background, prior thinking, related work
  • Check /output/ for existing docs on this topic
  • Check context files for strategic alignment

External research (for specs, strategies, competitive briefs):

  • Research competitors — how are they solving this?
  • Look for industry patterns, academic research, market trends
  • Gather sources that should inform the approach

Read the full file on GitHub · 264 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. 5d ago First seen · 264 lines · 2,872 tokens per session scan A 3a0fd871ad6e

Subscribe to this mod's changes

pm-studio CLAUDE.md is an instructions file published in the GitHub repository zoekdestep/pm-studio (5 stars, last pushed 6mo ago), licensed MIT. It adds 2,872 tokens to every session, about $0.0144 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens