pm-skills: Instructions file for Claude Code

CLAUDE.md

pm-skills CLAUDE.md is an instructions file for Claude Code from product-on-purpose/pm-skills. It costs 568 tokens per session, scanned A, original, Apache-2.0.

A set of writing and project instructions for Claude Code, an AI coding assistant. It defines style, documentation, and file-visibility rules.

In plain words
What is it for?
Use it to guide code changes, documentation, naming, formatting, and decisions about which files can be shared.
Why use it?
It gives the coding assistant consistent rules to follow, including avoiding em dashes and treating public and private files differently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is product-on-purpose/pm-skills's own configuration. It tells Claude Code how to work on pm-skills 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 pm-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to product-on-purpose/pm-skills. 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/product-on-purpose/pm-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/product-on-purpose/pm-skills

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 pm-skills CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/product-on-purpose/pm-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/product-on-purpose/pm-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 568 This file is loaded in full into every session.
When invoked 568 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 $0.00568 $0.00568
Opus 5 $0.00284 $0.00284
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured 11d ago against content hash 52c48c59d17e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 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.

CLAUDE.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Style Rules

No em-dash characters

NEVER use em-dash characters (, U+2014) in any output. This is a hard rule across all generated content: prose, code comments, file names, commit messages, plan docs, internal notes, memory files, or anything authored by Claude in this repo.

When you would reach for an em-dash, use one of:

  • - (space-hyphen-space) for parenthetical pauses
  • : (colon) when introducing a clarification or list
  • , (comma) for softer pauses
  • Sentence break (. ) when the thought completes
  • Restructure the sentence to remove the need entirely

This rule was codified 2026-04-13 and re-applied through multiple em-dash sweeps. Do not author em-dashes in the first place. The cost of authoring then sweeping is much higher than the cost of internalizing the rule.

Documentation Rules

Public vs Private Files

  • Some internal working material is gitignored (for example _NOTES/, _LOCAL/), so external readers cannot access those paths. Note that docs/internal/ is TRACKED, not gitignored: it is visible to anyone browsing the repo, so treat it as maintainer-facing rather than private.
  • Never reference gitignored internal notes in public-facing files:
    • README.md
    • CHANGELOG.md
    • CONTRIBUTING.md
    • Any file a user cloning the repo would read
  • If content from internal notes needs to be public, move it to a tracked location first
  • Agent context files (_agent-context/) may reference internal notes for coordination

CHANGELOG Best Practices

  • Describe what changed, not where your working files are
  • Reference public paths only (e.g., skills/deliver-prd/)
  • Link to GitHub issues/PRs for context, not internal planning docs

File References

When referencing files in documentation:

  • Use relative paths from repo root
  • Only reference tracked (non-gitignored) files
  • If a file is gitignored, summarize its content instead of linking

Project Context

  • 68 PM skills on main (catalog stable since v2.29.0): 30 phase skills (across 6 Triple Diamond phases) + 11 foundation skills + 12 utility skills + 15 tool-classification entries (Foundation Sprint family of 7 + Design Sprint family of 7 + tool-note-and-vote standalone).
  • Follows agentskills.io specification
  • Apache 2.0 licensed
  • See AGENTS.md for skill discovery

Read the full file on GitHub · 50 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 · 50 lines · 568 tokens per session scan A 52c48c59d17e

Subscribe to this mod's changes

pm-skills CLAUDE.md is an instructions file published in the GitHub repository product-on-purpose/pm-skills (657 stars, last pushed yesterday), licensed Apache-2.0. It adds 568 tokens to every session, about $0.0028 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

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

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 · 5,153 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

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

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