compounding-marketing: Instructions file for Claude Code

CLAUDE.md

compounding-marketing CLAUDE.md is an instructions file for Claude Code from classicchins/compounding-marketing. It costs 6,536 tokens per session, scanned B, original, MIT.

A collection of instructions and workflows for SaaS marketing. SaaS means software sold as an online service, and the files cover work such as positioning, copywriting, search visibility, conversion improvement, and customer growth.

In plain words
What is it for?
Use it to research a market, define product positioning, write marketing copy, improve landing-page conversion, plan search content, or work on customer lifecycle campaigns.
Why use it?
It gives an AI coding tool a structured way to support recurring marketing work instead of treating every task as a blank page.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; reads ~/.codex paths.

This is classicchins/compounding-marketing's own configuration. It tells Claude Code how to work on compounding-marketing 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 compounding-marketing configures →

Reuse

Borrowing it

Nothing to install: this file belongs to classicchins/compounding-marketing. 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/classicchins/compounding-marketing/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/classicchins/compounding-marketing

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 compounding-marketing CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/classicchins/compounding-marketing/claude-md"><img src="https://agentmods.dev/badge/instructions/classicchins/compounding-marketing/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,536 This file is loaded in full into every session.
When invoked 6,536 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.06536 $0.06536
Opus 5.5 $0.02614 $0.02614
Sonnet 5.5 $0.01307 $0.01307
Haiku 4.5 $0.00654 $0.00654

Measured 2mo ago against content hash d8e7beed5509, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

compounding-marketing CLAUDE.md scanned grade B with 1 finding 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Install via `/cm-setup` (it offers MCP wiring) or `npx compounding-marketing` (writes the right config file per tool: `.mcp.json`, `.cursor/mcp.json`, or `~/.codex/config.toml`). API keys are stored in `.cm-config.json`
CLAUDE.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Compounding Marketing

The Compounding Marketing plugin: 61 marketing skills + 16 workflow commands for SaaS marketing, available to Claude Code, Claude Cowork, Cursor, Codex, ChatGPT, and Zed.

What This Is

Compounding Marketing is a cross-platform AI plugin providing 61 marketing skills and 16 workflow commands for SaaS marketing — positioning, messaging, copy, CRO, SEO, GTM, lifecycle, growth.

It is not a traditional codebase. It's a structured knowledge system: skills are SKILL.md files, workflows are command .md files. The setup wizard (bin/setup.js) installs them into your AI tool of choice with safe, prompt-driven file writes.

Philosophy: Make each unit of marketing work easier than the last. 80% research and planning, 20% execution. Core loop: Research → Position → Message → Execute → Compound.

Quick Reference

You want to… Invoke it as Notes
Use a single skill (e.g., write copy) Natural language ("write landing page copy for…") or /cm-{skill} (e.g., /cm-copywriting) All 61 skills are registered as slash commands. Natural language also works — the right skill is matched by trigger keywords.
Run a multi-step workflow /cm-{workflow} (e.g., /cm-research, /cm-copy, /cm-launch) 16 workflows orchestrate multiple skills end-to-end.
Establish project context (do this first) /cm-context Creates .agents/product-marketing-context.md — every other skill reads from this.
Install / update / remove the plugin /cm-setup, /cm-uninstall, or npx compounding-marketing The npx wizard supports --dry-run, --yes, --scope, --tool.

Slash commands use /cm-{name} (hyphen, not colon). The legacy colon-form is no longer supported.

Repository Structure

skills/           # 61 self-contained marketing skills (each a SKILL.md with YAML frontmatter)
commands/         # 16 workflow commands (cm-*.md, invoked as /cm-{name})
bin/setup.js      # npx setup wizard — readline-only CLI, no external deps, ~1260 lines
scripts/          # generate-claude-md.js (refreshes the Skills section below)
                  # validate-skills.js  (enforces the 7-section skill structure)
mcp/              # Pre-configured MCP servers (Perplexity, Exa) for research enhancement
integrations/     # Optional tool integrations (Linear, GA4, etc.)
.agents/          # Runtime: product-marketing-context.md + learnings/<category>.md

Read the full file on GitHub · 496 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. 2mo ago First seen · 496 lines · 6,536 tokens per session scan B d8e7beed5509

Subscribe to this mod's changes

compounding-marketing CLAUDE.md is an instructions file published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo ago), licensed MIT. It adds 6,536 tokens to every session, about $0.0261 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

compounding-marketing CLAUDE.md compared with instructions from other repositories

compounding-marketing CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
compounding-marketing CLAUDE.mdclassicchins/compounding-marketingInstructions file85mo agoMITB6,536Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode