A project setup command that connects Compounding Marketing to the current code project. It checks existing files, asks where to install it, and records approved changes so they can be undone.

Use it after installing the Compounding Marketing plugin to set up project or global files, update configuration, and prepare the marketing tools for use.

It avoids changing project files without approval and keeps a record of changes for clean removal.

cm-setup — Command by classicchins

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 commands/classicchins/compounding-marketing/cm-setup

Clone the repo

git clone --depth 1 https://github.com/classicchins/compounding-marketing

Or install compounding-marketing, the plugin that ships this one along with the rest of its 39 skills, 17 commands.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,755 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01755
Opus 5	$0.00000	$0.00877
Sonnet 5	$0.00000	$0.00351
Haiku 4.5	$0.00000	$0.00176

Measured 3d ago against content hash 36fb4e91a534, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cm-setup 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 3d 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.

commands/cm-setup.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cm-setup — Per-Project Bootstrap

Safely wire Compounding Marketing into the current project.

What It Does

The in-Claude equivalent of npx compounding-marketing. Walks the user through the same decisions the wizard makes, writes only what they approve, and records every change in .compounding-marketing-install.json so /cm-uninstall can reverse it cleanly.

Use this after installing the plugin via /plugin install compounding-marketing (which never modifies user files).

Process

Step 1: Detect current state

Is cwd a project root? (package.json, .git, Cargo.toml, Gemfile, pyproject.toml, go.mod, Makefile, src/, app/)
Does ~/.claude/ exist?
Does CLAUDE.md exist at the project root? Does it already contain ?
Does .mcp.json exist?
Does .compounding-marketing-install.json exist (prior install)?

If a manifest exists, ask: re-run (idempotent — only adds missing pieces) or uninstall first.

Step 2: Pick install scope

[1] Project — install into ./compounding-marketing/   [default if cwd is a project]
[2] Global  — install into ~/.claude/plugins/compounding-marketing/
[3] Custom  — install into a path you specify

Auto-default: project if cwd looks like a project, else global if ~/.claude/ exists, else project.

Step 3: Pick MCPs (optional)

Offer the two research MCPs. For each, prompt for an API key (Enter to skip and store the ${PERPLEXITY_API_KEY} / ${EXA_API_KEY} placeholder).

Perplexity — AI web research. Key: https://perplexity.ai/settings/api
Exa — Neural search + company intelligence. Key: https://dashboard.exa.ai

Write the MCP config based on scope:

Project: write .mcp.json at project root (one mcpServers.<name> entry per MCP).
Global: do NOT touch ~/.claude.json (it holds Claude Code's own state). Instead, print claude mcp add --transport stdio --scope user --env KEY=… <name> -- npx -y <package> for the user to run.

Read the full file on GitHub · 137 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.

3d ago First seen · 137 lines · 0 tokens per session scan A 36fb4e91a534

Subscribe to this mod's changes

cm-setup is a command published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,755 tokens. 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.

Marketing and SEO

cm-setup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/cm-setup — Per-Project Bootstrap

What It Does

Process

Step 1: Detect current state

Step 2: Pick install scope

Step 3: Pick MCPs (optional)

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

converge