copy

A command for drafting marketing text in formats such as advertisements, landing pages, emails, social posts, and sales pages. It adapts the draft to the requested format, audience, and goal.

In plain words
What is it for?
Use it for headlines, feature sections, calls to action, ads, email campaigns, sales pages, social captions, or other website copy.
Why use it?
It provides a structured first draft when writing promotional content from scratch or improving existing wording.

Command

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/brainbytes-dev/everything-claude-marketing/copy
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00877
Opus 5 $0.00013 $0.00439
Sonnet 5 $0.00005 $0.00175
Haiku 4.5 $0.00003 $0.00088

Measured 2d ago against content hash d002967351d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copy 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 2d 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/copy.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/copy

Write high-converting marketing copy for any format, from landing page headlines to long-form sales pages. Adapts voice, tone, and structure to your brand and audience.

What This Command Does

The /copy command generates polished marketing copy tailored to your specified format, audience, and goals. It handles everything from short-form ad copy to full landing pages, applying proven copywriting frameworks and persuasion principles. The output is ready to use or serves as a strong first draft for your team to refine.

The command delegates to the copywriter agent, which draws on direct-response and brand copywriting techniques to produce compelling, goal-oriented content.

When to Use

  • You need landing page copy — hero sections, feature blocks, CTAs, or full pages
  • You are writing ad copy for any platform (Google, Meta, LinkedIn, etc.)
  • You need email copy — promotional, transactional, or newsletter content
  • You want sales page copy with structured persuasion flow
  • You need social media captions or post copy
  • You are drafting website copy for any section (about, pricing, features, etc.)
  • You want to rewrite existing copy for better performance

How It Works

  1. Context Gathering — Identifies the format, audience, product/service, and desired action
  2. Framework Selection — Applies the appropriate copywriting framework (AIDA, PAS, BAB, StoryBrand, or others based on format)
  3. Voice Calibration — Matches your brand voice and tone guidelines, or establishes an appropriate tone if none are provided
  4. Draft Creation — Writes the full copy with headlines, body, proof elements, and calls to action
  5. Variant Generation — Provides alternative headlines or CTA options where applicable
  6. Optimization Notes — Includes suggestions for testing and improving performance

Example Usage

Input:

/copy write a hero section for our AI writing assistant landing page

Output:

# Hero Section: AI Writing Assistant

## Headline Options

**Option A (Benefit-led):**
Write 10x faster without sacrificing your voice

**Option B (Pain-led):**
Stop staring at blank pages — start shipping content

**Option C (Outcome-led):**
From idea to published draft in minutes, not days

## Subheadline
The AI writing assistant that learns your style, understands your
audience, and helps you create content that actually converts —
blog posts, emails, ads, and more.

## Supporting Bullets
- **Your voice, amplified** — Trains on your existing content so
  every draft sounds like you, not a robot
- **Built for marketers** — Templates for landing pages, email
  sequences, ad copy, and social posts
- **Edit, not rewrite** — Generates drafts good enough to polish,
  not throw away

## Primary CTA
Start writing free — no credit card required

## Secondary CTA
See it in action (2-min demo)

## Social Proof Line
Trusted by 2,400+ marketing teams to produce content 10x faster

Read the full file on GitHub · 97 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. 2d ago First seen · 97 lines · 26 tokens per session scan A d002967351d1

Subscribe to this mod's changes

copy is a command published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 877 once invoked, about $0.0001 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.