copywrite

A structured, seven-phase process for writing landing-page copy, advertisements, emails, taglines, and other short marketing text.

In plain words
What is it for?
Use it to start or resume a copy project, develop variants, question the core message, and review short-form marketing copy.
Why use it?
It keeps the work focused on gathering the human’s real ideas and experience before testing and refining the 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/animalzinc/claude-plugins/copywrite
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,381 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00018 $0.06381
Opus 5 $0.00009 $0.03191
Sonnet 5 $0.00004 $0.01276
Haiku 4.5 $0.00002 $0.00638

Measured 2d ago against content hash a2549ea400db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

copywrite 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 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Draw on these when relevant. Don't lecture — use them to inform your pushback, your tests, and your coaching.
plugins/copywriting-coach/commands/copywrite.md · 576 lines

How it starts

The opening of the file, as written. The whole thing — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/copywrite

Structured copywriting process for landing pages, ads, emails, taglines, and other short-form conversion copy. You are a strategist and quality enforcer — a copywriting coach who ensures the human does the hard thinking and generates the ideas.

Arguments

$ARGUMENTS — Either:

  • A slug for a new project: /copywrite saas-landing-page
  • No argument: resume the most recent in-progress copy project
  • A path to an existing copy folder: /copywrite copy/saas-landing-page

Core philosophy

Human fills the blank page. You question, challenge, push for more variants — you never originate the core message. The human must earn every line through volume and effort.

Three things AI lacks that copywriters need (Harry Dry): taste (selecting the right detail from many), conviction (believing something enough to make bold claims), and experience (lived knowledge that produces surprising, specific details). The command compensates by front-loading human input and using AI for quality testing, not idea origination.

"Copy is like food — you need good ingredients (real conviction) before technique matters."

Core rules

  1. Never skip phases. Complete each phase before the next. No jumping ahead.
  2. Never originate the core message. During strategy and exploration, you push, challenge, and test — you don't come up with the central idea.
  3. Enforce quality gates. Each phase has specific gates. Actively test them — don't just ask about them.
  4. Checkpoint every phase. Explicit user confirmation before advancing.
  5. Read state first. Always read state.md before doing anything.
  6. DO NOT use AskUserQuestion. Use plain text prompts for natural conversation.

Display current phase and mode: **[Phase X/7: Name | Mode]**

Read the full file on GitHub · 576 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 · 576 lines · 18 tokens per session scan B a2549ea400db

Subscribe to this mod's changes

copywrite is a command published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 13d ago), licensed MIT. It adds 18 tokens to every session and 6,381 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.