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.
npx agentmods add commands/animalzinc/claude-plugins/copywritegit clone --depth 1 https://github.com/animalzinc/claude-pluginsWhat 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 | $0.00018 | $0.06381 |
| Opus 5 | $0.00009 | $0.03191 |
| Sonnet 5 | $0.00004 | $0.01276 |
| Haiku 4.5 | $0.00002 | $0.00638 |
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. 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
- Never skip phases. Complete each phase before the next. No jumping ahead.
- Never originate the core message. During strategy and exploration, you push, challenge, and test — you don't come up with the central idea.
- Enforce quality gates. Each phase has specific gates. Actively test them — don't just ask about them.
- Checkpoint every phase. Explicit user confirmation before advancing.
- Read state first. Always read
state.mdbefore doing anything. - DO NOT use AskUserQuestion. Use plain text prompts for natural conversation.
Display current phase and mode: **[Phase X/7: Name | Mode]**
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.
- 2d ago First seen · 576 lines · 18 tokens per session scan B a2549ea400db
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.
Other commands, from other repositories
brand-setup
Configure brand voice, terminology, compliance guardrails, and style guide for content production.
engagement
Run a marketing engagement using the 12-Part methodology. Subcommands: start, next, status, validate, re-run-decision, update-back, lif-show, file-tree, list-engagements, four-core, growth-plan, yearly-planner, loop.
resume
Resume a long-running DMP workflow (engagement / campaign-plan / content-engine / seo-audit / competitor-analysis / campaign-audit / launch-campaign) that was interrupted partway through.
seo-audit
Run a comprehensive SEO audit — technical health, on-page, content gaps, E-E-A-T, link profile, and competitor benchmarking.
content-engine
Draft blog posts, ad copy, emails, social media, landing pages, and video scripts with brand voice and SEO.
email-sequence
Design complete email sequences with subject lines, body copy, timing, segmentation, and deliverability guidance.