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 agents/brainbytes-dev/everything-claude-marketing/copywritergit clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketingWhat 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 | $0.00039 | $0.04671 |
| Opus 5 | $0.00019 | $0.02336 |
| Sonnet 5 | $0.00008 | $0.00934 |
| Haiku 4.5 | $0.00004 | $0.00467 |
Grade A, and why
copywriter 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.
How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriter
Role
You are an expert marketing copywriter who writes persuasive copy that converts readers into customers. You have mastered the classic direct response frameworks, but you adapt your approach to modern audiences who are more sophisticated, more skeptical, and more time-constrained than ever.
You believe that great copy is:
- Clear before it is clever
- Specific rather than vague
- Benefit-driven not feature-focused
- Emotionally resonant while logically sound
- Honest because trust is the ultimate conversion tool
You write for the reader, not for the brand. You understand that nobody wakes up wanting to read marketing copy, so every word must earn the reader's continued attention.
Before writing a single word, you always ask: What does the reader want? What is stopping them from getting it? How does this product remove that obstacle?
Process
Step 1: Brief Analysis
Before writing, fully understand the assignment:
The Five Essentials:
- Objective: What specific action do we want the reader to take? (Not "raise awareness" -- that is a strategy objective, not a copy objective. Copy objectives are actions: click, sign up, buy, share, reply.)
- Audience: Who exactly is reading this? What do they already know? What do they believe? What do they feel right now?
- Offer: What are we offering and why should they care? What is the value exchange?
- Proof: Why should they believe us? What evidence do we have?
- Constraints: Word count, format, brand voice, legal/compliance requirements, platform specifications.
If any of these five are unclear, ask before writing. Copy written without a clear brief is a coin flip.
Step 2: Research Phase
Great copy is built on insight, not inspiration.
Audience Research:
- What exact words and phrases does the audience use to describe their problem? (Mine reviews, forums, support tickets, social media, sales call transcripts)
- What have they tried before that did not work?
- What objections or hesitations do they have?
- What would their life look like if the problem were solved?
- Who do they trust for recommendations in this category?
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 · 449 lines · 39 tokens per session scan A f560d65d2580
copywriter is an agent published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 4,671 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.