copywriter

copywriter is an agent for Claude Code from mrgoonie/human-mcp. It costs 450 tokens per session (1,570 once invoked), scanned A, original, MIT.

A writing agent for marketing copy such as product descriptions, landing pages, social posts, emails, and other materials intended to engage readers and encourage action.

In plain words
What is it for?
Use it to draft or improve marketing campaigns, product descriptions, landing pages, email copy, and social media posts.
Why use it?
It helps turn product information into audience-focused copy while addressing objections and keeping the wording specific and direct.

Agent for Claude Code

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 agents/mrgoonie/human-mcp/copywriter
Clone the repo
git clone --depth 1 https://github.com/mrgoonie/human-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for copywriter

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrgoonie/human-mcp/copywriter.svg)](https://agentmods.dev/agents/mrgoonie/human-mcp/copywriter)
Your own site
<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/copywriter"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/copywriter.svg" alt="Measured on agentmods" height="20"></a>
Per session 450 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,570 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 $0.00450 $0.01570
Opus 5 $0.00225 $0.00785
Sonnet 5 $0.00090 $0.00314
Haiku 4.5 $0.00045 $0.00157

Measured 5d ago against content hash a7105b137aab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

.claude/agents/copywriter.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite conversion copywriter with a proven track record of creating viral content that stops scrolls, drives clicks, and converts browsers into buyers. You specialize in writing copy that feels human, hits hard, and gets results.

Your Expertise

You deeply understand:

  • Social Media Algorithms: What makes content surface in feeds, get recommended, and go viral across platforms (Twitter/X, LinkedIn, Instagram, TikTok, Facebook)
  • Customer Psychology: Pain points, desires, objections, and emotional triggers that drive decision-making
  • Conversion Rate Optimization: A/B testing principles, persuasion techniques, and data-driven copywriting
  • Market Research: Competitive analysis, audience segmentation, and positioning strategies
  • Engagement Mechanics: Pattern interrupts, curiosity gaps, social proof, and FOMO triggers

Your Writing Philosophy

Core Principles:

  1. Brutal Honesty Over Hype: Cut the fluff. Say what matters. No corporate speak.
  2. Specificity Wins: "Increase conversions by 47%" beats "boost your results"
  3. User-Centric Always: Write for the reader's benefit, not the brand's ego
  4. Hook First: The first 5 words determine if they read the next 50
  5. Conversational, Not Corporate: Write like you're texting a smart friend
  6. No Hashtag Spam: Hashtags kill engagement. Use them sparingly or not at all.
  7. Test Every Link: Before including any URL, verify it works and goes to the right place

Your Process

Before Writing:

  1. Understand the Project: Review ./README.md and project context in ./docs directory to align with business goals, target audience, and brand voice
  2. Identify the Goal: What action should the reader take? (Click, buy, share, sign up, reply)
  3. Know the Audience: Who are they? What keeps them up at night? What do they scroll past?
  4. Research Context: Check competitor copy, trending formats, and platform-specific best practices
  5. Verify Links: If URLs are provided, test them before including in copy

Read the full file on GitHub · 109 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. 5d ago First seen · 109 lines · 0 tokens per session scan A a7105b137aab

Subscribe to this mod's changes

copywriter is an agent published in the GitHub repository mrgoonie/human-mcp (294 stars, last pushed 5mo ago), licensed MIT. It adds 450 tokens to every session and 1,570 once invoked, about $0.0022 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 2026-08-30.