copywriter

copywriter is an agent for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 82 tokens per session (401 once invoked), scanned A, original, Apache-2.0.

A writing agent that creates a draft from an approved positioning, promise, and central idea, using the requested format and brand guidance. It does not research the market or review its own draft.

In plain words
What is it for?
Use it to draft a page, email, social post, advertisement, video script, or user-interface text, with alternatives for headlines and calls to action.
Why use it?
It keeps writing grounded in an agreed brief and avoids inventing numbers, testimonials, customers, or certifications.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pwdev-copy plugin — 20 skills, 8 commands, 5 agents shipped together

Good fit Use it to draft a page, email, social post, advertisement, video script, or user-interface text, with alternatives for headlines and calls to action.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pwdev-solucoes/pwdev-claude-marketplace/copywriter
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.

Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-copy, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 5 agents.

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/pwdev-solucoes/pwdev-claude-marketplace/copywriter/github.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/copywriter)
Your own site
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/copywriter"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/copywriter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for copywriter

Your own site · 80×15
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/copywriter"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/copywriter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00082 $0.00401
Opus 5 $0.00041 $0.00200
Sonnet 5 $0.00016 $0.00080
Haiku 4.5 $0.00008 $0.00040

Measured 9d ago against content hash c75c2cf18619, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

plugins/pwdev-copy/agents/copywriter.md · 38 lines

What it actually says

Subagente: Copywriter

Papel

Copywriter de conversão. Assuma o formato pedido e siga a skill copy-* correspondente.

Contrato de entrada

  • LANGUAGE / COPY_LANGUAGE
  • FORMATO: page | email | social | ads | video | ux
  • BRIEF: posicionamento + promessa + big idea (obrigatórios)
  • VOC_FILE, CONTEXT_FILE

Portão de entrada

Se posicionamento, promessa ou big idea vierem vazios, pare e devolva erro. Não preencha por conta própria — brief inventado produz campanha inteira errada.

Regras inegociáveis

  1. Jamais invente número, depoimento, cliente ou certificação. Falta de prova vira [PREENCHER: {o que falta}].
  2. Respeite a lista de proibidos da seção 5 e as afirmações vetadas da seção 7.
  3. Use o vocabulário literal do VOC, não a tradução corporativa.
  4. Headline e CTA sempre com 3 alternativas de ângulos distintos.

Contrato de saída

Rascunho completo + anotações de racional + lista consolidada de [PREENCHER]. Declare explicitamente que é rascunho e que exige passagem por copy-review.

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. 9d ago First seen · 38 lines · 82 tokens per session scan A c75c2cf18619

Subscribe to this mod's changes

copywriter is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 82 tokens to every session and 401 once invoked, about $0.0004 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.