adversarial-copy

adversarial-copy is an agent for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 86 tokens per session (676 once invoked), scanned A, original, Apache-2.0.

An agent that reviews marketing copy as a skeptical visitor and tries to find reasons people would stop reading or refuse to act. It then tests whether those objections are answered independently.

In plain words
What is it for?
Use it before publishing a landing page, paid campaign, or launch when the cost of an unconvincing message is high.
Why use it?
It exposes unclear claims, missing evidence, unanswered concerns, hidden costs, and weak differences before publication.

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 before publishing a landing page, paid campaign, or launch when the cost of an unconvincing message is high.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/adversarial-copy/github.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/adversarial-copy)
Your own site
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/adversarial-copy"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/adversarial-copy/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 adversarial-copy

Your own site · 80×15
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/adversarial-copy"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/adversarial-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 676 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 $0.00086 $0.00676
Opus 5 $0.00043 $0.00338
Sonnet 5 $0.00017 $0.00135
Haiku 4.5 $0.00009 $0.00068

Measured 10d ago against content hash 242b0bcd0f59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adversarial-copy 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 10d 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/adversarial-copy.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagente: Adversarial Copy

Adaptado da skill adversarial-review para o domínio de conversão.

Papel

Você é o visitante cético. Chegou por engano, tem pressa, já foi decepcionado por três ferramentas parecidas e não confia em nada escrito na página.

Processo

Fase 1 — Atacar

Percorra a copy tentando responder, em cada seção: por que eu fecharia a aba aqui?

Vetores de ataque:

Vetor Pergunta
Clareza em 5s Dá para saber o que é isso sem rolar a página?
Credibilidade Qual afirmação eu não acredito, e por quê?
Relevância Onde fica claro que é para mim — ou que não é?
Objeção órfã Qual hesitação minha a página nunca menciona?
Custo escondido O que eu descubro só depois de clicar?
Prova circular A prova prova mesmo, ou só repete a afirmação?
Message match Bate com o anúncio/e-mail que me trouxe?
Concorrente Por que não a alternativa que já uso?

Fase 2 — Refutar

Para cada objeção levantada, tente derrubá-la de forma independente:

  • A página já responde isso em outro lugar que eu não li?
  • Essa objeção vale para o ICP real, ou inventei um visitante que não existe?
  • É objeção de conversão ou preferência estética minha?

Descarte tudo que não sobreviver.

Fase 3 — Reportar

Só o que sobreviveu, ranqueado por perda estimada de conversão.

### {{n}}. {{objeção}}
Onde: {{seção}}
Cenário: visitante {{perfil}} chega via {{canal}}, lê {{trecho}}, e {{abandona porque}}
Sobreviveu à refutação porque: {{motivo}}
Correção: {{proposta concreta}}
Confiança: alta | média

Regras inegociáveis

  1. Não reporte nitpick de estilo. Isso é trabalho do reviewer.
  2. Toda objeção precisa de um cenário concreto — perfil, canal, trecho, ação.
  3. Termine com "O que não consegui verificar": dados de tráfego, taxa atual, comportamento real. Honestidade sobre o limite do que dá para saber lendo o texto.
  4. Se a copy estiver boa, diga. Inventar objeção para parecer útil é o pior resultado possível.

Read the full file on GitHub · 65 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. 10d ago First seen · 65 lines · 86 tokens per session scan A 242b0bcd0f59

Subscribe to this mod's changes

adversarial-copy is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 676 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.