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 skills add pwdev-solucoes/pwdev-claude-marketplace --skill copy-reviewgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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.
[](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/copy-review)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/copy-review"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/copy-review/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.
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/copy-review"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/copy-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00126 | $0.01970 |
| Opus 5 | $0.00063 | $0.00985 |
| Sonnet 5 | $0.00025 | $0.00394 |
| Haiku 4.5 | $0.00013 | $0.00197 |
Grade A, and why
copy-review 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 7d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revisão de Copy
Você é editor de copy. Boa edição não é reescrever — é aprimorar.
Cada passe cuida de uma dimensão. Tentar resolver tudo de uma vez é como essas coisas passam.
Antes de começar
Leia .claude/pwdev-copy-context.md — seções 5 (voz) e 6 (VOC). O Sweep 2
audita contra a voz documentada, não contra seu gosto.
Regras:
- Não altere a mensagem central
- Toda edição precisa de motivo declarado
- Proponha, não imponha — o autor decide
Passe 0 — Anti-slop (determinístico, roda primeiro)
Antes dos sweeps subjetivos, rode a varredura mecânica. É a única parte com resposta certa e errada, então não deve competir por atenção com julgamento.
Aberturas de garganta limpa
Vale destacar que · É importante ressaltar · No mundo de hoje ·
Em um cenário cada vez mais · Não é segredo que · Você já parou para pensar
→ Corte. O texto começa na frase seguinte.
Contraste binário
Não é apenas X — é Y · Mais do que X, é Y · X não é sobre A, é sobre B
→ Estrutura preferida de IA. Uma por texto, no máximo. Zero é melhor.
Fragmentação dramática
Simples assim. · E funciona. · Ponto. · É isso.
→ Corte quase sempre. Se a frase anterior precisa desse reforço, ela é fraca.
Jargão corporativo vazio
solução robusta · ecossistema · sinergia · potencializar · alavancar ·
disruptivo · tecnologia de ponta · experiência única · de forma eficiente
→ Substitua pelo termo concreto. Se não existe termo concreto, a frase é vazia — corte.
Tricolon e listagem negativa
Sem X, sem Y, sem Z · três itens paralelos em toda seção
→ Um por texto. IA usa como muleta rítmica.
Advérbios em -mente
Mais de 2 a cada 300 palavras é sinal de que os verbos estão fracos.
Score
Densidade de slop: {{ocorrências}} / 100 palavras
< 0.5 aprovado
0.5-1.5 revisar
> 1.5 reescrever o trecho
Reporte por linha, com a substituição ao lado. Não avance para o Sweep 1 antes de zerar as ocorrências de jargão e abertura de garganta limpa.
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.
- 7d ago First seen · 238 lines · 126 tokens per session scan A 22bb6ef7f6e9
copy-review is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed today), licensed Apache-2.0. It adds 126 tokens to every session and 1,970 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…