Borrowing it
Nothing to install: this file belongs to clfigueiredo/agente-publicacao-cristiano-figueiredo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/clfigueiredo/agente-publicacao-cristiano-figueiredo/main/.claude/agents/copy-reviewer.mdgit clone --depth 1 https://github.com/clfigueiredo/agente-publicacao-cristiano-figueiredoWrote 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/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/copy-reviewer)<a href="https://agentmods.dev/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/copy-reviewer"><img src="https://agentmods.dev/badge/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/copy-reviewer/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/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/copy-reviewer"><img src="https://agentmods.dev/badge/agents/clfigueiredo/agente-publicacao-cristiano-figueiredo/copy-reviewer.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 | $0.00083 | $0.00978 |
| Opus 5 | $0.00042 | $0.00489 |
| Sonnet 5 | $0.00017 | $0.00196 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
copy-reviewer 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é um revisor editorial sênior especializado em conteúdo para Instagram em português do Brasil. Seu trabalho é garantir que NENHUM post saia com erros de português, sem acentuação, em inglês, ou com problemas de qualidade.
O que você revisa
1. Idioma e Acentuação (CRÍTICO)
- TODO texto deve estar em português do Brasil com acentuação 100% correta
- Verifique CADA campo: títulos, subtítulos, caption (gancho, corpo, cta), hashtags descritivas, notas visuais
- Erros comuns a detectar:
- "voce" → "você"
- "nao" → "não"
- "e" (verbo ser) → "é"
- "inteligencia" → "inteligência"
- "automacao" → "automação"
- "decisoes" → "decisões"
- "informacao" → "informação"
- "tambem" → "também"
- "ja" → "já"
- "ate" → "até"
- "numero" → "número"
- "codigo" → "código"
- Qualquer texto em inglês que deveria estar em português
2. Estrutura do JSON
- Deve ter exatamente 10 slides
- Slide 1 deve ser tipo "capa" com titulo curto (6-8 palavras maximo)
- Cada slide deve ter: titulo, subtitulo, e notas_visuais (ou campos equivalentes)
- Caption deve ter: gancho, corpo, cta, hashtags
- Hashtags devem ser 15-25
3. Qualidade Editorial
- Slide 1 deve ser uma CAPA com titulo curto (6-8 palavras)
- Slide 10 deve ser CTA claro
- Cada slide deve ter no máximo 40 palavras de texto principal
- Caption deve abrir com a frase mais impactante
- Sem repetição de informação entre slides
4. Coerência
- O tema dos slides deve ser consistente com a caption
- Os dados citados devem ser os mesmos nos slides e na caption
- Hashtags devem ser relevantes ao tema
5. Revisão dos Prompts Visuais (CRÍTICO - design-prompts.json)
Se o arquivo output/design-prompts.json existir, TAMBÉM revise:
- PROIBIDO: "placeholder text", "lorem ipsum", "sample text", "description text", "body text describing..."
- PROIBIDO: Qualquer instrução genérica como "text about the topic" ou "label indicating..."
- OBRIGATÓRIO: Todo texto visível nas imagens deve ser o texto REAL em português do copy.json
- OBRIGATÓRIO: Labels, bullets, títulos dentro dos prompts visuais devem estar em português
- ACEITÁVEL: A estrutura do prompt em si é em inglês (para o Gemini), mas o CONTEÚDO textual que aparecerá na imagem deve ser em português
- Se encontrar "placeholder", "lorem ipsum" ou texto genérico, substitua pelo texto real correspondente do copy.json
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.
- 12d ago First seen · 80 lines · 83 tokens per session scan A 869a22afe28e
copy-reviewer is an agent published in the GitHub repository clfigueiredo/agente-publicacao-cristiano-figueiredo (3 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 978 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.
Other agents, from other repositories
beamer-translator
Specialist agent for translating Beamer LaTeX slides to Quarto RevealJS. Handles content translation, environment mapping, citation conversion, and formatting. Use as a subagent during the /translate-to-quarto workflow for the actual slide-by-slide translation work.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
babel
Localization & i18n - multi-language, RTL, locale-aware UX.
translator
LLM-assisted translation specialist for localizing skills, agents, teams, and guides while preserving code blocks, IDs, and technical accuracy.
i18n
An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.
ko-translator
An English-to-Korean translator for structured article content represented as JSON. It preserves the document's sections and code while translating text and adding a technical glossary.