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 tatagoncalvesof/imperatriz-toolkit --skill voz-humana-brgit clone --depth 1 https://github.com/tatagoncalvesof/imperatriz-toolkitWrote 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/tatagoncalvesof/imperatriz-toolkit/voz-humana-br)<a href="https://agentmods.dev/skills/tatagoncalvesof/imperatriz-toolkit/voz-humana-br"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/voz-humana-br/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/tatagoncalvesof/imperatriz-toolkit/voz-humana-br"><img src="https://agentmods.dev/badge/skills/tatagoncalvesof/imperatriz-toolkit/voz-humana-br.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 | $0.00243 | $0.04260 |
| Opus 5 | $0.00121 | $0.02130 |
| Sonnet 5 | $0.00049 | $0.00852 |
| Haiku 4.5 | $0.00024 | $0.00426 |
Grade A, and why
voz-humana-br scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voz Humana BR
Skill que transforma texto de IA em texto que soa como pessoa escrevendo em português brasileiro. Stripa todos os tiques de ChatGPT/Claude, mantém o significado intacto, respeita a voz do autor original.
Não é tradução. Não é resumo. Não é reescrita criativa. É reengenharia cirúrgica que troca palavra por palavra, quebra estrutura por estrutura, valida por régua quantitativa.
Filosofia central
- Cada palavra tem que pagar o aluguel. Se a frase funciona sem a palavra, a palavra é desnecessária. Corta.
- Significado é sagrado, voz é sagrada. Toda ideia do original sobrevive. Se o autor tinha opinião, humor, raiva, hesitação, ironia, isso fica. A skill tira a camada de máquina, não a pessoa por baixo.
- Concreto vence genérico. Número, nome, data, lugar específico. "Uma cliente em Curitiba pagou R$ 3.200" vence "muitos clientes investem em tráfego pago".
- Anglo-saxão vence latino. "Usar" vence "utilizar". "Mostrar" vence "demonstrar". "Pra" vence "a fim de".
- Variação rítmica não é opcional. Frase curta. Frase longa que respira. Corte. O desvio padrão do tamanho das frases tem que passar de 6 palavras.
- Quebra de regra calculada delata humano. Começar frase com "E" ou "Mas". Fragmento sem verbo. Vírgula onde gramático puxaria orelha. Uma quebra deliberada por página assina humano.
- A voz do canal manda. WhatsApp não é página de vendas. Stories não é e-mail. Cada canal tem régua própria.
Quando usar
- Usuário cola texto e pede pra humanizar, tirar cara de IA, deixar natural
- Texto saiu de ChatGPT/Claude/Gemini e precisa virar pessoal
- Copy de venda, e-mail, post, legenda, página, artigo, qualquer prosa
- Mentorada da Tata gerou conteúdo com IA e precisa adaptar pra voz dela
- Texto pra publicar em canal específico (WhatsApp, Stories, e-mail, página)
Quando NÃO usar
- Texto já é humano e natural (passa pelos detectores). Roda só pra confirmar.
- Ficção criativa, poesia, letra de música (regras estilísticas próprias)
- Documento técnico/jurídico que exige formalidade (avisar usuário antes)
- Usuário quer manter o estilo de IA por algum motivo
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/copy-vendas-antes-depois.md 3.8 KB
- examples/email-antes-depois.md 4.1 KB
- examples/post-instagram-antes-depois.md 4.2 KB
- examples/whatsapp-antes-depois.md 3.3 KB
- reference/dialeto-tata.md 8.4 KB
- reference/frases-proibidas-ptbr.md 19 KB
- reference/padroes-estruturais-ptbr.md 17 KB
- reference/palavras-proibidas-ptbr.md 25 KB
- reference/principios-reescrita-ptbr.md 19 KB
- reference/regua-por-canal.md 11 KB
- scripts/comparar_textos.py 2.8 KB runs code
- scripts/detectar_ia_ptbr.py 29 KB runs code
- scripts/validar_humanizado.py 4.8 KB runs code
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.
- 9d ago First seen · 289 lines · 0 tokens per session scan A 8dc7f5223403
voz-humana-br is a skill published in the GitHub repository tatagoncalvesof/imperatriz-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 243 tokens to every session and 4,260 once invoked, about $0.0012 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
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
feature-dev
Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.