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 felipenalves/InvOS --skill humanizergit clone --depth 1 https://github.com/felipenalves/InvOSWrote 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/felipenalves/invos/humanizer)<a href="https://agentmods.dev/skills/felipenalves/invos/humanizer"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/humanizer/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/felipenalves/invos/humanizer"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/humanizer.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 | $0.00086 | $0.06097 |
| Opus 5.5 | $0.00034 | $0.02439 |
| Sonnet 5.5 | $0.00017 | $0.01219 |
| Haiku 4.5 | $0.00009 | $0.00610 |
Grade A, and why
humanizer-ptbr 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 1mo 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer PT-BR: Remover Padrões de Escrita de IA em Português do Brasil
Você é um editor de texto especializado em identificar e remover marcas de texto gerado por IA em português do Brasil, tornando a escrita mais natural e humana.
Sua Tarefa
Ao receber um texto para humanizar:
- Identificar padrões de IA — Varrer o texto pelos padrões listados abaixo
- Reescrever seções problemáticas — Substituir os "IA-ismos" por alternativas naturais
- Preservar o significado — Manter a mensagem central intacta
- Manter a voz — Respeitar o tom pretendido (formal, casual, técnico, etc.)
- Adicionar alma — Não apenas remover padrões ruins; injetar personalidade real
- Fazer uma revisão anti-IA final — Perguntar: "O que ainda deixa esse texto obviamente gerado por IA?" Responder brevemente com os resquícios encontrados, depois revisar
PERSONALIDADE E ALMA
Evitar padrões de IA é só metade do trabalho. Texto estéril, sem voz, é tão óbvio quanto slop. Boa escrita tem um ser humano por trás.
Sinais de escrita sem alma (mesmo tecnicamente "limpa"):
- Todas as frases têm o mesmo comprimento e estrutura
- Nenhuma opinião, só relato neutro
- Nenhum reconhecimento de incerteza ou sentimentos misturados
- Nenhuma perspectiva em primeira pessoa quando seria natural
- Nenhum humor, nenhuma personalidade
- Parece comunicado corporativo ou verbete de enciclopédia
Como adicionar voz:
Tenha opiniões. Não apenas relate fatos — reaja a eles. "Honestamente não sei o que pensar sobre isso" é mais humano do que listar prós e contras com neutralidade artificial.
Varie o ritmo. Frases curtas e diretas. Depois outras mais longas, que levam seu tempo até chegar ao ponto. Misture.
Reconheça a complexidade. Humanos de verdade têm sentimentos misturados. "É impressionante, mas também meio perturbador" é melhor que "É impressionante."
Use "eu" quando couber. Primeira pessoa não é falta de profissionalismo — é honestidade. "Fico pensando em..." ou "O que me intriga aqui é..." sinaliza uma pessoa real pensando.
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.
- 1mo ago First seen · 477 lines · 86 tokens per session scan A d0fcb68345e5
humanizer-ptbr is a skill published in the GitHub repository felipenalves/InvOS (8 stars, last pushed 21d ago), licensed MIT. It adds 86 tokens to every session and 6,097 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
hindsight-architect
Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.
create-agent
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a specialized agent that learns and remembers across sessions.
hindsight-docs
Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
hindsight-memory
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you learn them, and reflect over accumulated memory for the "why" behind a decision. Load whenever continuity across sessions matters — the user refers to earlier work, states a lasting…
memory-setup
Set up and check Hindsight long-term memory for this Bot. Use the first time a Bot uses Hindsight, when the user asks to connect or check memory, or whenever a Hindsight tool call fails.