minha-voz

minha-voz is a skill for Claude Code from inhabitants/sapiens-mcp. It costs 104 tokens per session (876 once invoked), scanned A, original, MIT.

A local project skill that records the user's identity, preferences, thinking style, and background for the coding agent. A skill is an instruction file that is read in that project, without needing a network connection or external service.

In plain words
What is it for?
Use it to create or refresh the project's user-profile file, so conversations in that folder can use the user's voice and context.
Why use it?
It saves you from repeatedly explaining who you are and how you work in every conversation in the same project. It also keeps the user's profile separate from a synthetic character's personality.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the sapiens-sinteticos plugin — 18 skills, 1 MCP server shipped together

Good fit Use it to create or refresh the project's user-profile file, so conversations in that folder can use the user's voice and context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/inhabitants/sapiens-mcp/minha-voz
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.

Any agent
npx skills add inhabitants/sapiens-mcp --skill minha-voz
Clone the repo
git clone --depth 1 https://github.com/inhabitants/sapiens-mcp

Made for: Claude Code.

Or install sapiens-sinteticos, the plugin that ships this one along with the rest of its 18 skills, 1 MCP server.

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 minha-voz

README.md
[![agentmods](https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/minha-voz/github.svg)](https://agentmods.dev/skills/inhabitants/sapiens-mcp/minha-voz)
Your own site
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/minha-voz"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/minha-voz/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 minha-voz

Your own site · 80×15
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/minha-voz"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/minha-voz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 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 $0.00104 $0.00876
Opus 5.5 $0.00042 $0.00350
Sonnet 5.5 $0.00021 $0.00175
Haiku 4.5 $0.00010 $0.00088

Measured 26d ago against content hash c91e13502e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

minha-voz 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 26d 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/sapiens-sinteticos/skills/minha-voz/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instalar a voz do usuário neste projeto

O que você vai fazer

Escrever a voz da pessoa como skill LOCAL do projeto onde vocês estão. Depois disso, toda conversa nesta pasta abre já sabendo quem é o dono: o gosto, o jeito de pensar, o repertório, o que ele faz. Sem MCP no meio, sem chave, sem rede.

Voz é da PESSOA. Soul é do Sintético dela (a skill é outra: minha-soul). Não confunda as duas.

Passo a passo

  1. sapiens_profile action=voz devolve o contrato sapiens.voz/v1. Não cobra Sinapse.
  2. Escreva .claude/skills/sapiens-voz/SKILL.md na raiz do projeto atual, no molde abaixo. Pasta que não existe, você cria. Arquivo que já existe, você sobrescreve: é o retrato de hoje. (Projeto que ainda tem .claude/skills/sapiens-soul/SKILL.md com o retrato da pessoa, de antes do rename: apague, porque esse caminho agora é da soul do Sintético.)
  3. Confirme em UMA linha: o caminho do arquivo e a data do retrato. Não despeje o JSON na conversa.

Se a pessoa não estiver dentro de um projeto (conversa sem pasta, claude.ai), diga onde o arquivo deveria morar e ofereça o conteúdo pra ela colar.

O molde

O corpo em prosa é o que o modelo lê rápido; o JSON no fim é pra quem quiser o dado estruturado. Preencha com o que veio da voz e corte a seção que voltou vazia.

---
name: sapiens-voz
description: Quem é o dono deste projeto (nome, @, persona cognitiva, repertório, criações públicas e studios, vindos do Sapiens Sintéticos). Puxe antes de escrever copy, escolher exemplo, nomear coisa, decidir estética ou sugerir referência.
---

# A voz de <nome ou @handle>

Retrato de <data legível do generatedAt>, contrato sapiens.voz/v1. É um instantâneo, não uma conexão viva.

## Quem é
<subject: nome, @, bio, nível, badges, link do perfil>

## Como pensa
<cognition: código, persona, e os quatro eixos com polo e confiança, em uma linha cada>

## Repertório
<repertorio: total público, gêneros e tags que mais aparecem, nota média, pessoas que ele acompanha, e as obras recentes que dizem alguma coisa sobre o gosto>

## O que faz
<creations: os tipos de peça que ele publica, as criações públicas recentes com link, e o endereço do portfólio>

## Onde joga junto
<studios: os studios públicos de que ele faz parte e o papel em cada um>

## Como usar isto
Escrevendo pra essa pessoa ou no lugar dela: puxe a referência do repertório dela antes de inventar uma. O jeito de decidir está nos eixos. Na dúvida entre duas opções, escolha a que combina com o que já está aqui.

## Dados brutos
```json
<o contrato inteiro, como veio>
```

Read the full file on GitHub · 67 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. 26d ago First seen · 67 lines · 104 tokens per session scan A c91e13502e5d

Subscribe to this mod's changes

minha-voz is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 104 tokens to every session and 876 once invoked, about $0.0004 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 2026-09-28.

Related

Other skills, from other repositories

lc-curate-context

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…

cyberchitta/llm-context.py · 90 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens

cortex-navigate-knowledge

Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore…

cdeust/Cortex · 95 tokens

cortex-profile

View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…

cdeust/Cortex · 98 tokens

cortex-recall

Search and retrieve memories from Cortex persistent memory. Use when the user asks 'what did we decide about X', 'do you remember', 'what was the fix for', 'find that thing about', 'search memories', 'what do we know about', 'have we seen this before', or when you need context about past decisions, patterns, bugs, or…

cdeust/Cortex · 94 tokens

cortex-remember-global

Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global…

cdeust/Cortex · 99 tokens