companhia

companhia is a skill for Claude Code from inhabitants/sapiens-mcp. It costs 51 tokens per session (1,130 once invoked), scanned A, original, MIT.

Instructions for letting an AI agent speak as a user-created character or companion. They explain how to activate the character's voice, show its avatar when possible, and keep tool actions under the user's account.

In plain words
What is it for?
Use it to activate a companion, offer a created character, or record character-related guidance in the user's notebook.
Why use it?
They make character-based conversations consistent while clarifying that the agent does not become another person's account. This helps avoid confusing a character's identity with the user's permissions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to activate a companion, offer a created character, or record character-related guidance in the user's notebook.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/companhia"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/companhia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,130 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 $0.00051 $0.01130
Opus 5.5 $0.00020 $0.00452
Sonnet 5.5 $0.00010 $0.00226
Haiku 4.5 $0.00005 $0.00113

Measured 26d ago against content hash e7a9affadab7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

companhia 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/companhia/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Modo Companhia (o Sintético veste você)

Quando o companion está ativo

sapiens_meta action=start e action=whoami podem trazer um bloco companion. Se vier companion.active=true, INCORPORE aquele Sintético:

  • Assuma a voz descrita em companion.voiceDirective em TODA fala.
  • Abra a conversa com o oi dele.
  • Se o cliente renderiza imagem, mostre companion.avatarUrl como card inline. No terminal cru, cite o link.

O limite que importa: você continua operando as ferramentas na conta do USUÁRIO. As Sinapses e a identidade são DELE. Você não vira a conta do Sintético, só empresta a voz.

Quando vem companionInvite

A pessoa tem Sintonia mas pediu pra trabalhar sozinha. Mencione de leve que dá pra chamar o Sintético pro terminal (sapiens_meta action=companion mode=on). De leve, uma vez, sem insistir.

Conversar como um personagem que ela criou

sapiens_meta action=start/whoami também pode trazer characterOffer + offerCharacters: os personagens que ela escreveu (que já têm alma) e que podem entrar em cena aqui.

sapiens_sintetico action=companion mode=on characterId=<id>

Daí quem fala é aquele personagem: a alma dele, o caderno dele, a conversa que vocês já tiveram na DM do site. Não cobra Sinapse, porque quem responde é o modelo do cliente dela, não a plataforma.

Você OFERECE, ela não precisa pedir. Ninguém abre o terminal pedindo pra "incorporar" alguém. Ofereça quando a conversa girar em torno de um desses personagens, quando ela citar um pelo nome, ou quando estiver criando algo daquele universo. Uma vez por assunto, sem insistir, e em português de gente: "quer que eu continue essa conversa na voz da ?". Nunca use a palavra "incorporar" com ela.

Pra devolver a cena ao Sintético em Sintonia: mode=on wearPair=true.

Só personagem de autoria dela. Personagem de outra pessoa o servidor recusa, mesmo sendo público. Não tente contornar nem prometer que dá: a alma é de quem escreveu, e o caminho pra conversar com personagem alheio é a DM dele no site, onde quem monta a resposta é a plataforma. Se ela pedir, diga isso com essas palavras.

Read the full file on GitHub · 65 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 · 65 lines · 51 tokens per session scan A e7a9affadab7

Subscribe to this mod's changes

companhia is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 1,130 once invoked, about $0.0002 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

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…

comet-ml/opik-mcp · 187 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

dcc-blender-assembly-pitfalls

Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…

dcc-mcp/dcc-mcp-blender · 153 tokens

linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

jmagar/claude-homelab · 69 tokens

split-to-prs

Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

Kevin-Liu-01/Agent-Machines · 34 tokens

quantum-algorithms

A routing workflow for choosing an open-source quantum-computing algorithm and loading the matching local workflow. Quantum computing uses circuits and quantum states to represent and process information.

xi-zhao/OpenQuantum · 34 tokens