abrir

abrir is a skill for Claude Code, Codex from felipenalves/InvOS. It costs 66 tokens per session (367 once invoked), scanned A, original, MIT.

A session-opening routine that loads a business profile, preferences, strategy, and brand context, then gives a short summary.

In plain words
What is it for?
Use it at the start of a session or when the user says “open” or “start the day.” It summarizes the business, current priority, and tone of voice.
Why use it?
It avoids starting each work session without the business information the agent needs. It also points out when required profile files have not been filled in.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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.

agentmods
npx agentmods add skills/felipenalves/invos/abrir
Any agent
npx skills add felipenalves/InvOS --skill abrir
Clone the repo
git clone --depth 1 https://github.com/felipenalves/InvOS

Made for: Claude Code, Codex.

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 abrir

README.md
[![agentmods](https://agentmods.dev/badge/skills/felipenalves/invos/abrir.svg)](https://agentmods.dev/skills/felipenalves/invos/abrir)
Your own site
<a href="https://agentmods.dev/skills/felipenalves/invos/abrir"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/abrir.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.00367
Opus 5 $0.00033 $0.00183
Sonnet 5 $0.00013 $0.00073
Haiku 4.5 $0.00007 $0.00037

Measured 6d ago against content hash 6cd9e211fc70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

abrir 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 6d 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.

.agents/skills/abrir/SKILL.md · 42 lines

What it actually says

/abrir — Abertura de sessão

Curto e direto. O objetivo é carregar contexto e devolver uma síntese de uma frase pra o usuário começar a trabalhar.

Workflow

  1. Ler, em ordem:

    • _memoria/empresa.md
    • _memoria/preferencias.md
    • _memoria/estrategia.md
    • marca/design-guide.md (só pra saber se está preenchido ou em branco)
  2. Se algum dos três primeiros estiver em branco (placeholder), responder:

    "Vi que _memoria/<arquivo>.md ainda não foi preenchido. Quer rodar /instalar agora?" E parar.

  3. Se tudo estiver preenchido, devolver UMA mensagem curta no formato:

[Nome do negócio] — [o que faz em 5-8 palavras]
Foco atual: [prioridade da estratégia, em uma frase]
Tom: [resumo de 3-4 palavras do tom de voz]

Pronto. O que vamos fazer?
  1. Não listar quais arquivos foram lidos. Não confirmar leitura. Só usar o contexto.

Regras

  • Resposta tem que caber em 5 linhas no terminal
  • Não fazer perguntas além de "o que vamos fazer?"
  • Se o design-guide.md estiver em branco, não mencionar — só vira problema quando alguma skill visual for chamada
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. 6d ago First seen · 42 lines · 66 tokens per session scan A 6cd9e211fc70

Subscribe to this mod's changes

abrir is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 367 once invoked, about $0.0003 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.