A project-context maintenance workflow that compares the workspace with its memory and instruction files. It checks whether files describing the company, strategy, preferences, brand, and project rules still match reality.

Use it to scan the workspace, review recent files and folders, compare them with context documents, and propose updates when the user says “atualiza” or “/atualizar”.

It helps prevent agents from relying on outdated information about the project, clients, priorities, or how files should be organized.

atualizar — Skill for Claude Code and Codex by felipenalves

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 felipenalves/InvOS --skill atualizar

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/felipenalves/invos/atualizar/github.svg)](https://agentmods.dev/skills/felipenalves/invos/atualizar)

Your own site

<a href="https://agentmods.dev/skills/felipenalves/invos/atualizar"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/atualizar/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/felipenalves/invos/atualizar"><img src="https://agentmods.dev/badge/skills/felipenalves/invos/atualizar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 666 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.

Model	Per session	Once invoked
Fable 5.1	$0.00088	$0.00666
Opus 5	$0.00044	$0.00333
Sonnet 5	$0.00018	$0.00133
Haiku 4.5	$0.00009	$0.00067

Measured 10d ago against content hash e3fd98685200, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

atualizar 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 10d 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/atualizar/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/atualizar — Varredura e atualização de contexto

Compara o que está nos arquivos de contexto com o estado real do workspace e propõe atualizações.

Workflow

Passo 1 — Levantamento

Listar:

Pastas na raiz (cada uma representa uma área de trabalho)
Subpastas em clientes/ (se existir) — cada uma é um cliente
Skills em .agents/skills/ — quais existem hoje (.claude/skills/ deve ser só symlink)
Arquivos recentes (últimos 30 dias) em pastas como propostas/, conteudo/, clientes/<x>/

Passo 2 — Comparação

Ler os arquivos de contexto e identificar:

Em _memoria/empresa.md: lista de clientes / serviços / ferramentas — bate com a realidade do workspace?
Em _memoria/estrategia.md: o foco atual ainda faz sentido (datas, prioridades)?
Em AGENTS.md: as regras de organização e a estrutura de pastas listada batem com o que existe?
Em CLAUDE.md: deve ser só @AGENTS.md (ponteiro). Se tiver regras de negócio, mover pra AGENTS.md.
Em marca/design-guide.md: continua coerente com o que foi gerado nas últimas peças (carrosséis, slides)?

Passo 3 — Proposta de mudanças

Apresentar pro usuário uma lista curta no formato:

Encontrei [N] coisas pra atualizar:

1. _memoria/empresa.md — falta o cliente "Acme" (vi pasta clientes/Acme/ criada em [data])
2. AGENTS.md — tem regra "propostas vão em propostas/" mas vejo propostas em clientes/<x>/propostas/
3. _memoria/estrategia.md — fala em "fechar 1º cliente em fevereiro", já é abril e tem 3 clientes ativos

Quer que eu aplique essas mudanças? Posso aplicar todas, escolher algumas, ou nenhuma.

Passo 4 — Aplicação

Se o usuário aprovar, editar os arquivos com cirurgia — só a linha relevante, sem reformatar o documento todo. Mostrar o diff de cada mudança aplicada.

Regras

Não inventar fatos — só registrar o que tem evidência no workspace
Se a evidência for ambígua (ex: pasta vazia chamada "Cliente Novo"), perguntar antes de adicionar
Não apagar conteúdo dos arquivos de contexto — só atualizar e adicionar
Se nenhuma mudança for necessária, responder "Tá tudo coerente, nada pra atualizar"

Read the full file on GitHub · 58 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.

10d ago First seen · 58 lines · 88 tokens per session scan A e3fd98685200

Subscribe to this mod's changes

atualizar is a skill published in the GitHub repository felipenalves/InvOS (5 stars, last pushed 7d ago), licensed MIT. It adds 88 tokens to every session and 666 once invoked, about $0.0004 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.

Memory and context agents ai-memory invos starter-kit

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.

vectorize-io/hindsight · 35 tokens

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.

vectorize-io/hindsight · 31 tokens

hindsight-docs

Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.

vectorize-io/hindsight · 30 tokens

hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).

vectorize-io/hindsight · 32 tokens

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…

vectorize-io/hindsight · 74 tokens

hindsight-recall

Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools.

vectorize-io/hindsight · 21 tokens