processar-meus-extratos

processar-meus-extratos is a skill for Claude Code, Codex from gethouston/houston. It costs 151 tokens per session (9,671 once invoked), scanned A, original, MIT.

A bank- and credit-card-statement processor that extracts transactions from PDF or CSV files, standardizes counterparty names, categorizes them, identifies transfers, and builds a formula-based profit-and-loss spreadsheet.

In plain words
What is it for?
Use it to process statement batches, prepare a spreadsheet for your accountant, categorize transactions, and review reconciliation warnings.
Why use it?
It turns messy statement files into reviewed accounting data without inventing amounts or account codes, and places unresolved items where they can be checked.

Skill for Claude CodeCodex

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

Good fit Use it to process statement batches, prepare a spreadsheet for your accountant, categorize transactions, and review reconciliation warnings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/processar-meus-extratos
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 gethouston/houston --skill processar-meus-extratos
Clone the repo
git clone --depth 1 https://github.com/gethouston/houston

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 processar-meus-extratos

README.md
[![agentmods](https://agentmods.dev/badge/skills/gethouston/houston/processar-meus-extratos/github.svg)](https://agentmods.dev/skills/gethouston/houston/processar-meus-extratos)
Your own site
<a href="https://agentmods.dev/skills/gethouston/houston/processar-meus-extratos"><img src="https://agentmods.dev/badge/skills/gethouston/houston/processar-meus-extratos/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 processar-meus-extratos

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/processar-meus-extratos"><img src="https://agentmods.dev/badge/skills/gethouston/houston/processar-meus-extratos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,671 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00151 $0.09671
Opus 5 $0.00076 $0.04836
Sonnet 5 $0.00030 $0.01934
Haiku 4.5 $0.00015 $0.00967

Measured 9d ago against content hash d7828aec4927, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

processar-meus-extratos 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 9d 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.

store/agents-i18n/pt/bookkeeping/.agents/skills/processar-meus-extratos/SKILL.md · 626 lines

How it starts

The opening of the file, as written. The whole thing — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Processar Meus Extratos

Envie um lote de extratos bancários e de cartão de crédito em PDF ou CSV e eu produzo uma planilha revisada do Google Sheets com uma DRE baseada em fórmulas. Pipeline completo: extraio cada transação em paralelo, normalizo as contrapartes, categorizo contra o seu plano de contas travado, marco as transferências entre contas, e escrevo uma planilha que você pode entregar ao seu contador. O grupo de Suspenso e os avisos de conciliação ficam no topo, eu nunca insiro um número, nunca invento um código de conta, nunca lanço nada.

Alvo de Saída: Google Sheets via Composio

Uso a CLI do Composio disponível no PATH. Todas as gravações no Google Sheets passam por ela.

Antes de qualquer execução, verifico se o toolkit googlesheets está conectado:

composio execute GOOGLESHEETS_SEARCH_SPREADSHEETS -d '{"query": "", "max_results": 1}'

Se retornar "No active connection found for toolkit \"googlesheets\"", PARO e peço para você conectar:

composio link googlesheets --no-wait

Pego o redirect_url da resposta, apresento a você como um link em markdown com #houston_toolkit=googlesheets anexado (para o Houston renderizar o cartão de conexão). Espero a aprovação antes de continuar.

Conexões que eu preciso

Eu executo trabalho externo pelo Composio. Antes desta skill rodar, verifico se as categorias abaixo estão vinculadas. Se faltar, nomeio a categoria, peço para você conectar na aba Integrações, e paro.

  • Google Sheets (planilhas), obrigatório. Todo o pipeline termina em uma planilha do Google Sheets com uma DRE baseada em fórmulas, sem ela não há saída. Veja o bloco "Alvo de Saída: Google Sheets via Composio" acima para o comando de verificação e o link de conexão.
  • Stripe (cobrança), opcional. Traz repasses e taxas de processamento para que categorizem corretamente quando aparecerem no seu feed bancário.

Se o Google Sheets não estiver conectado, eu paro e peço para você conectá-lo antes de fazer qualquer trabalho.

Read the full file on GitHub · 626 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. 9d ago First seen · 626 lines · 151 tokens per session scan A d7828aec4927

Subscribe to this mod's changes

processar-meus-extratos is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 151 tokens to every session and 9,671 once invoked, about $0.0008 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 2026-09-03.