auditar-meus-livros

auditar-meus-livros is a skill for Claude Code, Codex from gethouston/houston. It costs 144 tokens per session (2,301 once invoked), scanned A, original, MIT.

An accounting-health audit skill that checks bookkeeping records for uncategorised items, reconciliation differences, overdue accruals, duplicate vendors, and other open issues. It can also prepare draft responses to audit or due-diligence requests.

In plain words
What is it for?
It helps check whether the books are ready, identify missing or duplicated records, prepare audit samples, and guide an auditor through accounting questions.
Why use it?
It gives you a prioritised list of bookkeeping problems without posting entries or submitting anything. Findings are ranked by financial impact so the most useful fix is clear.

Skill for Claude CodeCodex

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

Good fit It helps check whether the books are ready, identify missing or duplicated records, prepare audit samples, and guide an auditor through accounting questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/auditar-meus-livros
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 auditar-meus-livros
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 auditar-meus-livros

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/auditar-meus-livros"><img src="https://agentmods.dev/badge/skills/gethouston/houston/auditar-meus-livros.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,301 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 $0.00144 $0.02301
Opus 5 $0.00072 $0.01151
Sonnet 5 $0.00029 $0.00460
Haiku 4.5 $0.00014 $0.00230

Measured 9d ago against content hash ce72eefed4f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

auditar-meus-livros 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/auditar-meus-livros/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditar meus livros

Verificação de saúde para saber se os livros estão em ordem. Eu percorro todo índice plano na raiz e todo registro vivo, classifico os achados pelo impacto em dólares, e aponto a única coisa mais útil para resolver esta semana. O submodo mode=audit-response cuida de solicitações de auditor ou de diligência prévia com sementes aleatórias documentadas. Somente rascunhos, nunca lançado, nunca apresentado.

Quando usar

  • "os livros estão em ordem" / "o que está sem categorizar" / "verificação de saúde dos livros" / "lista de pendências".
  • Chamado por hand-off-to-my-tax-preparer como etapa de bloqueio, os itens em aberto precisam ser resolvidos antes que a entrega prossiga.
  • mode=audit-response, "responda a esta solicitação de auditoria" / "a diligência quer amostras do segundo trimestre" / "guie o auditor pelo reconhecimento de receita".

Conexões que preciso

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

  • Nenhuma conexão externa é necessária. Eu trabalho inteiramente a partir dos seus livros existentes, arquivos de conciliação, provisões e lançamentos contábeis. Para mode=audit-response, se você quiser que eu espelhe o pacote de documentos em uma pasta compartilhada, conecte o Google Drive (opcional).

Esta habilidade nunca fica bloqueada por falta de conexão. Os pacotes de documentos usam pastas locais por padrão, o espelho no Drive é um extra bem-vindo.

Informações que preciso

Eu leio primeiro o seu contexto contábil. Para cada campo obrigatório que estiver faltando, faço UMA pergunta em linguagem simples (melhor modalidade: aplicativo conectado > envio de arquivo > URL > colar) e espero.

  • Um contexto contábil finalizado e um plano de contas - Obrigatório. Por quê: eu ancoro a varredura no seu método contábil, código de suspenso e contas registradas. Se estiver faltando, pergunto: "Já configuramos os livros? Se não, rode a configuração uma vez para que eu saiba seu ano fiscal, método contábil e contas registradas antes de procurar problemas."
  • Um histórico de execução atual - Obrigatório. Por quê: preciso de pelo menos um período categorizado para comparar. Se estiver faltando, pergunto: "Você já processou algum extrato? Envie seus extratos bancários ou de cartão de crédito mais recentes e eu trabalho a partir daí."
  • Sua solicitação de auditor ou de diligência prévia, no mode=audit-response - Obrigatório para esse modo. Por quê: eu não consigo amostrar nem montar sem o pedido de fato. Se estiver faltando, pergunto: "Cole ou envie a solicitação do auditor ou da equipe de diligência, idealmente o e-mail completo ou o PDF com os itens que eles querem."

Read the full file on GitHub · 91 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 · 91 lines · 144 tokens per session scan A ce72eefed4f3

Subscribe to this mod's changes

auditar-meus-livros is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 2,301 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

expense-review-policy

Review invoices and contracts against accounts-payable policy before human approval.

openai/openai-cookbook · 17 tokens

kyc-doc-parse

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

anthropics/financial-services · 49 tokens

audit-support

Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.

anthropics/knowledge-work-plugins · 45 tokens

fiscaliste

Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…

romainsimon/paperasse · 302 tokens

regulatory-analysis

Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.

open-gitagent/opengap · 59 tokens

subcontractor-payment-tracker

Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 25 tokens