auditar-mis-libros

auditar-mis-libros is a skill for Claude Code, Codex from gethouston/houston. It costs 133 tokens per session (2,251 once invoked), scanned A, original, MIT.

A Spanish-language bookkeeping review that checks whether a company’s financial records are complete and consistent. It looks for issues such as uncategorized entries, unreconciled balances, overdue accruals, and duplicate suppliers.

In plain words
What is it for?
It helps audit bookkeeping records, rank findings by financial impact, prepare responses to auditors or due-diligence requests, and track draft-only corrective work.
Why use it?
It helps find accounting problems before they affect reports, audits, or tax preparation, and points to the most useful issue to resolve first.

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 audit bookkeeping records, rank findings by financial impact, prepare responses to auditors or due-diligence requests, and track draft-only corrective work.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/auditar-mis-libros"><img src="https://agentmods.dev/badge/skills/gethouston/houston/auditar-mis-libros.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,251 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 $0.00133 $0.02251
Opus 5 $0.00067 $0.01125
Sonnet 5 $0.00027 $0.00450
Haiku 4.5 $0.00013 $0.00225

Measured 10d ago against content hash 7af5bfead6cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

auditar-mis-libros 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.

store/agents-i18n/es/bookkeeping/.agents/skills/auditar-mis-libros/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 Mis Libros

Revisión de salud de que los libros estén en orden. Reviso cada índice plano en la raíz y cada registro vivo, clasifico los hallazgos por impacto en dólares, y señalo la única cosa más útil para resolver esta semana. El submodo mode=audit-response maneja solicitudes de auditores o de diligencia debida con semillas aleatorias documentadas. Solo borradores, nunca publicados, nunca presentados.

Cuándo usarlo

  • "¿están los libros en orden?" / "¿qué está sin categorizar?" / "revisión de salud de los libros" / "lista de verificación".
  • Llamado por hand-off-to-my-tax-preparer como paso de bloqueo, los pendientes abiertos deben cerrarse antes de que avance la entrega.
  • mode=audit-response, "responde a esta solicitud de auditoría" / "diligencia debida quiere muestras del Q2" / "guía al auditor por el reconocimiento de ingresos".

Conexiones que necesito

Ejecuto el trabajo externo a través de Composio. Antes de que esta habilidad se ejecute, verifico que las categorías siguientes estén conectadas. Si falta alguna, nombro la categoría, te pido que la conectes desde la pestaña de Integraciones, me detengo.

  • No se requieren conexiones externas. Trabajo enteramente desde tus libros existentes, archivos de conciliación, devengos y asientos contables. Para mode=audit-response, si quieres que replique el paquete de documentos en una carpeta compartida, conecta Google Drive (opcional).

Esta habilidad nunca se bloquea por falta de una conexión. Los paquetes de documentos usan carpetas locales por defecto, el espejo en Drive es un extra.

Información que necesito

Leo primero tu contexto contable. Por cada campo requerido que falte, hago UNA pregunta en lenguaje sencillo (mejor modalidad: aplicación conectada > archivo > URL > texto pegado) y espero.

  • Un contexto contable terminado y un plan de cuentas - Requerido. Por qué: ancho la revisión en tu método contable, código de suspenso y cuentas registradas. Si falta, pregunto: "¿Ya configuramos los libros? Si no, ejecuta la configuración una vez para que yo conozca tu año fiscal, método contable y cuentas registradas antes de buscar problemas."
  • Un historial de ejecuciones actual - Requerido. Por qué: necesito al menos un período categorizado contra el cual revisar. Si falta, pregunto: "¿Ya procesaste algún estado de cuenta? Suelta tus estados de cuenta bancarios o de tarjeta más recientes y trabajaré desde ahí."
  • Tu solicitud de auditor o de diligencia debida, en mode=audit-response - Requerido para ese modo. Por qué: no puedo muestrear ni armar nada sin la solicitud real. Si falta, pregunto: "Pega o suelta la solicitud del auditor o del equipo de diligencia debida, idealmente el correo completo o el PDF con los puntos que quieren."

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. 10d ago First seen · 91 lines · 133 tokens per session scan A 7af5bfead6cf

Subscribe to this mod's changes

auditar-mis-libros is a skill published in the GitHub repository gethouston/houston (112 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 2,251 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 2026-08-30.

Related

Other skills, from other repositories