responder-una-pregunta-de-politica

responder-una-pregunta-de-politica is a skill for Claude Code, Codex from gethouston/houston. It costs 80 tokens per session (2,040 once invoked), scanned A, original, MIT.

A workplace-policy answer explains whether a company rule covers a person's question about benefits, leave, remote work, equipment, or reimbursements. When the written policy is unclear, it produces an escalation note instead of guessing.

In plain words
What is it for?
Use it to answer recurring employee questions, create reusable reply templates, and flag policy questions that need escalation.
Why use it?
Employees need consistent answers, but policy documents may not cover every situation. This helps separate clear answers from cases that need human review.

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 Use it to answer recurring employee questions, create reusable reply templates, and flag policy questions that need escalation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/responder-una-pregunta-de-politica
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 responder-una-pregunta-de-politica
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 responder-una-pregunta-de-politica

README.md
[![agentmods](https://agentmods.dev/badge/skills/gethouston/houston/responder-una-pregunta-de-politica/github.svg)](https://agentmods.dev/skills/gethouston/houston/responder-una-pregunta-de-politica)
Your own site
<a href="https://agentmods.dev/skills/gethouston/houston/responder-una-pregunta-de-politica"><img src="https://agentmods.dev/badge/skills/gethouston/houston/responder-una-pregunta-de-politica/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 responder-una-pregunta-de-politica

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/responder-una-pregunta-de-politica"><img src="https://agentmods.dev/badge/skills/gethouston/houston/responder-una-pregunta-de-politica.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,040 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 $0.00080 $0.02040
Opus 5 $0.00040 $0.01020
Sonnet 5 $0.00016 $0.00408
Haiku 4.5 $0.00008 $0.00204

Measured 9d ago against content hash a29a8d97e88d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

responder-una-pregunta-de-politica 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/es/people/.agents/skills/responder-una-pregunta-de-politica/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Responder una Pregunta de Política

Cuándo usarla

  • Explícito: "¿{employee} califica para {PTO / licencia / parental / duelo / remoto}", "¿puede {employee} reembolsar {X}", "cuál es nuestra política sobre {topic}", "¿esto está cubierto?".
  • Variante de plantilla: "redacta la respuesta de PTO (o {topic}) como plantilla", "dame variantes reutilizables para preguntas de {policy}", produce las tres rutas de respuesta (directa / ambigua / escalamiento) para el tema indicado y guárdalas en approvals/{topic}-reply-template.md para reutilizar.
  • Implícito: enrutado desde el vigilante del canal de soporte (escucha de Slack, filtro de Gmail) cuando un integrante del equipo hace una pregunta de Recursos Humanos.
  • Frecuencia: tan seguido como el equipo pregunte. El clasificador corre cada vez.

Conexiones que necesito

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

  • Documentos (Google Docs, Notion): leer el manual o el documento de política cuando vive fuera de este agente. Opcional.
  • Bandeja de entrada (Gmail): igualar tu voz al responder. Opcional.
  • Chat (Slack): responder donde llegó la pregunta. Opcional.

Esta habilidad nunca envía nada sin tu aprobación, así que ninguna integración es estrictamente obligatoria, pero un manual conectado me evita hacerte preguntas que ya respondiste antes.

Información que necesito

Primero leo tu contexto de personal. Por cada campo obligatorio que falte, hago UNA pregunta en lenguaje sencillo (mejor modalidad: app conectada > archivo > URL > texto pegado) y espero.

  • La pregunta que se está haciendo: Obligatorio. Por qué la necesito: clasifico y respondo la solicitud específica. Si falta, pregunto: "¿Cuál es la pregunta, y quién la está haciendo?"
  • Canon de políticas: Obligatorio. Por qué lo necesito: toda respuesta directa cita la política relevante. Si falta, pregunto: "Comparte tu manual actual o un enlace a él, o corre primero configurar-mi-informacion-de-personal para capturar las políticas."
  • Reglas de escalamiento: Obligatorio. Por qué las necesito: nunca redacto respuestas sobre discriminación, acoso, salarios o preguntas de visa, esas las enruto. Si faltan, pregunto: "¿A quién se enrutan las preguntas de discriminación, acoso, disputas salariales y visas? ¿Hay un abogado designado, o lo marcamos como pendiente hasta que tengas uno?"
  • Jurisdicción: Opcional. Por qué la necesito: las respuestas sobre licencias y beneficios varían por estado y país. Si no la tienes, sigo adelante marcándola como pendiente y señalo los vacíos jurisdiccionales en el borrador.

Read the full file on GitHub · 151 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 · 151 lines · 80 tokens per session scan A a29a8d97e88d

Subscribe to this mod's changes

responder-una-pregunta-de-politica is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,040 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 2026-09-03.