redactar-un-documento-de-personal

redactar-un-documento-de-personal is a skill for Claude Code, Codex from gethouston/houston. It costs 97 tokens per session (5,916 once invoked), scanned A, original, MIT.

A personnel document is a first draft for an employee-related situation, such as a job offer, onboarding plan, performance-improvement plan, or retention conversation script. It follows your company's pay ranges, levels, voice, and boundaries.

In plain words
What is it for?
Use it to draft offer letters, onboarding plans, performance-improvement plans, or scripts for one-to-one retention conversations.
Why use it?
Starting these documents from scratch takes time and can lead to inconsistent wording or missed internal rules. This gives you a structured draft while leaving the final decision and delivery to you.

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 draft offer letters, onboarding plans, performance-improvement plans, or scripts for one-to-one retention conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/redactar-un-documento-de-personal
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 redactar-un-documento-de-personal
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 redactar-un-documento-de-personal

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/redactar-un-documento-de-personal"><img src="https://agentmods.dev/badge/skills/gethouston/houston/redactar-un-documento-de-personal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,916 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 $0.00097 $0.05916
Opus 5 $0.00048 $0.02958
Sonnet 5 $0.00019 $0.01183
Haiku 4.5 $0.00010 $0.00592

Measured 9d ago against content hash 44def64a637a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

redactar-un-documento-de-personal 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/redactar-un-documento-de-personal/SKILL.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redactar un Documento de Personal

Una sola habilidad para todo primer borrador de documento de personal que el fundador necesite. El parámetro type elige la plantilla, la estructura y las validaciones. La disciplina de "solo borradores, nunca enviados / programados / entregados" se comparte entre todos.

Parámetro: type

  • offer-letter: carta de oferta para una nueva contratación en un nivel específico, anclada en las bandas salariales y la postura de equity.
  • onboarding-plan: plan de Día 0, Semana 1, 30-60-90 más un mensaje de bienvenida de Slack y un correo de bienvenida en tu voz.
  • pip: plan de mejora de desempeño. Verificación de escalamiento obligatoria primero. Si se activa un disparador de clase protegida más un tiempo sospechoso, DETENGO y escribo una nota de escalamiento en su lugar.
  • stay-conversation: GUION verbal para una 1:1, no un correo. Cinco secciones: Abrir → Escuchar → Mostrar → Preguntar → Proponer. Filtrado contra los límites innegociables.

El usuario nombra el tipo en lenguaje sencillo ("redacta una oferta para {candidate}", "planea el onboarding de {new hire}", "redacta un PIP para {employee}", "escribe el guion para la conversación de retención") → lo infiero. Si es ambiguo, hago UNA pregunta nombrando las cuatro opciones.

Cuándo usarla

  • type=offer-letter: "redacta una oferta para {candidate}", "escribe la carta de oferta", "carta de oferta para {candidate} en {level}". Requisito previo: existen el registro del candidato y el resumen, y el fundador decidió avanzar.
  • type=onboarding-plan: "redacta el plan de onboarding para {new hire}", "primeros 90 días para {new hire}", "{new hire} empieza {date}, prepáralo", "lista de la primera mañana para {new hire}", "Slack de bienvenida del Día 0 para {new hire}". Implícito: enrutado después de redactar-un-documento-de-personal type=offer-letter cuando se acepta la oferta.
  • type=pip: "redacta un PIP para {employee}", "plan de mejora de desempeño para {employee}", "{manager} marcó a {employee} por preocupaciones de desempeño". Siempre lo activas tú, nunca de forma implícita.
  • type=stay-conversation: "redacta una conversación de retención para {employee}", "{employee} podría irse", "alguien marcó ROJO, ¿qué digo?", "preparación para conversación de retención".

Read the full file on GitHub · 406 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 · 406 lines · 97 tokens per session scan A 44def64a637a

Subscribe to this mod's changes

redactar-un-documento-de-personal is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 5,916 once invoked, about $0.0005 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.