redactar-un-mensaje

redactar-un-mensaje is a skill for Claude Code, Codex from gethouston/houston. It costs 95 tokens per session (2,128 once invoked), scanned A, original, MIT.

A message-drafting tool that writes replies, follow-ups, and supplier emails in your tone and saves them as drafts. It leaves sending and any commitments to you.

In plain words
What is it for?
It is for drafting replies to incoming email, following up on promises, and writing messages about supplier renewals, cancellations, trials, or reference checks.
Why use it?
It reduces the effort of writing routine outbound messages while keeping you in control of what gets sent. It can also track follow-up commitments and deadlines.

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 is for drafting replies to incoming email, following up on promises, and writing messages about supplier renewals, cancellations, trials, or reference checks.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/redactar-un-mensaje"><img src="https://agentmods.dev/badge/skills/gethouston/houston/redactar-un-mensaje.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,128 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 $0.00095 $0.02128
Opus 5 $0.00048 $0.01064
Sonnet 5 $0.00019 $0.00426
Haiku 4.5 $0.00010 $0.00213

Measured 9d ago against content hash 0f44353e2421, 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-mensaje 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/operations/.agents/skills/redactar-un-mensaje/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redactar un mensaje

Una sola primitiva de redacción para todo lo saliente. Tu tono, tu aprobación, tu botón de enviar; nunca envío, nunca me comprometo, nunca firmo.

Cuándo usarla

  • type=reply - "redacta respuestas" / "responde a {name}" / "redacta respuestas a los correos entrantes de mi triage".
  • type=followup - "haz seguimiento a este compromiso" (submodo TRACK) / "recuérdame hacer seguimiento con {X}" (TRACK) / "encárgate de mis seguimientos que vencen" (HANDLE).
  • type=vendor - "redacta un correo de negociación de renovación" / "escribe el correo de cancelación para {SaaS}" / "contacta a {supplier} para una prueba" / "correo de verificación de referencias para {vendor}".

Conexiones que necesito

Ejecuto todo el trabajo externo a través de Composio. Antes de ejecutar esta skill verifico que las categorías de abajo estén vinculadas. Si falta alguna → nombro la categoría, te pido conectarla desde la pestaña de Integraciones y me detengo.

  • Bandeja de entrada (Gmail, Outlook) - Requerido. Extrae el hilo al que respondo, muestrea tu tono y guarda el borrador de vuelta en tu bandeja para que lo revises y envíes.
  • Archivos (Google Drive) - Opcional. Me permite leer contratos de proveedores al redactar correos de renovación o cancelación.

Si no hay bandeja de entrada conectada, me detengo y te pido conectarla primero.

Información que necesito

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

  • Tu tono - Requerido. Por qué lo necesito: las respuestas suenan como tú y no como una plantilla. Si falta, pregunto: "La mejor manera es conectar tu bandeja de entrada para que pueda muestrear 20 a 30 mensajes enviados. Si no, pega 3 a 5 respuestas recientes que hayas escrito y trabajaré a partir de esas."
  • Documento de contexto operativo - Requerido. Por qué lo necesito: ancla las prioridades y los contactos clave para que las respuestas se mantengan alineadas con tu mensaje. Si falta, pregunto: "¿Quieres que configure primero tu contexto operativo? Las respuestas mejoran mucho una vez que lo tengo."
  • VIPs - Opcional. Por qué los necesito: definen el tono y el nivel de deferencia. Si no los tienes, sigo adelante con TBD y trato a todos por igual.
  • Postura con proveedores - Requerido para type=vendor. Por qué la necesito: guía las peticiones de renovación y el lenguaje para retirarse de la negociación. Si falta, pregunto: "¿Cómo abordas las conversaciones con proveedores: presionas fuerte por los términos o lo mantienes ligero? ¿Quién puede firmar?"

Read the full file on GitHub · 98 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 · 98 lines · 95 tokens per session scan A 0f44353e2421

Subscribe to this mod's changes

redactar-un-mensaje is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 2,128 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.

Related

Other skills, from other repositories