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.
npx skills add gethouston/houston --skill investigar-un-temagit clone --depth 1 https://github.com/gethouston/houstonWrote 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.
[](https://agentmods.dev/skills/gethouston/houston/investigar-un-tema)<a href="https://agentmods.dev/skills/gethouston/houston/investigar-un-tema"><img src="https://agentmods.dev/badge/skills/gethouston/houston/investigar-un-tema/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.
<a href="https://agentmods.dev/skills/gethouston/houston/investigar-un-tema"><img src="https://agentmods.dev/badge/skills/gethouston/houston/investigar-un-tema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01555 |
| Opus 5 | $0.00032 | $0.00777 |
| Sonnet 5 | $0.00013 | $0.00311 |
| Haiku 4.5 | $0.00006 | $0.00155 |
Grade A, and why
investigar-un-tema 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigar Un Tema
Plantilla de origen: Gumloop "AI Research Agent with Automated Report Generation". Adaptada para entregar a los otros cuatro agentes de marketing, no para memorandos de inversionistas de 20 páginas.
Cuándo usarlo
- "investiga {tema}" / "necesito un informe sobre {tema}" / "cuál es el estado de {tema}".
- "resume qué está pasando en {categoría}".
- Se invoca implícitamente desde otras skills (
plan-a-campaign,watch-my-competitors,profile-my-customer) cuando encuentran un vacío de evidencia que necesita una corrida de investigación dedicada.
Conexiones que necesito
Hago el trabajo externo a través de Composio. Antes de correr esta skill reviso 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.
- Búsqueda web (Exa o Perplexity), el motor que encuentra y ordena las fuentes. Necesario, no hay un respaldo útil, necesito un índice de búsqueda para empezar.
- Extracción web (Firecrawl), opcional, trae el texto completo de forma limpia. Si no está conectado, uso una extracción HTTP básica de respaldo en cada URL de fuente, más tosca pero suficiente para sacar citas de páginas estáticas.
Si la búsqueda web no está conectada, me detengo. El respaldo de extracción me permite seguir por su cuenta.
Información que necesito
Primero leo tu contexto de marketing. Por cada campo requerido que falte, hago UNA pregunta en lenguaje sencillo (mejor modalidad: app conectada > archivo > URL > texto pegado) y espero.
- Tu posicionamiento, Necesario. Por qué lo necesito: un informe que no filtra por tu cliente ideal y tu categoría es solo investigación genérica de internet. Si falta, pregunto: "¿Quieres que primero redacte tu posicionamiento? Es una skill, toma unos cinco minutos."
- La pregunta de investigación, Necesario. Por qué la necesito: el alcance que se desborda vuelve inútiles los informes. Si falta, pregunto: "¿Cuál es la única pregunta que este informe debería responder, y qué decisión desbloquea?"
- Profundidad, Opcional, por defecto estándar. Si falta, pregunto: "¿Qué tan profundo quieres que vaya, un vistazo de quince minutos, una hora de inmersión, o una corrida profunda? Si no tienes preferencia, sigo con la profundidad estándar."
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.
- 13d ago First seen · 92 lines · 65 tokens per session scan A a92692463d5e
investigar-un-tema is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,555 once invoked, about $0.0003 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.
Other skills, from other repositories
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
attribution
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
analytics
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…