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-una-cuentagit 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-una-cuenta)<a href="https://agentmods.dev/skills/gethouston/houston/investigar-una-cuenta"><img src="https://agentmods.dev/badge/skills/gethouston/houston/investigar-una-cuenta/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-una-cuenta"><img src="https://agentmods.dev/badge/skills/gethouston/houston/investigar-una-cuenta.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 | $0.00095 | $0.02129 |
| Opus 5 | $0.00048 | $0.01064 |
| Sonnet 5 | $0.00019 | $0.00426 |
| Haiku 4.5 | $0.00010 | $0.00213 |
Grade A, and why
investigar-una-cuenta 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigar una cuenta
Una sola skill, cuatro formatos de investigación. El parámetro depth define el recorrido. Comparten la disciplina de citar fuentes y "nunca inventar un hecho".
Parámetro: depth
quick-qualify: lectura de 30 segundos de una sola URL. Un rastreo, una decisión (GOOD-FIT / BORDER / OUT), un ángulo si es GOOD-FIT. Triaje rápido, no un informe.full-brief: informe citado de varias pasadas sobre una cuenta con nombre: rastreo del sitio, noticias recientes (12 semanas), detección de stack tecnológico, escaneo de redes sociales, señales de intención. Alimenta la prospección y la preparación de llamadas.enrich-contact: persona con nombre: firmográficos, contexto del rol, línea jerárquica si es identificable, publicaciones o charlas recientes, señales disparadoras. Para personalizar la prospección.warm-paths: presentaciones de primer grado: busco en LinkedIn, Gmail o CRM conectados a personas que conozcan a alguien en la cuenta objetivo. Clasifico los caminos por fuerza.
Si el pedido del usuario implica la profundidad ("lectura rápida", "profundiza", "enriquece a esta persona", "a quién conozco ahí"), la infiero. Si no, hago UNA pregunta que nombre las 4 opciones.
Cuándo usarla
- Disparadores explícitos en la descripción.
- Implícito: dentro de
write-my-outreach stage=cold-email(el correo en frío necesita una señal, esta skill la encuentra) yprep-a-meeting type=call(la llamada necesita un informe).
Conexiones que necesito
Todo el trabajo externo lo hago a través de Composio. Antes de ejecutar esta skill, verifico que las categorías de abajo estén conectadas. Si falta alguna, digo cuál es, te pido que la conectes desde la pestaña de Integraciones, y me detengo.
- Rastreo: leo el sitio de la empresa, sus páginas de producto, señales de stack tecnológico. Obligatorio para
quick-qualifyyfull-brief. - Búsqueda / investigación: obtengo noticias recientes, rondas de inversión, contrataciones para
full-briefyenrich-contact. Obligatorio para esas profundidades. - Redes sociales: leo el perfil público de LinkedIn y sus publicaciones para
enrich-contactywarm-paths. Obligatorio para esas profundidades. - CRM: cruzo conexiones de primer grado y contactos previos para
warm-paths. Obligatorio para esa profundidad. - Bandeja de entrada: cruzo con quién te has escrito por correo en la cuenta objetivo para
warm-paths. Opcional.
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.
- 9d ago First seen · 109 lines · 95 tokens per session scan A 02b17ed11cd6
investigar-una-cuenta is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,129 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…