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 buscar-un-clientegit 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/buscar-un-cliente)<a href="https://agentmods.dev/skills/gethouston/houston/buscar-un-cliente"><img src="https://agentmods.dev/badge/skills/gethouston/houston/buscar-un-cliente/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/buscar-un-cliente"><img src="https://agentmods.dev/badge/skills/gethouston/houston/buscar-un-cliente.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 | $0.00092 | $0.01681 |
| Opus 5 | $0.00046 | $0.00840 |
| Sonnet 5 | $0.00018 | $0.00336 |
| Haiku 4.5 | $0.00009 | $0.00168 |
Grade A, and why
buscar-un-cliente 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buscar un cliente
Una sola skill para cualquier necesidad de soporte de tipo "cuéntame sobre este cliente". Se ramifica según view.
Cuándo usarla
- dossier - "¿quién es este cliente?" / "cuéntame sobre {account}" / implícito antes de ejecutar
draft-a-reply. - timeline - "muéstrame la línea de tiempo completa de {account}" / "historial de {customer}" / implícito antes de
review-my-support scope=account-reviewodraft-a-lifecycle-message type=renewal. - health - "califica la salud de {account}" / "¿cómo va {customer}?" / "corre health."
- churn-risk - "riesgo de cancelación de {account}" / "busca riesgo de cancelación" / "¿este cliente está en riesgo?"
Conexiones que necesito
Hago el trabajo externo a través de Composio. Antes de ejecutar esta skill, 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.
- CRM (HubSpot / Attio / Salesforce) - trae el nivel de plan, el dueño de la cuenta, el registro de la cuenta. Obligatorio.
- Facturación (Stripe) - trae el ingreso mensual, el plan, la fecha de renovación, señales de downgrade. Obligatorio para
healthychurn-risk. - Bandeja de entrada (Gmail / Outlook) - trae el historial completo de conversación para la vista timeline. Opcional si
conversations.jsonya está poblado.
Si ninguna de las categorías obligatorias está conectada, me detengo y te pido que conectes primero tu CRM.
Información que necesito
Primero leo tu contexto de soporte. Por cada campo obligatorio que falte, te hago UNA pregunta en lenguaje simple (mejor modalidad: app conectada > archivo > URL > pegar texto) y espero.
- Niveles de plan y su peso - Obligatorio. Por qué lo necesito: ordena bien las señales para que la alerta de cancelación de un cliente P1 no quede enterrada. Si falta, pregunto: "¿Qué planes vendes, y cuáles cuentan como tu nivel más alto?"
- Dónde vive el historial de conversaciones - Obligatorio. Por qué lo necesito: necesito traer la línea de tiempo completa de la cuenta. Si falta, pregunto: "¿Qué bandeja de entrada o help-desk tiene los hilos de tus clientes? ¿Prefieres que lo traiga de una app conectada o subes una exportación reciente?"
- Cómo se ve "en riesgo" para ti - Obligatorio para
health/churn-risk. Por qué lo necesito: los umbrales de VERDE / AMARILLO / ROJO vienen de tu propia definición, no de la mía. Si falta, pregunto: "¿Qué señales te indican que un cliente está por cancelar? ¿Caída de uso, aumento de tickets de soporte, lenguaje de cancelación, algo más?"
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 · 73 lines · 92 tokens per session scan A 997196bec66e
buscar-un-cliente is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,681 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…