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-candidatosgit 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-candidatos)<a href="https://agentmods.dev/skills/gethouston/houston/buscar-candidatos"><img src="https://agentmods.dev/badge/skills/gethouston/houston/buscar-candidatos/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-candidatos"><img src="https://agentmods.dev/badge/skills/gethouston/houston/buscar-candidatos.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 | $0.00078 | $0.01529 |
| Opus 5 | $0.00039 | $0.00764 |
| Sonnet 5 | $0.00016 | $0.00306 |
| Haiku 4.5 | $0.00008 | $0.00153 |
Grade A, and why
buscar-candidatos 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buscar candidatos
Cuándo usarla
- Explícito: "encuentra candidatos para {puesto}", "busca ingenieros en GitHub", "arma una lista de búsqueda para {puesto}", "busca 20 candidatos para {puesto} desde {señal}".
- Variante de creación de rúbrica: "actualiza la rúbrica del {puesto}", "define los requisitos indispensables para la vacante de {puesto}": pregunto una vez por el nivel objetivo, los 3 requisitos indispensables principales, las 3 cualidades deseables principales, 2 a 3 señales de alerta, escribo
reqs/{role-slug}.md, y me detengo ahí (sin hacer la búsqueda) para que cualquier otra habilidad de contratación lea la rúbrica primero. - Implícito: lo inicia el founder al arrancar una ronda de contratación, o durante una sesión de planificación de vacantes.
- Seguro por puesto y por señal. Mantengo las listas cortas (máximo 30 por pasada) para que las clasificaciones tengan sentido.
Conexiones que necesito
Ejecuto el trabajo externo a través de Composio. Antes de correr esta habilidad reviso que las categorías de abajo estén conectadas. Si falta alguna, la nombro, te pido que la conectes desde la pestaña de Integraciones y me detengo.
- Scraping web (Firecrawl): para traer perfiles públicos y páginas de señal. Obligatorio.
- Ingeniería (GitHub): para evaluar colaboradores de código abierto y leer señales de repositorios. Obligatorio cuando la fuente es GitHub.
- Scraping web (LinkedIn): para evaluar perfiles públicos de LinkedIn. Obligatorio cuando la fuente es LinkedIn.
- ATS (Ashby, Greenhouse, Lever, Workable): para descartar duplicados contra el pipeline existente. Opcional.
Si ninguna de las categorías obligatorias está conectada, me detengo y te pido que conectes Firecrawl primero.
Información que necesito
Primero leo tu contexto de personal. Por cada campo obligatorio que falte, hago UNA pregunta en lenguaje simple (mejor modalidad: app conectada > archivo > URL > texto pegado) y espero.
- Rúbrica del puesto: Obligatorio. Por qué lo necesito: evalúo a cada candidato contra tus requisitos indispensables. Si falta, pregunto: "¿Para qué puesto estamos buscando, en qué nivel, y cuáles son tus tres requisitos indispensables principales?"
- Fuente de señal: Obligatorio. Por qué lo necesito: necesito un lugar de dónde traer nombres. Si falta, pregunto: "¿De dónde debería buscar? ¿Una organización de GitHub, una búsqueda en LinkedIn, una lista de comunidad, o una lista de asistentes a una conferencia?"
- Empresas a excluir: Opcional. Por qué lo necesito: mantiene fuera de la lista a personas que ya descartaste antes. Si no lo tienes, sigo con TBD.
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 · 62 lines · 78 tokens per session scan A f4cbc18d95f2
buscar-candidatos is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,529 once invoked, about $0.0004 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
hps-retro-tv
A family history told through five decades of home movies — the opening question, the eras, and what the footage reveals. Built as a decision-grade story deck for family, close friends.
hps-memphis-pop
A pop-culture retrospective on how 1980s design language shaped today's apps — the scenes, the turning point, and the takeaway. Built as a decision-grade story deck for talk audience, design community.
html-ppt-zhangzara-pink-script
A wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends.
html-ppt-zhangzara-8-bit-orbit
A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
error-recovery-skill
Handle errors gracefully with retry strategies and fallback patterns.