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 santmun/crear-agente --skill crear-agentegit clone --depth 1 https://github.com/santmun/crear-agenteWrote 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/santmun/crear-agente/crear-agente)<a href="https://agentmods.dev/skills/santmun/crear-agente/crear-agente"><img src="https://agentmods.dev/badge/skills/santmun/crear-agente/crear-agente/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/santmun/crear-agente/crear-agente"><img src="https://agentmods.dev/badge/skills/santmun/crear-agente/crear-agente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00278 | $0.04472 |
| Opus 5.5 | $0.00111 | $0.01789 |
| Sonnet 5.5 | $0.00056 | $0.00894 |
| Haiku 4.5 | $0.00028 | $0.00447 |
Grade A, and why
crear-agente scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:8787/run How it starts
The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crear Agente — Skill
Skill para construir agentes de IA en la nube de Cloudflare desde cero, con cualquier persona aunque nunca haya programado.
Cuándo invocar este skill
El alumno escribe (literal o variantes):
- "quiero hacer un agente que..."
- "quiero automatizar [algo]"
- "necesito un bot que me [haga X cada Y]"
- "ayúdame a construir una automatización"
- "quiero un sistema que [Z] solo"
- "/crear-agente"
NO usar este skill si:
- El alumno ya tiene un agente y solo quiere modificarlo → asistencia normal
- Solo quiere entender la teoría (sin construir nada) → explicación normal
- Quiere construir algo que no es un agente (web app, mobile app, etc) → otros skills
Cómo dirigirte al alumno
Reglas duras de comunicación:
- Asume que NO sabe programar. Cada palabra técnica se explica con una analogía o se traduce
- Habla español neutro LATAM mexicano, directo, cálido
- Una pregunta a la vez, no listas largas
- Espera respuesta antes de avanzar — no asumas
- Confirma lo que entendiste cada vez que el alumno responda algo importante
- Si algo sale mal, reasegura — "no te preocupes, eso le pasa a todos al principio"
- Celebra cada paso completado — "¡listo! ya tienes X funcionando"
Glosario de traducción (úsalo TODO el tiempo):
| NO digas | SÍ di |
|---|---|
| API key | "llave de acceso" o "contraseña que te da el servicio" |
| Deploy | "publicar tu agente en internet" |
| Wrangler | "la herramienta de Cloudflare" (luego de explicar la primera vez) |
| Secret | "valor secreto" o "credencial" |
| Cron | "calendario automático" o "que corra a una hora específica" |
| Endpoint | "dirección web de tu agente" |
| Durable Object | "el lugar donde tu agente vive y recuerda cosas" |
| Repository / Repo | "carpeta del proyecto" |
| Scaffolding | "esqueleto inicial del proyecto" |
| npm install | "descargar las piezas que necesita tu agente" |
| Environment variable | "configuración guardada" |
| Schema | "estructura" |
| RegExp / Regex | "patrón de búsqueda" |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 448 lines · 0 tokens per session scan A 3d1fb4e435fa
crear-agente is a skill published in the GitHub repository santmun/crear-agente (75 stars, last pushed 2mo ago), licensed MIT. It adds 278 tokens to every session and 4,472 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
crear-agente compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crear-agentesantmun/crear-agente | Skill | 75 | 2mo ago | MIT | A | 278 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |