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.
git clone --depth 1 https://github.com/Mazalucas/El-DT-Lightweight-ArmyWrote 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/rules/mazalucas/el-dt-lightweight-army/03-catalogo-subagentes)<a href="https://agentmods.dev/rules/mazalucas/el-dt-lightweight-army/03-catalogo-subagentes"><img src="https://agentmods.dev/badge/rules/mazalucas/el-dt-lightweight-army/03-catalogo-subagentes/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/rules/mazalucas/el-dt-lightweight-army/03-catalogo-subagentes"><img src="https://agentmods.dev/badge/rules/mazalucas/el-dt-lightweight-army/03-catalogo-subagentes.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 | $0.00605 | $0.00605 |
| Opus 5 | $0.00302 | $0.00302 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
03-catalogo-subagentes 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 8d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catálogo de Subagentes
Cursor inyecta la descripción de cada subagente en la herramienta Task. Usá este mapa para elegir rol; al delegar, incluí protocolos DT (01-protocolos-dt).
Mapeo rápido (keyword → subagente)
- backend, api, database, server → arquitecto
- frontend, ui, ux, client → frontend o ui-designer (Atelier:
/atelier) - deploy, ci/cd → devops · test, qa → qa
- planilla, csv, totales → data-auditor (
/verificar, regla16) - seguridad, vulnerabilidades, pentest, /hack → hack-audit (
/hack, canvas-first) - ordenar, capturar conocimiento, volcar archivos, dump →
/ordenar(skilldt-ordenar; redacción pesada → doc) - docs, readme → doc · research → researcher
- PRD / SRD / plan MVP → prd-creator / srd-creator / development-planner
- marketing, SEO, ads → marketing-strategist (guías en
.cursor/skills/marketing/*/GUIDE.md) - remotion, video programático → remotion-producer
- operations, monitoring → operations-maintainer
Lista completa y keywords: README — Subagentes.
Prompt de delegación (compacto)
- Contexto de la tarea y formato de salida esperado.
- Protocolos DT: ordenar, cuestionar, alternativas, Contexto consultado, puntos ciegos.
- Si web: bloque stack (
08,vitals/data/engineering/web-stack.yaml). - Si código (
arquitecto,frontend,devops,qa,remotion-producer): bloque reuse — skillengineering-reuse, diff mínimo, sección Qué reutilicé. - Si cifras: bloque numérico — regla
16, script ejecutado, etiquetas de procedencia. - Si seguridad (
hack-audit): bloque defensivo — sin exploits/PoCs; secretos redactados; hallazgo sin traza origen→sink va a Sospechas (tope MEDIUM); evidencia determinista (tools/security/scan-repo.sh) antes del juicio; canvas-first (17) e informe gitignoreado.
Varios pedidos en un mensaje: cada agente solo su rol; fuera de alcance → DEFER: <rol>.
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.
- 8d ago First seen · 38 lines · 605 tokens per session scan A e50978d59266
03-catalogo-subagentes is a cursor rule published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed 1mo ago), licensed MIT. It adds 605 tokens to every session, about $0.0030 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 cursor rules, from other repositories
po
AIOX agent @po - Product Owner.
client-workflow-bootstrap
Cursor rule "client-workflow-bootstrap" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, interview process and gate before generating.
agent-workflow-orchestration
Mandatory PM-orchestrated subagent workflow — main agent is manager, no separate PM subagent.
po
This rule is triggered when the user types @po and activates the Product Owner agent persona.
sm
This rule is triggered when the user types @sm and activates the Scrum Master agent persona.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.