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 Mazalucas/El-DT-Lightweight-Army --skill analisis-propuestagit 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/skills/mazalucas/el-dt-lightweight-army/analisis-propuesta)<a href="https://agentmods.dev/skills/mazalucas/el-dt-lightweight-army/analisis-propuesta"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/analisis-propuesta/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/mazalucas/el-dt-lightweight-army/analisis-propuesta"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/analisis-propuesta.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 | $0.00083 | $0.01595 |
| Opus 5.5 | $0.00033 | $0.00638 |
| Sonnet 5.5 | $0.00017 | $0.00319 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
analisis-propuesta 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocolos DT (heredar)
Orquestador: ordenar, cuestionar, alternativas, Contexto consultado, Puntos ciegos. Este skill no delega en un subagente del catálogo de 23.
Activación
/analisis-propuesta, mención de esta skill, o pedido explícito de panel multi-modelo sobre un plan ya escrito.
Diferencia con /cuestionar: /cuestionar es un solo modelo, preguntas y trade-offs sin panel ni Task con otros LLM. /analisis-propuesta exige propuesta congelada y al menos dos familias de modelo además del autor.
Mandato duro (no negociable)
- No implementar — ni el plan evaluado ni mejoras sugeridas. Sin editar código,
docs/, reglas, skills,vitals/, config versionada, commits, canvas ni informes en disco. - Solo leer — el repo y docs pueden consultarse para contrastar el plan con la realidad.
- Sin garantías — prohibido afirmar que el plan asegura el objetivo al 100%. Usar condiciones de fallo (
references/rubrica.md). Porcentajes solo comoDERIVADO(regla16). - Sin plan inventado — si el usuario no pegó o no hay plan en el hilo, pedir el texto del plan y el objetivo; no redactar un plan sustituto para evaluarlo.
- Diversidad real — no simular tres voces con un solo modelo. Si no hay panel diverso, parar y explicar (ver §Selección de panel).
/yo no es obligatorio: no hay escritura en el repo.
Entrada mínima (congelar en el prompt)
Antes de lanzar panelistas, el orquestador fija un bloque Brief congelado (chat o prompt de Task, no archivo):
- Objetivo declarado
- Restricciones (tiempo, stack, presupuesto, compliance)
- Fuera de alcance
- Plan / propuesta (texto completo)
- Modelo autor (slug del modelo que escribió el plan, si se conoce; si no,
desconocidoy excluir soloinheritdel panel)
Todos los panelistas reciben el mismo brief.
Selección de panel
- Leer
vitals/config/analisis-propuesta.yaml. - Cruzar con los slugs disponibles en la sesión (
available_subagent_modelsen Task). - Por cada familia en orden del YAML, elegir el primer slug listado que exista en la sesión y no esté en
never_panelni sea el modelo autor. - Tomar hasta
panel_size(default 3) slugs de familias distintas. - Parar si hay menos de 2 familias elegibles además del autor (o menos de 2 en total si autor desconocido). Mensaje: panel no diverso; sugerir
/cuestionaro ampliar modelos en el IDE.
What ships with it
1 file 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.
- 1mo ago First seen · 115 lines · 83 tokens per session scan A 894014caad4c
analisis-propuesta is a skill published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,595 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
world-builder
Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) development methodology with multi-agent orchestration. Use when running a structured spec-to-code workflow or decomposing a feature through the SPARC phases.
code-review
Orchestrates code review by detecting the project language and architecture, then routing to the appropriate specialized review skill (code-review-go, code-review-typescript, code-review-python, code-review-php, code-review-architecture). Falls back to the generic checklist when no specific skill applies. Invoked when…
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.
dale-lenses
Reframe an already bounded, difficult engineering, product, operational, or strategic question through one rigorous reasoning lens and at most one genuinely opposing lens, producing a falsifiable model, decision cruxes, and evidence needs instead of a tour of frameworks. Use when the user explicitly invokes…