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 auditoria-legalgit 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/auditoria-legal)<a href="https://agentmods.dev/skills/mazalucas/el-dt-lightweight-army/auditoria-legal"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/auditoria-legal/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/auditoria-legal"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/auditoria-legal.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 | $0.00090 | $0.01973 |
| Opus 5.5 | $0.00036 | $0.00789 |
| Sonnet 5.5 | $0.00018 | $0.00395 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
auditoria-legal 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 25d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocolos DT (heredar)
Subagente del Director Técnico: ordenar, cuestionar, alternativas, Contexto consultado, Puntos ciegos / Mejoras detectadas, post-delegación. Multi-agente: DEFER: <rol>.
Activación
/auditoria-legal, mención de esta skill o delegación → si el IDE expone subagentes, correr como auditoria-legal (.cursor/agents/auditoria-legal.md); si no (Antigravity, Codex), ejecutar este pipeline en la conversación.
Mandato duro
- No es un dictamen. El informe lo dice en la primera línea. No afirmes que "hay una multa de X" como si ya se hubiera impuesto.
- Cifras solo del catálogo, con su fecha.
references/controls.yamlguarda el techo o el precedente y el año. Si hoy es posterior aas_of, no inventes el número nuevo: escribí que la cifra está fechada y hay que contrastarla con la fuente oficial. - Territorio antes de puntuar. Si el producto no dice dónde están los usuarios o a qué mercados vende, preguntá y no cierres el informe en ese turno. Texto y reglas: abajo, sección Territorio.
- Evidencia. Un hallazgo Confirmado necesita un archivo (o la ausencia real de una página o control que el catálogo exige). Sin eso: Sospecha, Sin evidencia o No verificable. Sospecha no puede ser Crítico.
- No verificable no es "cumple". Contrato firmado, registro en un organismo, panel de Stripe, email que ya salió, backups: ver
standing_gapsen el catálogo. Esa sección del informe es obligatoria y va en lenguaje llano. - Por defecto no parches. Proponé el arreglo. Reescribir políticas, avisos o condiciones solo si el usuario lo pide en un mensaje aparte.
- El informe no se commitea. Canvas del IDE +
vitals/work/audits/YYYY-MM-DD-auditoria-legal.md(gitignoreado).
Territorio
Antes del inventario:
- Inferí del repo: idiomas y rutas legales, moneda, dirección, NIF,
countryde Stripe, locales, tiendas, menciones de RGPD, CCPA, LSSI, dominios. - Si con eso podés nombrar los mercados, seguí. Declaralo en el encabezado como inferido y citá la evidencia.
- Si no alcanza, parate y preguntá una sola cosa, con este sentido (podés adaptarla al producto que estás viendo):
What ships with it
3 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.
- 25d ago First seen · 113 lines · 90 tokens per session scan A fd7c9e2dc94b
auditoria-legal is a skill published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,973 once invoked, about $0.0004 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 2026-10-03.
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.
zoning-analysis-nyc
Analyze NYC lot zoning, FAR, height, setbacks, uses, and buildable envelope from PLUTO and the Zoning Resolution. Use for "what can I build"; use nyc-bsa for relief and zoning-envelope for 3D visualization.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
nyc-acris
Look up NYC ACRIS deeds, mortgages, liens, sales, and ownership history. Use for property transactions or recorded ownership; not permits or violations.
nyc-dob-violations
Look up open and resolved DOB and ECB violations for any NYC building, with class, status, and penalty detail. Use when the user asks whether a building has violations, stop-work orders, or outstanding ECB penalties. NYC only; for housing-code violations use /as:nyc-hpd.
nyc-hpd
Look up HPD violations, complaints, and building registration for NYC residential buildings. Use when the user asks about housing-code violations, tenant complaints, or HPD registration at an address. NYC only; for DOB and ECB violations use /as:nyc-dob-violations.