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 MartinOlivero/saas-legal-docs --skill legal-docsgit clone --depth 1 https://github.com/MartinOlivero/saas-legal-docsWrote 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/martinolivero/saas-legal-docs/legal-docs)<a href="https://agentmods.dev/skills/martinolivero/saas-legal-docs/legal-docs"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-legal-docs/legal-docs/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/martinolivero/saas-legal-docs/legal-docs"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-legal-docs/legal-docs.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 | $0.00329 | $0.03470 |
| Opus 5 | $0.00164 | $0.01735 |
| Sonnet 5 | $0.00066 | $0.00694 |
| Haiku 4.5 | $0.00033 | $0.00347 |
Grade A, and why
legal-docs 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 12d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legales para productos digitales
Genera y audita documentos legales deduciéndolos del código real, no de una plantilla. Cubre Argentina, Unión Europea, Estados Unidos, Brasil y Reino Unido, cada una con su tabla normativa verificada contra fuente primaria.
Por qué existe: los generadores de legales rellenan un formulario y producen un texto genérico que describe un producto que no es el tuyo. Esta skill hace lo contrario: lee el esquema, los proveedores y los píxeles, y escribe lo que ese producto efectivamente hace. En modo auditoría, compara lo que el documento promete contra lo que el código cumple.
Analogía: una plantilla es un traje comprado hecho. Le sobra tela de un lado y le falta del otro, y desde lejos parece que te queda. Esta skill toma las medidas.
Los seis no negociables
Si alguno se rompe, la salida no sirve. No son sugerencias.
- Determinar la jurisdicción antes que nada. No se deduce del código: un producto en Vercel con la interfaz en español puede vender a treinta países. Preguntar → Paso 0. Escribir un documento argentino para un producto global lo deja desprotegido justo donde vende, y es el mismo error que una plantilla europea para un producto argentino.
- Verificar vigencia antes de escribir. El modelo recuerda normativa vieja. Cada tabla normativa tiene su § Verificación obligatoria. Correrla, siempre.
- Leer el producto antes de redactar. Esquema, código, proveedores, píxeles → Paso 2.
- No prometer lo que el producto no hace. Sin respaldos verificados, el documento no dice que hay respaldos. Es la regla que más valor agrega y la que más se rompe.
- Frenar sin identificación del responsable. Razón social o nombre, identificación fiscal
y domicilio. Si el usuario no los tiene, se entrega el borrador marcado
[FALTA]y no se publica. - Decir el límite en la salida, no solo acá. Todo documento generado cierra con el aviso de revisión profesional. Esto produce un borrador informado, no un documento validado por un abogado.
What ships with it
7 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.
- 12d ago First seen · 235 lines · 0 tokens per session scan A a3a07c1c1613
legal-docs is a skill published in the GitHub repository MartinOlivero/saas-legal-docs (1 stars, last pushed 24d ago), licensed MIT. It adds 329 tokens to every session and 3,470 once invoked, about $0.0016 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 2026-08-31.
Other skills, from other repositories
gdpr-data-handling-note
Drafts a plain-language data handling notice for a journalistic or media production project that involves collecting, storing, or processing personal data — structured to meet GDPR transparency requirements while remaining understandable to non-lawyers.
gdpr-note-writer
Drafts a GDPR compliance note for a specific piece of journalistic content or data collection activity — documenting the lawful basis for processing personal data, what data is held, how long it is retained, and who has access.
privacy-generator
Generates comprehensive privacy policies by scanning websites for data collection signals including cookies, forms, payment processors, and third-party scripts. Use when launching a website or app that collects user data and needs GDPR/CCPA compliance. Trigger with "/privacy-generator" or "create a privacy policy for…
terms-generator
Generates comprehensive terms of service by analyzing a website or application to detect business type, data collection, and user interactions. Use when launching a website, app, or SaaS product that needs terms of service with GDPR/CCPA compliance. Trigger with "/terms-generator" or "create terms of service for my…
children-data-minimization
Implements strict data minimization and retention limits for children's personal data under GDPR Art. 5(1)(c), Recital 38, UK AADC Standard 8, and COPPA Section 312.7. Covers strict necessity testing, shorter retention periods, limited profiling, parental dashboard design, and automated deletion. Keywords: data…
children-deletion-requests
Manages deletion requests for children's personal data. Covers parental-initiated versus child-initiated requests, age of capacity assessment, identity verification, scope determination, third-party notification obligations, and regulatory timelines under GDPR Art. 17, COPPA Section 312.6, and UK AADC Standard 15.…