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 kokesaurio/mercadolibre-algoritmodigital --skill publicidad-mlgit clone --depth 1 https://github.com/kokesaurio/mercadolibre-algoritmodigitalWrote 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/kokesaurio/mercadolibre-algoritmodigital/publicidad-ml)<a href="https://agentmods.dev/skills/kokesaurio/mercadolibre-algoritmodigital/publicidad-ml"><img src="https://agentmods.dev/badge/skills/kokesaurio/mercadolibre-algoritmodigital/publicidad-ml/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/kokesaurio/mercadolibre-algoritmodigital/publicidad-ml"><img src="https://agentmods.dev/badge/skills/kokesaurio/mercadolibre-algoritmodigital/publicidad-ml.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 | $0.00096 | $0.00706 |
| Opus 5.5 | $0.00038 | $0.00282 |
| Sonnet 5.5 | $0.00019 | $0.00141 |
| Haiku 4.5 | $0.00010 | $0.00071 |
Grade A, and why
publicidad-ml 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publicidad y promociones en MercadoLibre
Análisis de Product Ads y de las promociones que ofrece MercadoLibre, terminando en decisiones: dónde invertir, qué apagar y a qué promo entrar.
Requisito
Herramientas ml_* del conector de Algoritmo Digital. Si no están, indicá
agregar el conector desde https://mcp.algoritmodigital.com.ar y frená.
Product Ads
ml_publicidad(por defecto 30 días; ajustardiassegún lo pedido): inversión, clics, ventas atribuidas y ACOS por campaña.- Leer el ACOS con criterio de margen, no en el aire: cruzar con
ml_rentabilidad. La regla: si ACOS > margen del producto, la campaña vende a pérdida. Un ACOS de 15% es buenísimo con margen 40% y ruinoso con margen 10%. - Diagnóstico por campaña, en este orden:
- ACOS mayor al margen → pausar o bajar puja: está pagando por perder.
- Mucha inversión sin ventas atribuidas → revisar la publicación (precio, título, ficha) antes que la campaña: el ad trae el clic, la publicación no convierte. Usar la skill de mejorar publicaciones si está disponible.
- ACOS bajo y pocas impresiones → oportunidad de escalar inversión.
- Presentar como tabla corta: campaña, inversión, ventas, ACOS, margen del producto, veredicto (escalar / sostener / ajustar / pausar).
Promociones y campañas
ml_promocionessin argumentos: qué campañas ofrece MercadoLibre ahora.- Con
promocion_id: qué publicaciones son elegibles y con qué precio. - Evaluar cada candidata con dos números:
- Descuento que pone el vendedor (no el descuento total: en las co-fondeadas MercadoLibre aporta una parte — decir cuánto pone cada uno).
- Margen resultante al precio final, validado con
ml_rentabilidadoml_simular_precios. Nunca recomendar entrar a pérdida sin decirlo explícitamente; a veces conviene (liquidar stock), pero es una decisión informada del usuario, no un default.
- Recomendar por ítem: entrar / no entrar / entrar solo si ML co-fondea.
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 · 51 lines · 96 tokens per session scan A ea04ccc40459
publicidad-ml is a skill published in the GitHub repository kokesaurio/mercadolibre-algoritmodigital (0 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 706 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 2026-09-09.
publicidad-ml compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| publicidad-mlkokesaurio/mercadolibre-algoritmodigital | Skill | 0 | 1mo ago | MIT | A | 96 | Claude Code, Codex |
| category-opportunity-indexjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 221 | Claude Code |
| growing-leaf-category-trackerjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 213 | Claude Code |
| ml-product-analysisjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 229 | Claude Code |
| seller-copilotjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 230 | Claude Code |
| seller-overview-trackerjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 226 | Claude Code |
| uncontested-niche-finderjoomcode/joompulse-skills | Skill | 54 | 3d ago | MIT | A | 222 | Claude Code |