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 ANFAIA/ClimaSafe --skill climasafeaigit clone --depth 1 https://github.com/ANFAIA/ClimaSafeWrote 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/anfaia/climasafe/climasafeai)<a href="https://agentmods.dev/skills/anfaia/climasafe/climasafeai"><img src="https://agentmods.dev/badge/skills/anfaia/climasafe/climasafeai/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/anfaia/climasafe/climasafeai"><img src="https://agentmods.dev/badge/skills/anfaia/climasafe/climasafeai.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 | $0.00060 | $0.03011 |
| Opus 5 | $0.00030 | $0.01505 |
| Sonnet 5 | $0.00012 | $0.00602 |
| Haiku 4.5 | $0.00006 | $0.00301 |
Grade A, and why
climasafeai scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L "https://github.com/ollama/ollama/releases/download/v0.32.5/ollama-linux-amd64.tar.zst" \ How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClimaSafeAI — Predicción de riesgo térmico
Sistema completo de predicción de riesgo térmico personalizado. Combina un ensemble de modelos (XGBoost, LSTM, fórmulas físicas) con 27 factores de riesgo científicos, personalización individual y conformal prediction.
Cobertura: calor y frío extremo en España peninsular.
Arquitectura
Usuario → Bot Telegram / MCP / API REST
↓
[Predictor] → Ensemble (XGBoost + LSTM + Fórmula)
↓
Personalización (edad, sexo, IMC, comorbilidades, medicación,
fototipo, situación social, aclimatación, actividad)
↓
Safety Overrides (HI ≥ 39°C → EXTREMO, WC ≤ -25°C → EXTREMO)
↓
Conformal Prediction (α = 0.1)
↓
Respuesta + recomendaciones
Tres modos de conversación (auto‑detección):
- Qwen 2.5 fine‑tuneado → mejor experiencia (requiere GPU)
- Qwen 2.5 raw + RAG → responde preguntas de fondo citando fuentes (CPU)
- Bot determinista → fallback seguro sin LLM
Requisitos
| Dependencia | Versión | ¿Cuándo? |
|---|---|---|
| Python | >= 3.12 | siempre (ver pyproject.toml) |
uv |
cualquiera reciente | siempre |
make |
cualquiera | opcional (targets de conveniencia) |
| Ollama | v0.32.5+ | solo LLM local (Qwen 2.5 + RAG) |
Claves API (.env) |
— | ver tabla abajo |
El resto de dependencias Python se instalan con uv sync desde
pyproject.toml (numpy, pandas, scikit-learn, mcp>=1.28.1,
sqlite-vec, litellm, ...). No hace falta Docker.
Setup reproducible
git clone https://github.com/ANFAIA/ClimaSafe.git
cd ClimaSafe
# 1. Entorno
uv sync
# 2. Claves API — copia y rellena
cp .env.example .env
| Variable | ¿Obligatoria? | Uso |
|---|---|---|
AEMET_API_KEY |
no | Datos AEMET OpenData |
OpenUV_API_KEY |
no | Índice UV |
TELEGRAM_BOT_TOKEN |
solo bot Telegram | Token de @BotFather |
GEMINI_API_KEY |
solo RAG Gemini | ask_rag_mcp / Paper Scout |
GROQ_API_KEY |
no (la sustituye el LLM local) | LLM externo (legado) |
CLIMASAFE_MCP_TOKEN |
solo MCP con identidad | Token del llamante MCP |
CLIMASAFE_MCP_WRITE_TOKEN |
solo MCP con escritura | Token de escritura MCP |
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.
- 9d ago First seen · 285 lines · 60 tokens per session scan A e33d5abec027
climasafeai is a skill published in the GitHub repository ANFAIA/ClimaSafe (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 3,011 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
master-buddhaghosa
A reference-based guide to Buddhaghosa, a fifth-century Theravāda Buddhist scholar, and the meditation and doctrine explained in his works. It covers the Three Trainings—ethics, concentration, and wisdom—along with meditation subjects and stages of insight.
video_action_recognition
Technical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules.
flavormancer
Bench-chemistry flavor & aroma analysis from chemical structure. Use when working on food/beverage flavor formulation, ingredient substitution, or molecular taste/aroma questions: predict a molecule's taste (6 heads) and aroma (24 heads); analyze a whole formulation "before you pour" (blended note-profile…
science_writing_expert
A writing guide for explaining science and technology to general readers in clear, everyday language.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
tooluniverse
Access 1000+ scientific tools through ToolUniverse for drug discovery, protein analysis, genomics, literature search, clinical data, ADMET prediction, molecular docking, and more. Use when the user needs biomedical or scientific research capabilities.