Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skillsnpx agentmods add skills/ricneves-ai/flowgrammers-skills/senior-ml-engineerWrote 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/ricneves-ai/flowgrammers-skills/senior-ml-engineer)<a href="https://agentmods.dev/skills/ricneves-ai/flowgrammers-skills/senior-ml-engineer"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/senior-ml-engineer/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/ricneves-ai/flowgrammers-skills/senior-ml-engineer"><img src="https://agentmods.dev/badge/skills/ricneves-ai/flowgrammers-skills/senior-ml-engineer.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 | $0.00110 | $0.02551 |
| Opus 5 | $0.00055 | $0.01275 |
| Sonnet 5 | $0.00022 | $0.00510 |
| Haiku 4.5 | $0.00011 | $0.00255 |
Grade A, and why
senior-ml-engineer 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 8d 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.
HEALTHCHECK CMD curl -f http://localhost:8080/health || exit 1 How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engenheiro de ML Sênior
Padrões de engenharia de ML em produção para implantação de modelos, infraestrutura MLOps e integração de LLM.
Sumário
- Workflow de Implantação de Modelo
- Configuração de Pipeline MLOps
- Workflow de Integração de LLM
- Implementação de Sistema RAG
- Monitoramento de Modelo
- Documentação de Referência
- Ferramentas
Workflow de Implantação de Modelo
Implante um modelo treinado em produção com monitoramento:
- Exporte o modelo para formato padronizado (ONNX, TorchScript, SavedModel)
- Empacote o modelo com dependências em container Docker
- Implante no ambiente de staging
- Execute testes de integração no staging
- Implante canary (5% do tráfego) em produção
- Monitore latência e taxas de erro por 1 hora
- Promova para produção completa se as métricas passarem
- Validação: latência p95 < 100ms, taxa de erro < 0,1%
Template de Container
FROM python:3.11-slim
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY model/ /app/model/
COPY src/ /app/src/
HEALTHCHECK CMD curl -f http://localhost:8080/health || exit 1
EXPOSE 8080
CMD ["uvicorn", "src.server:app", "--host", "0.0.0.0", "--port", "8080"]
Opções de Serving
| Opção | Latência | Throughput | Caso de Uso |
|---|---|---|---|
| FastAPI + Uvicorn | Baixa | Médio | REST APIs, modelos pequenos |
| Triton Inference Server | Muito Baixa | Muito Alto | Inferência GPU, batching |
| TensorFlow Serving | Baixa | Alto | Modelos TensorFlow |
| TorchServe | Baixa | Alto | Modelos PyTorch |
| Ray Serve | Média | Alto | Pipelines complexos, multi-modelo |
Configuração de Pipeline MLOps
Estabeleça treinamento e implantação automatizados:
- Configure feature store (Feast, Tecton) para dados de treinamento
- Configure tracking de experimentos (MLflow, Weights & Biases)
- Crie pipeline de treinamento com logging de hiperparâmetros
- Registre o modelo no model registry com metadados de versão
- Configure implantação em staging acionada por eventos do registry
- Configure infraestrutura de teste A/B para comparação de modelos
- Habilite monitoramento de drift com alertas
- Validação: Novos modelos avaliados automaticamente contra baseline
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.
- 8d ago First seen · 296 lines · 110 tokens per session scan A 0ced72e361eb
senior-ml-engineer is a skill published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 2,551 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
rag-blueprint
NVIDIA RAG Blueprint deployment, configuration, troubleshooting, and shutdown guidance for Docker, Helm, and library-based RAG stacks.
local-rag-llamaindex
Deploy a local RAG chatbot on Jetson using LlamaIndex + ChromaDB + quantized Llama2-7b (MLC). Uses jetson-containers Docker environment. Requires Jetson with ≥16GB RAM and JetPack 5.1+.
vss-deploy-video-embedding
Use this skill when deploying, operating, integrating, or customizing the VSS RT-Embed Video Embedding microservice. Covers standalone Docker Compose deployment, the /v1 REST API for text/video embeddings and live streams, Redis/Kafka/OTel integration, troubleshooting, and bring-your-own-model (BYOM) custom embedding…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.