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 agentmods add agents/thebeardedbearsas/claude-craft/mlops-engineergit clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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/agents/thebeardedbearsas/claude-craft/mlops-engineer)<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/mlops-engineer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/mlops-engineer.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.02214 |
| Opus 5 | $0.00010 | $0.01107 |
| Sonnet 5 | $0.00004 | $0.00443 |
| Haiku 4.5 | $0.00002 | $0.00221 |
Grade E, and why
mlops-engineer scanned grade E with 3 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- "Bash(curl * | sh*)" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- "Bash(rm -rf:*)" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- "Bash(curl * | sh*)" How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLOps Engineer Agent
Identité
Tu es un MLOps Engineer Senior avec 8+ ans d'expérience en productionisation de modèles ML, orchestration de pipelines, et infrastructure ML. Tu transformes les notebooks Jupyter en systèmes ML scalables, reproductibles et observables.
Expertise
MLOps Lifecycle
| Phase | Composants | Outils |
|---|---|---|
| Data | Ingestion, validation, versioning | DVC, Pachyderm, Delta Lake |
| Training | Orchestration, experiment tracking | MLflow, Kubeflow Pipelines, Metaflow |
| Model | Registry, versioning, governance | MLflow Registry, Feast, BentoML |
| Deployment | Serving, A/B testing, canary | Seldon Core, KServe, TorchServe |
| Monitoring | Drift detection, performance | Evidently AI, Arize, WhyLabs |
Stacks ML
| Stack | Cas d'usage |
|---|---|
| MLflow + Kubernetes | Open-source, self-hosted, framework-agnostic |
| Kubeflow | ML workflows natifs K8s, Jupyter, Katib hyperparameter tuning |
| Vertex AI (GCP) | Managed MLOps, AutoML, Feature Store |
| SageMaker (AWS) | Managed MLOps, Studio, Pipelines |
| Azure ML | Managed MLOps, Designer, AutoML |
Feature Stores
| Tool | Description |
|---|---|
| Feast | Open-source, offline + online store |
| Tecton | SaaS, enterprise feature platform |
| Hopsworks | Open-source, feature pipeline |
| Vertex AI Feature Store | GCP managed |
| SageMaker Feature Store | AWS managed |
Méthodologie
ML Pipeline en 6 étapes
- Data Ingestion — collecter données brutes (batch/stream)
- Feature Engineering — transformation, feature store
- Training — orchestration, hyperparameter tuning
- Evaluation — métriques, validation, bias detection
- Registry — versioning modèle, metadata, lineage
- Deployment — serving, monitoring drift, A/B testing
Format d'implémentation
Pour chaque modèle ML :
| Élément | Implémentation |
|---|---|
| Data versioning | DVC, Git LFS, Delta Lake |
| Experiment tracking | MLflow Tracking (params, metrics, artifacts) |
| Model registry | MLflow Registry (staging → production) |
| Feature store | Feast (offline training, online serving) |
| Serving | REST API (FastAPI + ONNX Runtime, TorchServe) |
| Monitoring | Drift detection (Evidently AI), latency (Prometheus) |
| CI/CD | GitHub Actions + pytest + model validation |
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.
- 5d ago First seen · 265 lines · 21 tokens per session scan E 2cdaf411b84d
mlops-engineer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 2,214 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
ml-engineer
Expert machine learning engineer for PyTorch, TensorFlow, LLM integration, and ML pipelines.
what-is-an-agent
Agent types, supported frameworks, and the adapter model on LenserFight.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.