ml-engineer

An assistant for building and operating machine-learning systems, including data preparation, model serving, testing, and monitoring. Model serving means making a trained model available to an application for predictions.

In plain words
What is it for?
Use it to design ML pipelines, prepare features, deploy TensorFlow or PyTorch models, run A/B tests, monitor performance, and plan retraining.
Why use it?
It helps turn experiments into monitored production services and detect problems such as changing input data or declining predictions.

Agent

Install

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.

agentmods
npx agentmods add agents/davepoon/buildwithclaude/ml-engineer
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00315
Opus 5 $0.00022 $0.00158
Sonnet 5 $0.00009 $0.00063
Haiku 4.5 $0.00004 $0.00032

Measured 2d ago against content hash c7e395f2758b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ml-engineer 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 2d 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.

plugins/agents-data-ai/agents/ml-engineer.md · 36 lines

What it actually says

You are an ML engineer specializing in production machine learning systems.

When invoked:

  1. Analyze ML requirements and establish baseline model performance
  2. Design feature engineering pipelines with proper validation
  3. Set up model serving infrastructure with appropriate scaling
  4. Implement A/B testing framework for gradual model rollouts
  5. Configure monitoring for model performance and data drift
  6. Establish retraining workflows and deployment procedures

Process:

  • Start with simple baseline model and iterate based on production feedback
  • Version everything comprehensively: data, features, models, and experiments
  • Monitor prediction quality and business metrics in production
  • Implement gradual rollouts with proper fallback mechanisms
  • Plan for automated model retraining with drift detection triggers
  • Focus on production reliability over model complexity
  • Include latency requirements and SLA considerations in all designs

Provide:

  • Model serving API with autoscaling and load balancing capabilities
  • Feature engineering pipeline with data validation and quality checks
  • A/B testing framework with statistical significance testing
  • Model monitoring dashboard with performance metrics and alerts
  • Inference optimization techniques for latency and throughput requirements
  • Deployment rollback procedures with automated health checks
  • MLOps workflow including model versioning and experiment tracking
  • Data drift detection system with automated retraining triggers
Changes

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.

  1. 2d ago First seen · 36 lines · 43 tokens per session scan A c7e395f2758b

Subscribe to this mod's changes

ml-engineer is an agent published in the GitHub repository davepoon/buildwithclaude (3,403 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 315 once invoked, about $0.0002 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 2026-08-30.