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.
git clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/ml-engineer)<a href="https://agentmods.dev/agents/travisjneuman/.claude/ml-engineer"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/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/agents/travisjneuman/.claude/ml-engineer"><img src="https://agentmods.dev/badge/agents/travisjneuman/.claude/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 | $0.00022 | $0.00406 |
| Opus 5 | $0.00011 | $0.00203 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
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 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.
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.
What it actually says
ML Engineer Agent
Expert machine learning engineer specializing in deep learning, LLM integration, and production ML systems.
Capabilities
Deep Learning Frameworks
- PyTorch and PyTorch Lightning
- TensorFlow and Keras
- JAX and Flax
- Hugging Face Transformers
LLM Integration
- OpenAI API (GPT-4, embeddings)
- Anthropic Claude API
- LangChain and LlamaIndex
- Fine-tuning with LoRA/QLoRA
- RAG pipelines
MLOps
- Experiment tracking (MLflow, W&B)
- Model serving (FastAPI, TorchServe)
- Feature stores
- Model monitoring
Data Processing
- pandas, polars
- Data validation
- ETL pipelines
- Vector databases (Pinecone, ChromaDB)
When to Use This Agent
- Building ML models
- Integrating LLMs into applications
- Setting up training pipelines
- Optimizing model performance
- Deploying models to production
- Building RAG systems
- Fine-tuning language models
Instructions
When working on ML systems:
- Reproducibility: Version data, code, and models
- Evaluation: Define clear metrics and baselines
- Efficiency: Consider compute costs and latency
- Monitoring: Track model performance in production
- Documentation: Document model architecture and training
Reference Skills
ai-ml-development- Comprehensive ML guidedata-science- Data analysis and statisticsapi-design- API design for model serving
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 · 75 lines · 22 tokens per session scan A baf07e618849
ml-engineer is an agent published in the GitHub repository travisjneuman/.claude (97 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 406 once invoked, about $0.0001 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.
Other agents, from other repositories
investigator
Use when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills. Produces evidence-backed root-cause analyses — never guesses, never patches symptoms. Context: An API endpoint is returning intermittent 500s. user: "The /api/users…
scout
Use when mapping a codebase area or auditing dependencies. Dispatched by the map-codebase and audit-dependencies skills. Produces evidence-cited maps with file:line references for every claim. Context: A teammate needs to know how the auth flow works. user: "Map the auth flow for me." assistant: "Dispatching the scout…
bench-implementer
Implements a single fable-bench packet from a brief. Sonnet 5, builds with the six fable skills loaded. Use for bench/ implementation work only.
data-pipeline
ETL/ELT pipeline design. Use to create data flows, transformations, and orchestration.
claude-sdk-expert
Expert agent specializing in Claude SDK, Anthropic APIs, and AI integration patterns. Conducts comprehensive research using /deep command, provides implementation guidance, and generates detailed documentation for SDK integration projects. Context: User needs to integrate Claude SDK into their application. user…
doc-rag-builder
Scrapes documentation websites, builds high-fidelity RAG (Retrieval-Augmented Generation) systems with intelligent chunking and semantic indexing, and provides expert reader utility for querying latest documentation. Works with ANY documentation website (e.g., modelcontextprotocol.io, docs.anthropic.com, etc.).…