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 PracticalSwan/agent-skills --skill hf-cloud-sagemaker-production-defaultsgit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWrote 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/practicalswan/agent-skills/hf-cloud-sagemaker-production-defaults)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/hf-cloud-sagemaker-production-defaults"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/hf-cloud-sagemaker-production-defaults/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/practicalswan/agent-skills/hf-cloud-sagemaker-production-defaults"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/hf-cloud-sagemaker-production-defaults.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 | $0.00150 | $0.07148 |
| Opus 5 | $0.00075 | $0.03574 |
| Sonnet 5 | $0.00030 | $0.01430 |
| Haiku 4.5 | $0.00015 | $0.00715 |
Grade A, and why
hf-cloud-sagemaker-production-defaults 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 3d 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.
This is a copy
94% identical to hf-cloud-sagemaker-production-defaults — 81 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SageMaker Production Defaults
The difference between a demo endpoint and one you can leave running is: it scales with traffic, it tells you when it breaks, and you can debug it later. This skill makes those three the default rather than optional extras.
By the time this skill runs, the planner has chosen a real-time endpoint, IAM has a usable role, and image-selection has resolved a container URI + AMI version. This skill turns those into an actual deployment.
What gets created
For every endpoint, the skill creates these as a unit:
- SageMaker Model — image + env vars + execution role + S3 artifacts
- Endpoint config — instance type, initial count, optional data capture
- Endpoint — the real-time endpoint serving inference
- Autoscaling target + policy — target tracking on invocations per instance
- CloudWatch alarms — latency, errors, platform overhead
An inference-component deployment (deploy_ic.py) creates the same set with two changes: the endpoint config carries the execution role and ManagedInstanceScaling, and an inference component carries the model. Its autoscaling target is the component, not the variant.
Data capture (logging requests/responses to S3) is off by default — useful for debugging but creates ongoing S3 costs the user didn't necessarily ask for. Enable with --enable-data-capture.
All resources get a consistent tag set including CreatedBy=agentic-deploy-skills for later cleanup.
Defaults and reasoning in references/deployment-template.md.
Running the deployment
For a text-generation LLM (vLLM):
python scripts/deploy.py \
--model-name qwen3-medical \
--image-uri "$IMAGE_URI" \
--inference-ami-version "$AMI" \
--role-arn "$ROLE_ARN" \
--instance-type ml.g5.xlarge \
--region "$REGION" \
--env SM_VLLM_MODEL=Qwen/Qwen3-0.6B \
--env SM_VLLM_HOST=0.0.0.0 \
--env SM_VLLM_TRUST_REMOTE_CODE=true \
--env SM_VLLM_MAX_MODEL_LEN=4096
For an embedding model (TEI, often on CPU):
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 3.1 KB
- LICENSE.txt 11 KB
- references/deployment-template.md 3.6 KB
- scripts/_common.py 4.8 KB runs code
- scripts/deploy_async.py 18 KB runs code
- scripts/deploy_ic.py 20 KB runs code
- scripts/deploy.py 13 KB runs code
- scripts/invoke_endpoint.py 6.4 KB runs code
- scripts/teardown.py 9.2 KB runs code
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.
- 3d ago Changed 95683c54004d
- 4d ago Changed 313c8a2d11ae
- 7d ago First seen · 469 lines · 150 tokens per session scan A 1de68b5bc698
hf-cloud-sagemaker-production-defaults is a skill published in the GitHub repository PracticalSwan/agent-skills (14 stars, last pushed 3d ago), licensed MIT. It adds 150 tokens to every session and 7,148 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to hf-cloud-sagemaker-production-defaults, differing in 81 lines, and is treated as a copy.
Other skills, from other repositories
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
aws-genai-ml-architect
Reasoning skill for designing AWS GenAI and ML architectures for healthcare and life sciences workloads. Use when the user asks to choose between SageMaker and Bedrock, design a RAG system over medical literature, architect clinical NLP or medical imaging inference, plan genomics or drug discovery pipelines on AWS…